feat: add machine learning engineering workflow

.agents/skills/mle-workflow/SKILL.md

@@ -37,8 +37,6 @@ Use only the lanes that fit the system in front of you. This skill is useful for
 
 Do not treat MLE as separate from software engineering. Most ECC SWE workflows apply directly to ML systems, often with stricter failure modes:
 
-The recommended `minimal --with capability:machine-learning` install keeps the core agent surface available alongside this skill. For skill-only or agent-limited harnesses, pair `skill:mle-workflow` with `agent:mle-reviewer` where the target supports agents.
-
 | SWE surface | MLE use |
 |-------------|---------|
 | `product-capability` / `architecture-decision-records` | Turn model work into explicit product contracts and record irreversible data, model, and rollout choices |

.claude-plugin/marketplace.json

@@ -11,7 +11,7 @@
     {
       "name": "ecc",
       "source": "./",
-      "description": "The most comprehensive Claude Code plugin — 56 agents, 217 skills, 72 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning",
+      "description": "The most comprehensive Claude Code plugin — 54 agents, 204 skills, 69 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning",
       "version": "2.0.0-rc.1",
       "author": {
         "name": "Affaan Mustafa",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ecc",
   "version": "2.0.0-rc.1",
-  "description": "Battle-tested Claude Code plugin for engineering teams — 56 agents, 217 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use",
+  "description": "Battle-tested Claude Code plugin for engineering teams — 54 agents, 204 skills, 69 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use",
   "author": {
     "name": "Affaan Mustafa",
     "url": "https://x.com/affaanmustafa"

.codex-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ecc",
   "version": "2.0.0-rc.1",
-  "description": "Battle-tested Codex workflows — 207 shared ECC skills, production-ready MCP configs, and selective-install-aligned conventions for TDD, security scanning, code review, and autonomous development.",
+  "description": "Battle-tested Codex workflows — 200 shared ECC skills, production-ready MCP configs, and selective-install-aligned conventions for TDD, security scanning, code review, and autonomous development.",
   "author": {
     "name": "Affaan Mustafa",
     "email": "me@affaanmustafa.com",
@@ -15,7 +15,7 @@
   "mcpServers": "./.mcp.json",
   "interface": {
     "displayName": "Everything Claude Code",
-    "shortDescription": "207 battle-tested ECC skills plus MCP configs for TDD, security, code review, and autonomous development.",
+    "shortDescription": "200 battle-tested ECC skills plus MCP configs for TDD, security, code review, and autonomous development.",
     "longDescription": "Everything Claude Code (ECC) is a community-maintained collection of Codex-ready skills and MCP configs evolved over 10+ months of intensive daily use. It covers TDD workflows, security scanning, code review, architecture decisions, operator workflows, and more — all in one installable plugin.",
     "developerName": "Affaan Mustafa",
     "category": "Productivity",

.env.example

@@ -20,16 +20,6 @@ GITHUB_TOKEN=
 # ─── Optional: Package manager override ──────────────────────────────────────
 # CLAUDE_CODE_PACKAGE_MANAGER=npm  # npm | pnpm | yarn | bun
 
-# --- Optional: Astraflow / UModelVerse (OpenAI-compatible) -------------------
-# Global endpoint: https://api.umodelverse.ai/v1
-ASTRAFLOW_API_KEY=
-# ASTRAFLOW_MODEL=gpt-4o-mini
-# ASTRAFLOW_BASE_URL=https://api.umodelverse.ai/v1
-# China endpoint: https://api.modelverse.cn/v1
-ASTRAFLOW_CN_API_KEY=
-# ASTRAFLOW_CN_MODEL=gpt-4o-mini
-# ASTRAFLOW_CN_BASE_URL=https://api.modelverse.cn/v1
-
 # ─── Session & Security ─────────────────────────────────────────────────────
 # GitHub username (used by CI scripts for credential context)
 GITHUB_USER="your-github-username"

.opencode/commands/harness-audit.md

@@ -1,7 +1,3 @@
----
-description: Run a deterministic repository harness audit and return a prioritized scorecard.
----
-
 # Harness Audit Command
 
 Run a deterministic repository harness audit and return a prioritized scorecard.

.opencode/commands/security-scan.md

@@ -1,92 +0,0 @@
----
-description: Run AgentShield against agent, hook, MCP, permission, and secret surfaces.
-agent: everything-claude-code:security-reviewer
-subtask: true
----
-
-# Security Scan Command
-
-Run AgentShield against the current project or a target path, then turn the findings into a prioritized remediation plan.
-
-## Usage
-
-`/security-scan [path] [--format text|json|markdown|html] [--min-severity low|medium|high|critical] [--fix]`
-
-- `path` (optional): defaults to the current project. Use a `.claude/` path, a repo root, or a checked-in template directory.
-- `--format`: output format. Use `json` for CI, `markdown` for handoffs, and `html` for standalone review reports.
-- `--min-severity`: filters lower-priority findings.
-- `--fix`: applies only AgentShield fixes explicitly marked as safe and auto-fixable.
-
-## Deterministic Engine
-
-Prefer the packaged scanner:
-
-```bash
-npx ecc-agentshield scan --path "${TARGET_PATH:-.}" --format text
-```
-
-For local AgentShield development, run from the AgentShield checkout:
-
-```bash
-npm run scan -- --path "${TARGET_PATH:-.}" --format text
-```
-
-Do not invent findings. Use AgentShield output as the source of truth and separate scanner facts from follow-up judgment.
-
-## Review Checklist
-
-1. Identify active runtime findings first:
-   - hardcoded secrets
-   - broad permissions
-   - executable hooks
-   - MCP servers with shell, filesystem, remote transport, or unpinned `npx`
-   - agent prompts that handle untrusted content without defenses
-2. Separate lower-confidence inventory:
-   - docs examples
-   - template examples
-   - plugin manifests
-   - project-local optional settings
-3. For each critical or high finding, return:
-   - file path
-   - severity
-   - runtime confidence
-   - why it matters
-   - exact remediation
-   - whether it is safe to auto-fix
-4. If `--fix` is requested, state the planned edits before applying fixes.
-5. Re-run the scan after fixes and report the before/after score.
-
-## Output Contract
-
-Return:
-
-1. Security grade and score.
-2. Counts by severity and runtime confidence.
-3. Critical/high findings with exact paths.
-4. Lower-confidence findings grouped separately.
-5. A remediation order.
-6. Commands run and whether the scan was local, CI, or npx-backed.
-
-## CI Pattern
-
-Use AgentShield in GitHub Actions for enforced gates:
-
-```yaml
-- uses: affaan-m/agentshield@v1
-  with:
-    path: "."
-    min-severity: "medium"
-    fail-on-findings: true
-```
-
-## Links
-
-- Skill: `skills/security-scan/SKILL.md`
-- Agent: `agents/security-reviewer.md`
-- Scanner: <https://github.com/affaan-m/agentshield>
-
-## Arguments
-
-$ARGUMENTS:
-- optional target path
-- optional AgentShield flags

.opencode/plugins/ecc-hooks.ts

@@ -45,7 +45,7 @@ export const ECCHooksPlugin: ECCHooksPluginFn = async ({
 
   function hasProjectFile(relativePath: string): boolean {
     try {
-      return fs.statSync(resolvePath(relativePath)).isFile()
+      return fs.existsSync(resolvePath(relativePath))
     } catch {
       return false
     }

AGENTS.md

@@ -1,6 +1,6 @@
 # Everything Claude Code (ECC) — Agent Instructions
 
-This is a **production-ready AI coding plugin** providing 56 specialized agents, 217 skills, 72 commands, and automated hook workflows for software development.
+This is a **production-ready AI coding plugin** providing 54 specialized agents, 204 skills, 69 commands, and automated hook workflows for software development.
 
 **Version:** 2.0.0-rc.1
 
@@ -27,7 +27,6 @@ This is a **production-ready AI coding plugin** providing 56 specialized agents,
 | doc-updater | Documentation and codemaps | Updating docs |
 | cpp-reviewer | C/C++ code review | C and C++ projects |
 | cpp-build-resolver | C/C++ build errors | C and C++ build failures |
-| fsharp-reviewer | F# functional code review | F# projects |
 | docs-lookup | Documentation lookup via Context7 | API/docs questions |
 | go-reviewer | Go code review | Go projects |
 | go-build-resolver | Go build errors | Go build failures |
@@ -147,9 +146,9 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
 ## Project Structure
 
 ```
-agents/          — 56 specialized subagents
-skills/          — 217 workflow skills and domain knowledge
-commands/        — 72 slash commands
+agents/          — 54 specialized subagents
+skills/          — 204 workflow skills and domain knowledge
+commands/        — 69 slash commands
 hooks/           — Trigger-based automations
 rules/           — Always-follow guidelines (common + per-language)
 scripts/         — Cross-platform Node.js utilities

README.md

@@ -1,4 +1,4 @@
-**Language:** English | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md) | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md) | [Tiếng Việt](docs/vi-VN/README.md)
+**Language:** English | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md) | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md)
 
 # Everything Claude Code
 
@@ -25,10 +25,10 @@
 
 <div align="center">
 
-**Language / 语言 / 語言 / Dil / Язык / Ngôn ngữ**
+**Language / 语言 / 語言 / Dil / Язык**
 
 [**English**](README.md) | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md)
- | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md) | [Tiếng Việt](docs/vi-VN/README.md)
+ | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md)
 
 </div>
 
@@ -89,7 +89,7 @@ This repo is the raw code only. The guides explain everything.
 ### v2.0.0-rc.1 — Surface Refresh, Operator Workflows, and ECC 2.0 Alpha (Apr 2026)
 
 - **Dashboard GUI** — New Tkinter-based desktop application (`ecc_dashboard.py` or `npm run dashboard`) with dark/light theme toggle, font customization, and project logo in header and taskbar.
-- **Public surface synced to the live repo** — metadata, catalog counts, plugin manifests, and install-facing docs now match the actual OSS surface: 55 agents, 208 skills, and 72 legacy command shims.
+- **Public surface synced to the live repo** — metadata, catalog counts, plugin manifests, and install-facing docs now match the actual OSS surface: 54 agents, 204 skills, and 69 legacy command shims.
 - **Operator and outbound workflow expansion** — `brand-voice`, `social-graph-ranker`, `connections-optimizer`, `customer-billing-ops`, `ecc-tools-cost-audit`, `google-workspace-ops`, `project-flow-ops`, and `workspace-surface-audit` round out the operator lane.
 - **Media and launch tooling** — `manim-video`, `remotion-video-creation`, and upgraded social publishing surfaces make technical explainers and launch content part of the same system.
 - **Framework and product surface growth** — `nestjs-patterns`, richer Codex/OpenCode install surfaces, and expanded cross-harness packaging keep the repo usable beyond Claude Code alone.
@@ -358,7 +358,7 @@ If you stacked methods, clean up in this order:
 /plugin list ecc@ecc
 ```
 
-**That's it!** You now have access to 56 agents, 217 skills, and 72 legacy command shims.
+**That's it!** You now have access to 54 agents, 204 skills, and 69 legacy command shims.
 
 ### Dashboard GUI
 
@@ -456,7 +456,7 @@ everything-claude-code/
 |   |-- plugin.json         # Plugin metadata and component paths
 |   |-- marketplace.json    # Marketplace catalog for /plugin marketplace add
 |
-|-- agents/           # 56 specialized subagents for delegation
+|-- agents/           # 54 specialized subagents for delegation
 |   |-- planner.md           # Feature implementation planning
 |   |-- architect.md         # System design decisions
 |   |-- tdd-guide.md         # Test-driven development
@@ -472,7 +472,6 @@ everything-claude-code/
 |   |-- harness-optimizer.md # Harness config tuning
 |   |-- cpp-reviewer.md      # C++ code review
 |   |-- cpp-build-resolver.md # C++ build error resolution
-|   |-- fsharp-reviewer.md   # F# functional code review
 |   |-- go-reviewer.md       # Go code review
 |   |-- go-build-resolver.md # Go build error resolution
 |   |-- python-reviewer.md   # Python code review
@@ -482,7 +481,6 @@ everything-claude-code/
 |   |-- java-build-resolver.md # Java/Maven/Gradle build errors
 |   |-- kotlin-reviewer.md   # Kotlin/Android/KMP code review
 |   |-- kotlin-build-resolver.md # Kotlin/Gradle build errors
-|   |-- harmonyos-app-resolver.md # HarmonyOS/ArkTS app development
 |   |-- rust-reviewer.md     # Rust code review
 |   |-- rust-build-resolver.md # Rust build error resolution
 |   |-- pytorch-build-resolver.md # PyTorch/CUDA training errors
@@ -526,10 +524,6 @@ everything-claude-code/
 |   |-- springboot-security/        # Spring Boot security (NEW)
 |   |-- springboot-tdd/             # Spring Boot TDD (NEW)
 |   |-- springboot-verification/    # Spring Boot verification (NEW)
-|   |-- quarkus-patterns/           # Quarkus REST, Panache, and messaging patterns (NEW)
-|   |-- quarkus-security/           # Quarkus JWT/OIDC and RBAC security (NEW)
-|   |-- quarkus-tdd/                # Quarkus testing with JUnit, REST Assured, and Dev Services (NEW)
-|   |-- quarkus-verification/       # Quarkus build, test, security, and native verification (NEW)
 |   |-- configure-ecc/              # Interactive installation wizard (NEW)
 |   |-- security-scan/              # AgentShield security auditor integration (NEW)
 |   |-- java-coding-standards/     # Java coding standards (NEW)
@@ -612,7 +606,6 @@ everything-claude-code/
 |   |-- golang/              # Go specific
 |   |-- swift/               # Swift specific
 |   |-- php/                 # PHP specific (NEW)
-|   |-- arkts/               # HarmonyOS / ArkTS specific
 |
 |-- hooks/            # Trigger-based automations
 |   |-- README.md                 # Hook documentation, recipes, and customization guide
@@ -847,7 +840,6 @@ cp -r everything-claude-code/rules/typescript ~/.claude/rules/ecc/   # pick your
 cp -r everything-claude-code/rules/python ~/.claude/rules/ecc/
 cp -r everything-claude-code/rules/golang ~/.claude/rules/ecc/
 cp -r everything-claude-code/rules/php ~/.claude/rules/ecc/
-cp -r everything-claude-code/rules/arkts ~/.claude/rules/ecc/
 
 # Copy skills first (primary workflow surface)
 # Recommended (new users): core/general skills only
@@ -967,7 +959,6 @@ rules/
   golang/          # Go specific patterns and tools
   swift/           # Swift specific patterns and tools
   php/             # PHP specific patterns and tools
-  arkts/           # HarmonyOS / ArkTS patterns and constraints
 ```
 
 See [`rules/README.md`](rules/README.md) for installation and structure details.
@@ -991,9 +982,7 @@ Not sure where to start? Use this quick reference. Skills are the canonical work
 | Update documentation | `/update-docs` | doc-updater |
 | Review Go code | `/go-review` | go-reviewer |
 | Review Python code | `/python-review` | python-reviewer |
-| Review F# code | *(invoke `fsharp-reviewer` directly)* | fsharp-reviewer |
 | Review TypeScript/JavaScript code | *(invoke `typescript-reviewer` directly)* | typescript-reviewer |
-| Develop HarmonyOS apps | *(invoke `harmonyos-app-resolver` directly)* | harmonyos-app-resolver |
 | Audit database queries | *(auto-delegated)* | database-reviewer |
 | Review production ML changes | `mle-workflow` skill + `mle-reviewer` agent | mle-reviewer |
 
@@ -1152,7 +1141,7 @@ Please contribute! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 
 ### Ideas for Contributions
 
-- Language-specific skills (Rust, C#, Kotlin, Java) — Go, Python, Perl, Swift, TypeScript, and HarmonyOS/ArkTS already included
+- Language-specific skills (Rust, C#, Kotlin, Java) — Go, Python, Perl, Swift, and TypeScript already included
 - Framework-specific configs (Rails, FastAPI) — Django, NestJS, Spring Boot, and Laravel already included
 - DevOps agents (Kubernetes, Terraform, AWS, Docker)
 - Testing strategies (different frameworks, visual regression)
@@ -1360,9 +1349,9 @@ The configuration is automatically detected from `.opencode/opencode.json`.
 
 | Feature | Claude Code | OpenCode | Status |
 |---------|-------------|----------|--------|
-| Agents | PASS: 56 agents | PASS: 12 agents | **Claude Code leads** |
-| Commands | PASS: 72 commands | PASS: 35 commands | **Claude Code leads** |
-| Skills | PASS: 217 skills | PASS: 37 skills | **Claude Code leads** |
+| Agents | PASS: 54 agents | PASS: 12 agents | **Claude Code leads** |
+| Commands | PASS: 69 commands | PASS: 31 commands | **Claude Code leads** |
+| Skills | PASS: 204 skills | PASS: 37 skills | **Claude Code leads** |
 | Hooks | PASS: 8 event types | PASS: 11 events | **OpenCode has more!** |
 | Rules | PASS: 29 rules | PASS: 13 instructions | **Claude Code leads** |
 | MCP Servers | PASS: 14 servers | PASS: Full | **Full parity** |
@@ -1465,9 +1454,9 @@ ECC is the **first plugin to maximize every major AI coding tool**. Here's how e
 
 | Feature | Claude Code | Cursor IDE | Codex CLI | OpenCode |
 |---------|------------|------------|-----------|----------|
-| **Agents** | 56 | Shared (AGENTS.md) | Shared (AGENTS.md) | 12 |
-| **Commands** | 72 | Shared | Instruction-based | 35 |
-| **Skills** | 217 | Shared | 10 (native format) | 37 |
+| **Agents** | 54 | Shared (AGENTS.md) | Shared (AGENTS.md) | 12 |
+| **Commands** | 69 | Shared | Instruction-based | 31 |
+| **Skills** | 204 | Shared | 10 (native format) | 37 |
 | **Hook Events** | 8 types | 15 types | None yet | 11 types |
 | **Hook Scripts** | 20+ scripts | 16 scripts (DRY adapter) | N/A | Plugin hooks |
 | **Rules** | 34 (common + lang) | 34 (YAML frontmatter) | Instruction-based | 13 instructions |
@@ -1601,7 +1590,6 @@ Projects built on or inspired by Everything Claude Code:
 | Project | Description |
 |---------|-------------|
 | [EVC](https://github.com/SaigonXIII/evc) | Marketing agent workspace — 42 commands for content operators, brand governance, and multi-channel publishing. [Visual overview](https://saigonxiii.github.io/evc). |
-| [trading-skills](https://github.com/VictorVVedtion/trading-skills) | 68 trading-themed Claude Code skills with pre-trade review prompts and risk gates inspired by market operators. |
 
 Built something with ECC? Open a PR to add it here.
 

README.zh-CN.md

@@ -21,9 +21,9 @@
 
 <div align="center">
 
-**Language / 语言 / 語言 / Dil / Язык / Ngôn ngữ**
+**Language / 语言 / 語言 / Dil**
 
-[**English**](README.md) | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md) | [Türkçe](docs/tr/README.md) | [Русский](docs/ru/README.md) | [Tiếng Việt](docs/vi-VN/README.md)
+[**English**](README.md) | [Português (Brasil)](docs/pt-BR/README.md) | [简体中文](README.zh-CN.md) | [繁體中文](docs/zh-TW/README.md) | [日本語](docs/ja-JP/README.md) | [한국어](docs/ko-KR/README.md) | [Türkçe](docs/tr/README.md)
 
 </div>
 
@@ -160,7 +160,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
 /plugin list ecc@ecc
 ```
 
-**完成！** 你现在可以使用 56 个代理、217 个技能和 72 个命令。
+**完成！** 你现在可以使用 54 个代理、204 个技能和 69 个命令。
 
 ### multi-* 命令需要额外配置
 

agent.yaml

@@ -9,12 +9,10 @@ model:
   fallback:
     - claude-sonnet-4-6
 skills:
-  - agent-architecture-audit
   - agent-eval
   - agent-harness-construction
   - agent-payment-x402
   - agentic-engineering
-  - agentic-os
   - ai-first-engineering
   - ai-regression-testing
   - android-clean-architecture
@@ -63,7 +61,6 @@ skills:
   - e2e-testing
   - energy-procurement
   - enterprise-agent-ops
-  - error-handling
   - eval-harness
   - exa-search
   - fal-ai-media
@@ -71,7 +68,6 @@ skills:
   - foundation-models-on-device
   - frontend-patterns
   - frontend-slides
-  - fsharp-testing
   - git-workflow
   - golang-patterns
   - golang-testing
@@ -99,7 +95,6 @@ skills:
   - logistics-exception-management
   - market-research
   - mcp-server-patterns
-  - motion-ui
   - nanoclaw-repl
   - nextjs-turbopack
   - nutrient-document-processing
@@ -108,7 +103,6 @@ skills:
   - perl-security
   - perl-testing
   - plankton-code-quality
-  - plan-orchestrate
   - postgres-patterns
   - product-lens
   - production-scheduling
@@ -117,10 +111,6 @@ skills:
   - python-testing
   - pytorch-patterns
   - quality-nonconformance
-  - quarkus-patterns
-  - quarkus-security
-  - quarkus-tdd
-  - quarkus-verification
   - ralphinho-rfc-pipeline
   - regex-vs-llm-structured-text
   - repo-scan
@@ -161,7 +151,6 @@ commands:
   - cpp-build
   - cpp-review
   - cpp-test
-  - ecc-guide
   - evolve
   - fastapi-review
   - feature-dev
@@ -200,7 +189,6 @@ commands:
   - pm2
   - projects
   - promote
-  - project-init
   - prp-commit
   - prp-implement
   - prp-plan
@@ -217,7 +205,6 @@ commands:
   - rust-test
   - santa-loop
   - save-session
-  - security-scan
   - sessions
   - setup-pm
   - skill-create

agents/fsharp-reviewer.md

@@ -1,100 +0,0 @@
----
-name: fsharp-reviewer
-description: Expert F# code reviewer specializing in functional idioms, type safety, pattern matching, computation expressions, and performance. Use for all F# code changes. MUST BE USED for F# projects.
-tools: ["Read", "Grep", "Glob", "Bash"]
-model: sonnet
----
-
-You are a senior F# code reviewer ensuring high standards of idiomatic functional F# code and best practices.
-
-When invoked:
-1. Run `git diff -- '*.fs' '*.fsx'` to see recent F# file changes
-2. Run `dotnet build` and `fantomas --check .` if available
-3. Focus on modified `.fs` and `.fsx` files
-4. Begin review immediately
-
-## Review Priorities
-
-### CRITICAL - Security
-- **SQL Injection**: String concatenation/interpolation in queries - use parameterized queries
-- **Command Injection**: Unvalidated input in `Process.Start` - validate and sanitize
-- **Path Traversal**: User-controlled file paths - use `Path.GetFullPath` + prefix check
-- **Insecure Deserialization**: `BinaryFormatter`, unsafe JSON settings
-- **Hardcoded secrets**: API keys, connection strings in source - use configuration/secret manager
-- **CSRF/XSS**: Missing anti-forgery tokens, unencoded output in views
-
-### CRITICAL - Error Handling
-- **Swallowed exceptions**: `with _ -> ()` or `with _ -> None` - handle or reraise
-- **Missing disposal**: Manual disposal of `IDisposable` - use `use` or `use!` bindings
-- **Blocking async**: `.Result`, `.Wait()`, `.GetAwaiter().GetResult()` - use `let!` or `do!`
-- **Bare `failwith` in library code**: Prefer `Result` or `Option` for expected failures
-
-### HIGH - Functional Idioms
-- **Mutable state in domain logic**: `mutable`, `ref` cells where immutable alternatives exist
-- **Incomplete pattern matches**: Missing cases or catch-all `_` that hides new union cases
-- **Imperative loops**: `for`/`while` where `List.map`, `Seq.filter`, `Array.fold` are clearer
-- **Null usage**: Using `null` instead of `Option<'T>` for missing values
-- **Class-heavy design**: OOP-style classes where modules + functions + records suffice
-
-### HIGH - Type Safety
-- **Primitive obsession**: Raw strings/ints for domain concepts - use single-case DUs
-- **Unvalidated input**: Missing validation at system boundaries - use smart constructors
-- **Downcasting**: `:?>` without type test - use pattern matching with `:? T as t`
-- **`obj` usage**: Avoid `obj` boxing; prefer generics or explicit union types
-
-### HIGH - Code Quality
-- **Large functions**: Over 40 lines - extract helper functions
-- **Deep nesting**: More than 3 levels - use early returns, `Result.bind`, or computation expressions
-- **Missing `[<RequireQualifiedAccess>]`**: On modules/unions that could cause name collisions
-- **Unused `open` declarations**: Remove unused module imports
-
-### MEDIUM - Performance
-- **Seq in hot paths**: Lazy sequences recomputed repeatedly - materialize with `Seq.toList` or `Seq.toArray`
-- **String concatenation in loops**: Use `StringBuilder` or `String.concat`
-- **Excessive boxing**: Value types passed through `obj` - use generic functions
-- **N+1 queries**: Lazy loading in loops when using EF Core - use eager loading
-
-### MEDIUM - Best Practices
-- **Naming conventions**: camelCase for functions/values, PascalCase for types/modules/DU cases
-- **Pipe operator readability**: Overly long chains - break into named intermediate bindings
-- **Computation expression misuse**: Nested `task { task { } }` - flatten with `let!`
-- **Module organization**: Related functions scattered across files - group cohesively
-
-## Diagnostic Commands
-
-```bash
-dotnet build                                          # Compilation check
-fantomas --check .                                    # Format check
-dotnet test --no-build                                # Run tests
-dotnet test --collect:"XPlat Code Coverage"           # Coverage
-```
-
-## Review Output Format
-
-```text
-[SEVERITY] Issue title
-File: path/to/File.fs:42
-Issue: Description
-Fix: What to change
-```
-
-## Approval Criteria
-
-- **Approve**: No CRITICAL or HIGH issues
-- **Warning**: MEDIUM issues only (can merge with caution)
-- **Block**: CRITICAL or HIGH issues found
-
-## Framework Checks
-
-- **ASP.NET Core**: Giraffe or Saturn handlers, model validation, auth policies, middleware order
-- **EF Core**: Migration safety, eager loading, `AsNoTracking` for reads
-- **Fable**: Elmish architecture, message handling completeness, view function purity
-
-## Reference
-
-For detailed .NET patterns, see skill: `dotnet-patterns`.
-For testing guidelines, see skill: `fsharp-testing`.
-
----
-
-Review with the mindset: "Is this idiomatic F# that leverages the type system and functional patterns effectively?"

agents/harmonyos-app-resolver.md

@@ -1,173 +0,0 @@
----
-name: harmonyos-app-resolver
-description: HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
-tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
-model: sonnet
----
-
-# HarmonyOS Application Development Expert
-
-You are a senior HarmonyOS application development expert specializing in ArkTS and ArkUI for building high-quality HarmonyOS native applications. You have deep understanding of HarmonyOS system components, APIs, and underlying mechanisms, and always apply industry best practices.
-
-## Core Tech Stack Constraints (Strictly Enforced)
-
-In all code generation, Q&A, and technical recommendations, you MUST strictly follow these technology choices - **no compromise**:
-
-### 1. State Management: V2 Only (ArkUI State Management V2)
-
-- **MUST use**: ArkUI State Management V2 decorators/patterns (use applicable decorators by context), including `@ComponentV2`, `@Local`, `@Param`, `@Event`, `@Provider`, `@Consumer`, `@Monitor`, `@Computed`; use `@ObservedV2` + `@Trace` for observable model classes/properties when needed.
-- **MUST NOT use**: V1 decorators (`@Component`, `@State`, `@Prop`, `@Link`, `@ObjectLink`, `@Observed`, `@Provide`, `@Consume`, `@Watch`)
-
-### 2. Routing: Navigation Only
-
-- **MUST use**: `Navigation` component with `NavPathStack` for route management; use `NavDestination` as root container for sub-pages
-- **MUST NOT use**: Legacy `router` module (`@ohos.router`) for page navigation
-
-## Your Role
-
-- **ArkTS & ArkUI mastery** - Write elegant, efficient, type-safe declarative UI code with deep understanding of V2 state management observation mechanisms and UI update logic
-- **Full-stack component & API expertise** - Proficient with UI components (List, Grid, Swiper, Tabs, etc.) and system APIs (network, media, file, preferences, etc.) to rapidly implement complex business requirements
-- **Best practice enforcement**:
-  - **Architecture**: Modular, layered architecture ensuring high cohesion and low coupling
-  - **Performance**: Use `LazyForEach`, component reuse, async processing for expensive tasks
-  - **Code standards**: Consistent style, rigorous logic, clear comments, compliant with HarmonyOS official guidelines
-
-## Workflow
-
-### Step 1: Understand Project Context
-
-- Read `CLAUDE.md`, `module.json5`, `oh-package.json5` for project conventions
-- Identify existing state management version (V1 vs V2) and routing approach
-- Check `build-profile.json5` for API level and device targets
-
-### Step 2: Review or Implement
-
-When reviewing code:
-- Flag any V1 state management usage - recommend V2 migration
-- Flag any `@ohos.router` usage - recommend Navigation migration
-- Check API level compatibility and permission declarations
-- Verify resource references use `$r()` instead of hardcoded literals
-- Check i18n completeness across all language directories
-
-When implementing features:
-- Use V2 state management exclusively
-- Use Navigation + NavPathStack for routing
-- Define UI constants in resources, reference via `$r()`
-- Add i18n strings to all language directories
-- Consider dark theme support for new color resources
-
-### Step 3: Validate
-
-```bash
-# Build HAP package (global hvigor environment)
-hvigorw assembleHap -p product=default
-```
-
-- Run build after every implementation to verify compilation
-- Check for ArkTS syntax constraint violations
-- Verify permission declarations in `module.json5`
-
-## ArkTS Syntax Constraints (Compilation Blockers)
-
-ArkTS is a strict subset of TypeScript. The following are NOT supported and will cause compilation failures:
-
-**Type System:**
-- No `any` or `unknown` types - use explicit types
-- No index access types - use type names
-- No conditional type aliases or `infer` keyword
-- No intersection types - use inheritance
-- No mapped types - use classes
-- No `typeof` for type annotations - use explicit type declarations
-- No `as const` assertions - use explicit type annotations
-- No structural typing - use inheritance, interfaces, or type aliases
-- No TypeScript utility types except `Partial`, `Required`, `Readonly`, `Record`
-
-**Functions & Classes:**
-- No function expressions - use arrow functions
-- No nested functions - use lambdas
-- No generator functions - use async/await
-- No `Function.apply`, `Function.call`, `Function.bind`
-- No constructor type expressions - use lambdas
-- No constructor signatures in interfaces or object types
-- No declaring class fields in constructors - declare in class body
-- No `this` in standalone functions or static methods
-- No `new.target`
-
-**Object & Property Access:**
-- No dynamic field declaration or `obj["field"]` access - use `obj.field`
-- No `delete` operator - use nullable type with `null`
-- No prototype assignment
-- No `in` operator - use `instanceof`
-- No `Symbol()` API (except `Symbol.iterator`)
-- No `globalThis` or global scope - use explicit module exports/imports
-
-**Destructuring & Spread:**
-- No destructuring assignments or variable declarations
-- No destructuring parameter declarations
-- Spread operator only for arrays into rest parameters or array literals
-
-**Modules & Imports:**
-- No `require()` imports - use regular `import`
-- No `export = ...` syntax - use normal export/import
-- No import assertions
-- No UMD modules
-- No wildcards in module names
-- All `import` statements must precede other statements
-
-**Other:**
-- No `var` keyword - use `let`
-- No `for...in` loops - use regular `for` loops for arrays
-- No `with` statements
-- No JSX expressions
-- No `#` private identifiers - use `private` keyword
-- No declaration merging
-- No index signatures - use arrays
-- No class literals - use named class types
-- Comma operator only in `for` loops
-- Unary operators `+`, `-`, `~` only for numeric types
-- Omit type annotations in `catch` clauses
-
-**Object Literals:**
-- Supported only when compiler can infer the corresponding class/interface
-- Not supported for: `any`/`Object`/`object` types, classes with methods, classes with parameterized constructors, classes with `readonly` fields
-
-## HarmonyOS API Usage Guidelines
-
-- Prefer official HarmonyOS APIs, UI components, animations, and code templates
-- Verify API parameters, return values, API level, and device support before use
-- When uncertain about syntax or API usage, search official Huawei developer documentation - never guess
-- Confirm `import` statements are added at file header before using APIs
-- Verify required permissions in `module.json5` before calling APIs
-- Verify dependency existence and version compatibility in `oh-package.json5`
-- Enforce `@ComponentV2` for all new or modified ArkUI components; when encountering legacy `@Component`, recommend migration to V2
-- Define UI display constants as resources, reference via `$r()` - avoid hardcoded literals
-- Add i18n resource strings to all language directories when creating new entries
-- Check if new color resources need dark theme support (recommended for new projects)
-
-## ArkUI Animation Guidelines
-
-- Prefer native HarmonyOS animation APIs and advanced templates
-- Use declarative UI with state-driven animations (change state variables to trigger animations)
-- Set `renderGroup(true)` for complex sub-component animations to reduce render batches
-- NEVER frequently change `width`, `height`, `padding`, `margin` during animations - severe performance impact
-
-## Behavior Guidelines
-
-- **Proactive refactoring**: If user code contains V1 state management or `router` routing, proactively flag it and refactor to V2 + Navigation
-- **Explain best practices**: Briefly explain why a solution is "best practice" (e.g., performance advantages of `@ComponentV2` over V1)
-- **Rigor**: Ensure code snippets are complete, runnable, and handle common edge cases (empty data, loading states, error handling)
-
-## Output Format
-
-```text
-[REVIEW] src/main/ets/pages/HomePage.ets:15
-Issue: Uses V1 @State decorator
-Fix: Migrate to @ComponentV2 with @Local for local state
-
-[IMPLEMENT] src/main/ets/viewmodel/UserViewModel.ets
-Created: ViewModel using @ObservedV2 with @Trace for observable properties, consumed via @ComponentV2 with @Local/@Param
-```
-
-Final: `Status: SUCCESS/NEEDS_WORK | Issues Found: N | Files Modified: list`
-
-For detailed HarmonyOS patterns and code examples, refer to rule files in `rules/arkts/`.

commands/ecc-guide.md

@@ -1,93 +0,0 @@
----
-description: Navigate ECC's current agents, skills, commands, hooks, install profiles, and docs from the live repository surface.
----
-
-# /ecc-guide
-
-Use this command as a conversational map of Everything Claude Code. It should help the user discover the right ECC surface for their task without dumping the entire README or stale catalog counts.
-
-## Usage
-
-```text
-/ecc-guide
-/ecc-guide setup
-/ecc-guide skills
-/ecc-guide commands
-/ecc-guide hooks
-/ecc-guide install
-/ecc-guide find: <query>
-/ecc-guide <feature-or-file-name>
-```
-
-## Operating Rules
-
-1. Read current repository files before answering when the checkout is available.
-2. Prefer current filesystem/catalog data over hard-coded counts.
-3. Keep the first answer short, then offer specific drill-down paths.
-4. Link users to canonical files instead of copying long sections.
-5. Do not invent commands, skills, agents, or install profiles that are not present.
-
-## What To Inspect
-
-Use these files as the canonical map:
-
-- `README.md` for install paths, reset/uninstall guidance, and high-level positioning
-- `AGENTS.md` for contributor and project-structure guidance
-- `agent.yaml` for exported agent and command surface
-- `commands/` for maintained slash-command shims
-- `skills/*/SKILL.md` for reusable skill workflows
-- `agents/*.md` for delegated agent roles
-- `hooks/README.md` and `hooks/hooks.json` for hook behavior
-- `manifests/install-*.json` for selective install modules, components, and profiles
-- `scripts/ci/catalog.js --json` for live catalog counts when running inside ECC
-
-## Response Patterns
-
-### No Arguments
-
-Give a compact menu:
-
-- setup and install
-- choosing skills
-- command compatibility shims
-- agents and delegation
-- hooks and safety
-- troubleshooting an install
-- finding a specific feature
-
-Then ask what they want to do next.
-
-### Topic Lookup
-
-For topics like `skills`, `commands`, `hooks`, `install`, or `agents`:
-
-1. Summarize the current surface in 3-6 bullets.
-2. Point to the canonical directories/files.
-3. Suggest one or two commands that can verify the state.
-4. Avoid exhaustive lists unless the user asks for one.
-
-### Search Mode
-
-For `find: <query>`:
-
-1. Search the relevant files with `rg`.
-2. Group results by surface: skills, commands, agents, rules, docs, hooks.
-3. Return the strongest matches first with file paths.
-4. Recommend the next action for each match.
-
-### Feature Lookup
-
-For a specific feature name:
-
-1. Check exact paths first, such as `skills/<name>/SKILL.md`, `commands/<name>.md`, and `agents/<name>.md`.
-2. If exact lookup fails, search with `rg`.
-3. Explain what the feature does, when to use it, and what file is canonical.
-4. Mention adjacent features only when they reduce confusion.
-
-## Related Commands
-
-- `/project-init` for stack-aware ECC onboarding of a target project
-- `/harness-audit` for deterministic repo readiness scoring
-- `/skill-health` for skill quality checks
-- `/skill-create` for extracting a new skill from local git history
-- `/security-scan` for Claude/OpenCode configuration security review

commands/project-init.md

@@ -1,86 +0,0 @@
----
-description: Detect a project's stack and produce a dry-run ECC onboarding plan using the repository's install manifests and stack mappings.
----
-
-# /project-init
-
-Create a safe, reviewable ECC onboarding plan for the current project. This command should start in dry-run mode and only write files after explicit user approval.
-
-## Usage
-
-```text
-/project-init
-/project-init --dry-run
-/project-init --target claude
-/project-init --target cursor
-/project-init --skills continuous-learning-v2,security-review
-/project-init --config ecc-install.json
-```
-
-## Safety Rules
-
-1. Default to dry-run. Do not modify `CLAUDE.md`, settings files, rules, skills, or install state until the user approves the concrete plan.
-2. Preserve existing project guidance. If `CLAUDE.md`, `.claude/settings.local.json`, `.cursor/`, `.codex/`, `.gemini/`, `.opencode/`, `.codebuddy/`, `.joycode/`, or `.qwen/` already exists, inspect it and propose a merge/append plan instead of overwriting.
-3. Use ECC's installer and manifest tooling. Do not hand-copy files or clone arbitrary remotes as an install shortcut.
-4. Keep permissions narrow. Any generated settings should match detected build/test/lint tools and avoid broad shell access.
-5. Report exactly what would change before applying anything.
-
-## Detection Inputs
-
-Read the current project root and detect stack signals from:
-
-- package manager files: `package.json`, `package-lock.json`, `pnpm-lock.yaml`, `yarn.lock`, `bun.lockb`
-- language manifests: `pyproject.toml`, `requirements.txt`, `go.mod`, `Cargo.toml`, `pom.xml`, `build.gradle`, `build.gradle.kts`
-- framework files: `next.config.*`, `vite.config.*`, `tailwind.config.*`, `Dockerfile`, `docker-compose.yml`
-- ECC config: `ecc-install.json`
-- optional stack map: `config/project-stack-mappings.json` in the ECC repo
-
-When the ECC checkout is available, use `config/project-stack-mappings.json` as the stack-to-rules/skills reference. If the file is unavailable, fall back to the installed ECC manifests and explicit user choices.
-
-## Planning Flow
-
-1. Identify the target harness. Default to `claude` unless the user asks for `cursor`, `codex`, `gemini`, `opencode`, `codebuddy`, `joycode`, or `qwen`.
-2. Detect stacks from project files and show the evidence for each match.
-3. Resolve the smallest useful ECC plan:
-   - project has an `ecc-install.json`: `node scripts/install-plan.js --config ecc-install.json --json`
-   - user named a profile: `node scripts/install-plan.js --profile <profile> --target <target> --json`
-   - user named skills: `node scripts/install-plan.js --skills <skill-ids> --target <target> --json`
-   - only language stacks are detected: use the legacy language install dry-run with those language names
-4. Run a dry-run apply command before writing:
-
-```bash
-node scripts/install-apply.js --target <target> --dry-run --json <language-or-profile-args>
-```
-
-5. Summarize detected stacks, selected modules/components/skills, target paths, skipped unsupported modules, and files that would be changed.
-6. Ask for approval before applying the non-dry-run command.
-
-## Output Contract
-
-Return:
-
-1. detected stack evidence
-2. proposed target harness
-3. exact dry-run command used
-4. exact apply command to run after approval
-5. files/directories that would be created or changed
-6. warnings about existing files, broad permissions, missing scripts, or unsupported targets
-
-## CLAUDE.md Guidance
-
-If the user wants a `CLAUDE.md` starter, generate it separately from the installer plan and keep it minimal:
-
-- build command, if detected
-- test command, if detected
-- lint/typecheck command, if detected
-- dev server command, if detected
-- repo-specific notes from existing package scripts or manifests
-
-Never replace an existing `CLAUDE.md` without showing a diff and receiving approval.
-
-## Related
-
-- `config/project-stack-mappings.json` for stack-to-surface hints
-- `scripts/install-plan.js` for deterministic plan resolution
-- `scripts/install-apply.js` for dry-run and apply operations
-- `/ecc-guide` for interactive feature discovery before installing

commands/security-scan.md

@@ -1,92 +0,0 @@
----
-description: Run AgentShield against agent, hook, MCP, permission, and secret surfaces.
-agent: everything-claude-code:security-reviewer
-subtask: true
----
-
-# Security Scan Command
-
-Run AgentShield against the current project or a target path, then turn the findings into a prioritized remediation plan.
-
-## Usage
-
-`/security-scan [path] [--format text|json|markdown|html] [--min-severity low|medium|high|critical] [--fix]`
-
-- `path` (optional): defaults to the current project. Use a `.claude/` path, a repo root, or a checked-in template directory.
-- `--format`: output format. Use `json` for CI, `markdown` for handoffs, and `html` for standalone review reports.
-- `--min-severity`: filters lower-priority findings.
-- `--fix`: applies only AgentShield fixes explicitly marked as safe and auto-fixable.
-
-## Deterministic Engine
-
-Prefer the packaged scanner:
-
-```bash
-npx ecc-agentshield scan --path "${TARGET_PATH:-.}" --format text
-```
-
-For local AgentShield development, run from the AgentShield checkout:
-
-```bash
-npm run scan -- --path "${TARGET_PATH:-.}" --format text
-```
-
-Do not invent findings. Use AgentShield output as the source of truth and separate scanner facts from follow-up judgment.
-
-## Review Checklist
-
-1. Identify active runtime findings first:
-   - hardcoded secrets
-   - broad permissions
-   - executable hooks
-   - MCP servers with shell, filesystem, remote transport, or unpinned `npx`
-   - agent prompts that handle untrusted content without defenses
-2. Separate lower-confidence inventory:
-   - docs examples
-   - template examples
-   - plugin manifests
-   - project-local optional settings
-3. For each critical or high finding, return:
-   - file path
-   - severity
-   - runtime confidence
-   - why it matters
-   - exact remediation
-   - whether it is safe to auto-fix
-4. If `--fix` is requested, state the planned edits before applying fixes.
-5. Re-run the scan after fixes and report the before/after score.
-
-## Output Contract
-
-Return:
-
-1. Security grade and score.
-2. Counts by severity and runtime confidence.
-3. Critical/high findings with exact paths.
-4. Lower-confidence findings grouped separately.
-5. A remediation order.
-6. Commands run and whether the scan was local, CI, or npx-backed.
-
-## CI Pattern
-
-Use AgentShield in GitHub Actions for enforced gates:
-
-```yaml
-- uses: affaan-m/agentshield@v1
-  with:
-    path: "."
-    min-severity: "medium"
-    fail-on-findings: true
-```
-
-## Links
-
-- Skill: `skills/security-scan/SKILL.md`
-- Agent: `agents/security-reviewer.md`
-- Scanner: <https://github.com/affaan-m/agentshield>
-
-## Arguments
-
-$ARGUMENTS:
-- optional target path
-- optional AgentShield flags

config/project-stack-mappings.json

@@ -1,539 +0,0 @@
-{
-  "version": 1,
-  "description": "Maps project indicator files to ECC skills, rules, hooks, and default commands. Used by /project-init to auto-configure projects.",
-  "stacks": [
-    {
-      "id": "typescript",
-      "name": "TypeScript / JavaScript",
-      "indicators": [
-        { "file": "tsconfig.json" },
-        { "file": "tsconfig.*.json" },
-        { "file": "package.json", "contains": "typescript" }
-      ],
-      "rules": ["common", "typescript"],
-      "skills": [
-        "coding-standards",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["npx tsc --noEmit", "npm run build"],
-        "test": ["npm test", "npx jest", "npx vitest"],
-        "lint": ["npx eslint .", "npx tsc --noEmit"],
-        "format": ["npx prettier --write ."]
-      },
-      "permissions": {
-        "allow": ["npx tsc", "npx eslint", "npx prettier", "npm test", "npm run *", "npx jest", "npx vitest"],
-        "deny": ["npm publish"]
-      }
-    },
-    {
-      "id": "javascript",
-      "name": "JavaScript (Node.js)",
-      "indicators": [
-        { "file": "package.json" },
-        { "file": ".eslintrc*" },
-        { "file": "eslint.config.*" }
-      ],
-      "rules": ["common", "typescript"],
-      "skills": [
-        "coding-standards",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["npm run build"],
-        "test": ["npm test", "npx jest", "npx vitest"],
-        "lint": ["npx eslint ."],
-        "format": ["npx prettier --write ."]
-      },
-      "permissions": {
-        "allow": ["npx eslint", "npx prettier", "npm test", "npm run *", "npx jest", "npx vitest"],
-        "deny": ["npm publish"]
-      }
-    },
-    {
-      "id": "react",
-      "name": "React",
-      "indicators": [
-        { "file": "package.json", "contains": "\"react\":" }
-      ],
-      "rules": ["common", "typescript", "web"],
-      "skills": [
-        "coding-standards",
-        "frontend-patterns",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["npm run build"],
-        "test": ["npm test", "npx jest", "npx vitest"],
-        "lint": ["npx eslint ."],
-        "format": ["npx prettier --write ."]
-      },
-      "permissions": {
-        "allow": ["npx eslint", "npx prettier", "npm test", "npm run *", "npx jest", "npx vitest"],
-        "deny": ["npm publish"]
-      }
-    },
-    {
-      "id": "nextjs",
-      "name": "Next.js",
-      "indicators": [
-        { "file": "next.config.*" },
-        { "file": "package.json", "contains": "\"next\":" }
-      ],
-      "rules": ["common", "typescript", "web"],
-      "skills": [
-        "coding-standards",
-        "frontend-patterns",
-        "backend-patterns",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["npm run build", "npx next build"],
-        "test": ["npm test", "npx jest", "npx vitest"],
-        "lint": ["npx next lint", "npx eslint ."],
-        "format": ["npx prettier --write ."],
-        "dev": ["npm run dev", "npx next dev"]
-      },
-      "permissions": {
-        "allow": ["npx next *", "npx eslint", "npx prettier", "npm test", "npm run *", "npx jest", "npx vitest"],
-        "deny": ["npm publish"]
-      }
-    },
-    {
-      "id": "golang",
-      "name": "Go",
-      "indicators": [
-        { "file": "go.mod" },
-        { "file": "go.sum" }
-      ],
-      "rules": ["common", "golang"],
-      "skills": [
-        "golang-patterns",
-        "golang-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["go build ./..."],
-        "test": ["go test ./..."],
-        "lint": ["golangci-lint run", "go vet ./..."],
-        "format": ["gofmt -w ."]
-      },
-      "permissions": {
-        "allow": ["go build *", "go test *", "go vet *", "go mod *", "go run *", "golangci-lint *", "gofmt *"],
-        "deny": []
-      }
-    },
-    {
-      "id": "python",
-      "name": "Python",
-      "indicators": [
-        { "file": "pyproject.toml" },
-        { "file": "setup.py" },
-        { "file": "setup.cfg" },
-        { "file": "requirements.txt" },
-        { "file": "Pipfile" },
-        { "file": "poetry.lock" }
-      ],
-      "rules": ["common", "python"],
-      "skills": [
-        "python-patterns",
-        "python-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["python -m build", "pip install -e ."],
-        "test": ["pytest", "python -m pytest"],
-        "lint": ["ruff check .", "flake8", "mypy ."],
-        "format": ["ruff format .", "black ."]
-      },
-      "permissions": {
-        "allow": ["python *", "pip install *", "pytest *", "ruff *", "black *", "mypy *", "flake8 *"],
-        "deny": ["pip install --user *"]
-      }
-    },
-    {
-      "id": "rust",
-      "name": "Rust",
-      "indicators": [
-        { "file": "Cargo.toml" },
-        { "file": "Cargo.lock" }
-      ],
-      "rules": ["common", "rust"],
-      "skills": [
-        "rust-patterns",
-        "rust-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["cargo build"],
-        "test": ["cargo test"],
-        "lint": ["cargo clippy -- -D warnings"],
-        "format": ["cargo fmt"]
-      },
-      "permissions": {
-        "allow": ["cargo build *", "cargo test *", "cargo clippy *", "cargo fmt *", "cargo run *", "cargo check *"],
-        "deny": ["cargo publish"]
-      }
-    },
-    {
-      "id": "java",
-      "name": "Java",
-      "indicators": [
-        { "file": "pom.xml" },
-        { "file": "build.gradle" },
-        { "file": "build.gradle.kts" }
-      ],
-      "rules": ["common", "java"],
-      "skills": [
-        "java-coding-standards",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["./mvnw compile", "./gradlew build", "mvn compile", "gradle build"],
-        "test": ["./mvnw test", "./gradlew test", "mvn test", "gradle test"],
-        "lint": ["./mvnw checkstyle:check", "./gradlew checkstyleMain"],
-        "format": ["./mvnw spotless:apply", "./gradlew spotlessApply"]
-      },
-      "permissions": {
-        "allow": ["./mvnw *", "./gradlew *", "mvn *", "gradle *", "java *"],
-        "deny": ["./mvnw deploy", "./gradlew publish", "mvn deploy", "gradle publish"]
-      }
-    },
-    {
-      "id": "springboot",
-      "name": "Spring Boot (Java/Kotlin)",
-      "indicators": [
-        { "file": "pom.xml", "contains": "spring-boot" },
-        { "file": "build.gradle", "contains": "spring-boot" },
-        { "file": "build.gradle.kts", "contains": "spring-boot" }
-      ],
-      "rules": ["common", "java"],
-      "skills": [
-        "springboot-patterns",
-        "springboot-tdd",
-        "springboot-verification",
-        "springboot-security",
-        "java-coding-standards",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["./mvnw compile", "./gradlew build"],
-        "test": ["./mvnw test", "./gradlew test"],
-        "lint": ["./mvnw checkstyle:check"],
-        "format": ["./mvnw spotless:apply"],
-        "dev": ["./mvnw spring-boot:run", "./gradlew bootRun"]
-      },
-      "permissions": {
-        "allow": ["./mvnw *", "./gradlew *", "mvn *", "gradle *", "java *"],
-        "deny": ["./mvnw deploy", "./gradlew publish", "mvn deploy", "gradle publish"]
-      }
-    },
-    {
-      "id": "kotlin",
-      "name": "Kotlin",
-      "indicators": [
-        { "file": "build.gradle.kts" },
-        { "file": "settings.gradle.kts" },
-        { "file": "build.gradle", "contains": "kotlin" }
-      ],
-      "rules": ["common", "kotlin"],
-      "skills": [
-        "kotlin-patterns",
-        "kotlin-testing",
-        "kotlin-coroutines-flows",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["./gradlew build"],
-        "test": ["./gradlew test"],
-        "lint": ["./gradlew ktlintCheck", "./gradlew detekt"],
-        "format": ["./gradlew ktlintFormat"]
-      },
-      "permissions": {
-        "allow": ["./gradlew *", "gradle *", "kotlin *"],
-        "deny": ["./gradlew publish"]
-      }
-    },
-    {
-      "id": "swift",
-      "name": "Swift / SwiftUI",
-      "indicators": [
-        { "file": "Package.swift" },
-        { "file": "*.xcodeproj" },
-        { "file": "*.xcworkspace" },
-        { "file": "Podfile" }
-      ],
-      "rules": ["common", "swift"],
-      "skills": [
-        "swiftui-patterns",
-        "swift-concurrency-6-2",
-        "swift-actor-persistence",
-        "swift-protocol-di-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["swift build", "xcodebuild build"],
-        "test": ["swift test", "xcodebuild test"],
-        "lint": ["swiftlint"],
-        "format": ["swiftformat ."]
-      },
-      "permissions": {
-        "allow": ["swift build *", "swift test *", "swift run *", "xcodebuild *", "swiftlint *", "swiftformat *"],
-        "deny": []
-      }
-    },
-    {
-      "id": "dart-flutter",
-      "name": "Dart / Flutter",
-      "indicators": [
-        { "file": "pubspec.yaml" },
-        { "file": "pubspec.lock" }
-      ],
-      "rules": ["common", "dart"],
-      "skills": [
-        "dart-flutter-patterns",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["flutter build", "dart compile"],
-        "test": ["flutter test", "dart test"],
-        "lint": ["dart analyze"],
-        "format": ["dart format ."]
-      },
-      "permissions": {
-        "allow": ["flutter *", "dart *"],
-        "deny": ["flutter pub publish"]
-      }
-    },
-    {
-      "id": "php-laravel",
-      "name": "PHP / Laravel",
-      "indicators": [
-        { "file": "composer.json" },
-        { "file": "artisan" },
-        { "file": "composer.lock" }
-      ],
-      "rules": ["common", "php"],
-      "skills": [
-        "laravel-patterns",
-        "laravel-tdd",
-        "laravel-verification",
-        "laravel-security",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["composer install"],
-        "test": ["php artisan test", "vendor/bin/phpunit", "vendor/bin/pest"],
-        "lint": ["vendor/bin/phpstan analyse", "vendor/bin/pint"],
-        "format": ["vendor/bin/pint"]
-      },
-      "permissions": {
-        "allow": ["php artisan *", "composer *", "vendor/bin/*"],
-        "deny": []
-      }
-    },
-    {
-      "id": "ruby",
-      "name": "Ruby / Rails",
-      "indicators": [
-        { "file": "Gemfile" },
-        { "file": "Gemfile.lock" },
-        { "file": "Rakefile" }
-      ],
-      "rules": ["common"],
-      "skills": [
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["bundle install"],
-        "test": ["bundle exec rspec", "bundle exec rake test"],
-        "lint": ["bundle exec rubocop"],
-        "format": ["bundle exec rubocop -A"]
-      },
-      "permissions": {
-        "allow": ["bundle exec *", "rails *", "rake *", "ruby *"],
-        "deny": ["gem push"]
-      }
-    },
-    {
-      "id": "csharp-dotnet",
-      "name": "C# / .NET",
-      "indicators": [
-        { "file": "*.csproj" },
-        { "file": "*.sln" },
-        { "file": "global.json" }
-      ],
-      "rules": ["common", "csharp"],
-      "skills": [
-        "dotnet-patterns",
-        "csharp-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["dotnet build"],
-        "test": ["dotnet test"],
-        "lint": ["dotnet format --verify-no-changes"],
-        "format": ["dotnet format"]
-      },
-      "permissions": {
-        "allow": ["dotnet build *", "dotnet test *", "dotnet run *", "dotnet format *"],
-        "deny": ["dotnet nuget push"]
-      }
-    },
-    {
-      "id": "cpp",
-      "name": "C / C++",
-      "indicators": [
-        { "file": "CMakeLists.txt" },
-        { "file": "Makefile" },
-        { "file": "meson.build" },
-        { "file": "*.vcxproj" }
-      ],
-      "rules": ["common", "cpp"],
-      "skills": [
-        "cpp-coding-standards",
-        "cpp-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["cmake --build build", "make"],
-        "test": ["ctest --test-dir build", "make test"],
-        "lint": ["clang-tidy -p build"],
-        "format": ["clang-format -i **/*.cpp **/*.h **/*.c **/*.hpp"]
-      },
-      "permissions": {
-        "allow": ["cmake *", "make *", "ctest *", "clang-tidy *", "clang-format *", "gcc *", "g++ *"],
-        "deny": []
-      }
-    },
-    {
-      "id": "perl",
-      "name": "Perl",
-      "indicators": [
-        { "file": "cpanfile" },
-        { "file": "Makefile.PL" },
-        { "file": "Build.PL" },
-        { "file": "dist.ini" }
-      ],
-      "rules": ["common", "perl"],
-      "skills": [
-        "perl-patterns",
-        "perl-testing",
-        "perl-security",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["perl Makefile.PL && make", "perl Build.PL && ./Build"],
-        "test": ["prove -lr t/", "make test"],
-        "lint": ["perlcritic lib/"],
-        "format": ["perltidy -b lib/**/*.pl"]
-      },
-      "permissions": {
-        "allow": ["perl *", "prove *", "make *", "perlcritic *", "perltidy *"],
-        "deny": []
-      }
-    },
-    {
-      "id": "django",
-      "name": "Django (Python)",
-      "indicators": [
-        { "file": "manage.py" },
-        { "file": "requirements.txt", "contains": "django" },
-        { "file": "pyproject.toml", "contains": "django" }
-      ],
-      "rules": ["common", "python"],
-      "skills": [
-        "django-patterns",
-        "django-tdd",
-        "django-verification",
-        "django-security",
-        "python-patterns",
-        "python-testing",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["pip install -e ."],
-        "test": ["python manage.py test", "pytest"],
-        "lint": ["ruff check .", "mypy ."],
-        "format": ["ruff format .", "black ."],
-        "dev": ["python manage.py runserver"]
-      },
-      "permissions": {
-        "allow": ["python *", "pip install *", "pytest *", "ruff *", "black *", "mypy *"],
-        "deny": []
-      }
-    },
-    {
-      "id": "android",
-      "name": "Android (Kotlin/Java)",
-      "indicators": [
-        { "file": "settings.gradle.kts", "contains": "android" },
-        { "file": "build.gradle", "contains": "android" },
-        { "file": "AndroidManifest.xml" }
-      ],
-      "rules": ["common", "kotlin"],
-      "skills": [
-        "android-clean-architecture",
-        "kotlin-patterns",
-        "kotlin-testing",
-        "kotlin-coroutines-flows",
-        "compose-multiplatform-patterns",
-        "tdd-workflow",
-        "verification-loop"
-      ],
-      "commands": {
-        "build": ["./gradlew assembleDebug"],
-        "test": ["./gradlew testDebugUnitTest"],
-        "lint": ["./gradlew lint", "./gradlew ktlintCheck"],
-        "format": ["./gradlew ktlintFormat"]
-      },
-      "permissions": {
-        "allow": ["./gradlew *", "adb *"],
-        "deny": []
-      }
-    },
-    {
-      "id": "docker",
-      "name": "Docker / Containerized",
-      "indicators": [
-        { "file": "Dockerfile" },
-        { "file": "docker-compose.yml" },
-        { "file": "docker-compose.yaml" },
-        { "file": "compose.yml" },
-        { "file": "compose.yaml" }
-      ],
-      "rules": [],
-      "skills": [
-        "docker-patterns",
-        "deployment-patterns"
-      ],
-      "commands": {
-        "build": ["docker compose build", "docker build ."],
-        "test": ["docker compose run --rm app test"],
-        "dev": ["docker compose up"]
-      },
-      "permissions": {
-        "allow": ["docker compose *", "docker build *"],
-        "deny": ["docker push"]
-      }
-    }
-  ]
-}

docs/architecture/observability-readiness.md

@@ -1,66 +0,0 @@
-# ECC 2.0 Observability Readiness
-
-ECC 2.0 should be observable before it becomes more autonomous. The local
-default is an opt-in, repo-owned readiness gate that checks whether the core
-signals are present without sending telemetry anywhere.
-
-Run:
-
-```bash
-npm run observability:ready
-node scripts/observability-readiness.js --format json
-```
-
-The gate is deterministic and safe to run in CI. It only checks repository
-files and reports whether the release surface can expose the signals an
-operator needs.
-
-## Signal Model
-
-- Live status: `scripts/loop-status.js` can emit JSON, watch active loops, and
-  write snapshots for dashboards or handoffs.
-- Session traces: `scripts/session-inspect.js` can inspect Claude, dmux, and
-  adapter-backed sessions, then write canonical snapshots.
-- Harness baseline: `scripts/harness-audit.js` provides a repeatable scorecard
-  for tool coverage, context efficiency, quality gates, memory persistence,
-  eval coverage, security guardrails, and cost efficiency.
-- Tool activity: `scripts/hooks/session-activity-tracker.js` records local
-  `tool-usage.jsonl` events that ECC2 can sync.
-- Risk ledger: `ecc2/src/observability/mod.rs` scores tool calls and stores a
-  paginated ledger for review.
-
-## Reference Pressure
-
-The current agent-tooling ecosystem is converging on the same operating needs:
-
-- dmux, Orca, and Superset emphasize isolated worktrees plus one place to see
-  agent state and merge/review work.
-- Claude HUD makes context, tool activity, agent activity, and todo progress
-  visible inside the coding loop.
-- Autocontext records every run as durable traces, reports, artifacts, and
-  reusable improvements.
-- Meta-Harness treats the harness itself as something to evaluate and improve,
-  which requires clean logs of proposer behavior and outcomes.
-- Zed and OpenCode emphasize agent control surfaces, reviewable changes, and
-  harness-specific configuration that should still preserve portable project
-  knowledge.
-
-ECC's answer is not a hosted analytics dependency by default. The first
-release-candidate gate is local and file-backed. Hosted telemetry can come
-later, but only after the local event model is useful enough to trust.
-
-## Operator Workflow
-
-1. Run `npm run observability:ready`.
-2. Run `npm run harness:audit -- --format json` for the broader harness
-   scorecard.
-3. Run `node scripts/loop-status.js --json --write-dir .ecc/loop-status`
-   during longer autonomous batches.
-4. Run `node scripts/session-inspect.js --list-adapters` to confirm which
-   session surfaces are available.
-5. Use ECC2 tool logs for risky operations, conflict analysis, and handoff
-   review before increasing autonomy.
-
-The end-state is practical: before asking ECC to run larger multi-agent loops,
-the operator can prove the system has live status, durable session traces,
-baseline scorecards, and a local risk ledger.

docs/ja-JP/README.md

@@ -1,4 +1,4 @@
-**言語:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+**言語:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md)
 
 # Everything Claude Code
 
@@ -19,9 +19,9 @@
 
 <div align="center">
 
-**言語 / Language / 語言 / Dil / Язык / Ngôn ngữ**
+**言語 / Language / 語言 / Dil**
 
-[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md)
 
 </div>
 

docs/ko-KR/README.md

@@ -1,4 +1,4 @@
-**언어:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | 한국어 | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+**언어:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | 한국어 | [Türkçe](../tr/README.md)
 
 # Everything Claude Code
 
@@ -22,9 +22,9 @@
 
 <div align="center">
 
-**Language / 语言 / 語言 / 언어 / Dil / Язык / Ngôn ngữ**
+**Language / 语言 / 語言 / 언어 / Dil**
 
-[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](README.md) | [Türkçe](../tr/README.md)
 
 </div>
 

docs/pt-BR/README.md

@@ -1,4 +1,4 @@
-**Idioma:** [English](../../README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | Português (Brasil) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+**Idioma:** [English](../../README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | Português (Brasil) | [Türkçe](../tr/README.md)
 
 # Everything Claude Code
 
@@ -22,9 +22,9 @@
 
 <div align="center">
 
-**Idioma / Language / 语言 / Dil / Язык / Ngôn ngữ**
+**Idioma / Language / 语言 / Dil**
 
-[**English**](../../README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Português (Brasil)](README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Português (Brasil)](README.md) | [Türkçe](../tr/README.md)
 
 </div>
 

docs/releases/2.0.0-rc.1/article-outline.md

@@ -2,7 +2,7 @@
 
 ## Working Title
 
-Turning ECC Into a Cross-Harness Operating System
+Turning ECC Into a Cross-Harness Operator System
 
 ## Core Argument
 
@@ -58,4 +58,4 @@ The leverage comes from treating the harness, reusable workflow layer, and opera
 
 The goal is not to copy one exact stack.
 
-The goal is to build an operating system around the agent that turns repeated work into reusable, measurable surfaces.
+The goal is to build an operator system that turns repeated work into reusable, measurable surfaces.

docs/releases/2.0.0-rc.1/quickstart.md

@@ -31,15 +31,6 @@ Expected result: every test passes with zero failures. For release-specific drif
 node tests/docs/ecc2-release-surface.test.js
 ```
 
-Then check the local observability surface:
-
-```bash
-npm run observability:ready
-```
-
-This runs the [observability readiness gate](../../architecture/observability-readiness.md)
-for loop status, session traces, harness audit, and ECC2 tool-risk logs.
-
 ## First Skill
 
 Read `skills/hermes-imports/SKILL.md` first.

docs/releases/2.0.0-rc.1/release-notes.md

@@ -13,7 +13,6 @@ Claude Code remains a core target. Codex, OpenCode, Cursor, Gemini, and other ha
 - Clarified the split between ECC as the reusable substrate and Hermes as the operator shell.
 - Documented the cross-harness portability model for skills, hooks, MCPs, rules, and instructions.
 - Added a Hermes import playbook for turning local operator patterns into publishable ECC skills.
-- Added a local [observability readiness gate](../../architecture/observability-readiness.md) for loop status, session traces, harness audit, and ECC2 tool-risk logs.
 
 ## Why This Matters
 
@@ -51,7 +50,6 @@ What stays local:
 1. Follow the [rc.1 quickstart](quickstart.md).
 2. Read the [Hermes setup guide](../../HERMES-SETUP.md).
 3. Review the [cross-harness architecture](../../architecture/cross-harness.md).
-4. Run the [observability readiness gate](../../architecture/observability-readiness.md).
-5. Start with one workflow lane: engineering, research, content, or outreach.
-6. Import only sanitized operator patterns into ECC skills.
-7. Treat `ecc2/` as an alpha control plane until release packaging and installer behavior are finalized.
+4. Start with one workflow lane: engineering, research, content, or outreach.
+5. Import only sanitized operator patterns into ECC skills.
+6. Treat `ecc2/` as an alpha control plane until release packaging and installer behavior are finalized.

docs/ru/README.md

@@ -1,4 +1,4 @@
-**Язык:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | **Русский** | [Tiếng Việt](../vi-VN/README.md)
+**Язык:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | **Русский**
 
 # Everything Claude Code
 
@@ -25,9 +25,9 @@
 
 <div align="center">
 
-**Язык / 语言 / 語言 / Dil / Ngôn ngữ**
+**Язык / 语言 / 語言 / Dil**
 
-[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | **Русский** | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | **Русский**
 
 </div>
 

docs/tr/README.md

@@ -21,9 +21,9 @@
 
 <div align="center">
 
-**Dil / Language / 语言 / 語言 / Язык / Ngôn ngữ**
+**Dil / Language / 语言 / 語言**
 
-[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [**Türkçe**](README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [**Türkçe**](README.md)
 
 </div>
 

docs/vi-VN/README.md

@@ -1,179 +0,0 @@
-**Ngôn ngữ:** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | **Tiếng Việt**
-
-# Everything Claude Code
-
-![Everything Claude Code - hệ thống hiệu năng cho AI agent harness](../../assets/hero.png)
-
-[![Stars](https://img.shields.io/github/stars/affaan-m/everything-claude-code?style=flat)](https://github.com/affaan-m/everything-claude-code/stargazers)
-[![Forks](https://img.shields.io/github/forks/affaan-m/everything-claude-code?style=flat)](https://github.com/affaan-m/everything-claude-code/network/members)
-[![Contributors](https://img.shields.io/github/contributors/affaan-m/everything-claude-code?style=flat)](https://github.com/affaan-m/everything-claude-code/graphs/contributors)
-[![npm ecc-universal](https://img.shields.io/npm/dw/ecc-universal?label=ecc-universal%20weekly%20downloads&logo=npm)](https://www.npmjs.com/package/ecc-universal)
-[![License](https://img.shields.io/badge/license-MIT-blue.svg)](../../LICENSE)
-
-> **140K+ sao** | **21K+ fork** | **170+ contributor** | **12+ hệ sinh thái ngôn ngữ** | **Anthropic Hackathon Winner**
-
----
-
-<div align="center">
-
-**Ngôn ngữ / Language / 语言 / 語言 / Dil / Язык**
-
-[English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | **Tiếng Việt**
-
-</div>
-
----
-
-**Everything Claude Code là hệ thống tối ưu hiệu năng cho AI agent harness.**
-
-ECC không chỉ là một bộ cấu hình. Repo này đóng gói agents, skills, hooks, rules, MCP config, selective install, kiểm tra bảo mật, và workflow vận hành cho Claude Code, Codex, Cursor, OpenCode, Gemini và các harness agent khác.
-
-Trang tiếng Việt này là bản onboarding gọn, được phục hồi từ đóng góp cộng đồng trong PR [#1322](https://github.com/affaan-m/everything-claude-code/pull/1322) và cập nhật để khớp mặt cài đặt hiện tại. README tiếng Anh vẫn là nguồn chuẩn đầy đủ nhất.
-
----
-
-## Bắt Đầu Nhanh
-
-### Chọn một đường cài đặt duy nhất
-
-Với Claude Code, phần lớn người dùng nên chọn đúng **một** trong hai đường:
-
-- **Khuyến nghị:** cài plugin Claude Code, sau đó copy thủ công chỉ những thư mục `rules/` bạn thật sự cần.
-- **Dùng installer thủ công** nếu bạn muốn kiểm soát chi tiết hơn, muốn tránh plugin, hoặc bản Claude Code của bạn không resolve được marketplace tự host.
-- **Không chồng nhiều cách cài lên nhau.** Cấu hình dễ hỏng nhất là `/plugin install` trước, rồi chạy tiếp `install.sh --profile full` hoặc `npx ecc-install --profile full`.
-
-Nếu bạn đã cài chồng nhiều lần và thấy skill/hook bị trùng, xem [Reset / Gỡ ECC](#reset--gỡ-ecc).
-
-### Cài plugin Claude Code
-
-```bash
-# Thêm marketplace
-/plugin marketplace add https://github.com/affaan-m/everything-claude-code
-
-# Cài plugin
-/plugin install ecc@ecc
-```
-
-ECC có ba định danh công khai khác nhau:
-
-- Repo GitHub: `affaan-m/everything-claude-code`
-- Plugin Claude marketplace: `ecc@ecc`
-- Gói npm: `ecc-universal`
-
-Các tên này cố ý khác nhau. Plugin Claude Code dùng `ecc@ecc`; npm vẫn dùng `ecc-universal`.
-
-### Copy rules nếu cần
-
-Plugin Claude Code không tự phân phối `rules/`. Nếu bạn đã cài bằng plugin, **đừng** chạy thêm full installer. Hãy copy riêng rule pack bạn muốn:
-
-```bash
-git clone https://github.com/affaan-m/everything-claude-code.git
-cd everything-claude-code
-
-mkdir -p ~/.claude/rules/ecc
-cp -R rules/common ~/.claude/rules/ecc/
-cp -R rules/typescript ~/.claude/rules/ecc/
-```
-
-```powershell
-git clone https://github.com/affaan-m/everything-claude-code.git
-cd everything-claude-code
-
-New-Item -ItemType Directory -Force -Path "$HOME/.claude/rules/ecc" | Out-Null
-Copy-Item -Recurse rules/common "$HOME/.claude/rules/ecc/"
-Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/ecc/"
-```
-
-Copy cả thư mục ngôn ngữ, ví dụ `rules/common` hoặc `rules/golang`, thay vì copy từng file riêng lẻ.
-
-### Cài thủ công nếu không dùng plugin
-
-Chỉ dùng đường này nếu bạn cố ý bỏ qua plugin:
-
-```bash
-npm install
-./install.sh --profile full
-```
-
-```powershell
-npm install
-.\install.ps1 --profile full
-# hoặc
-npx ecc-install --profile full
-```
-
-Nếu chọn đường thủ công, dừng ở đó. Đừng chạy thêm `/plugin install`.
-
-### Đường low-context / không hooks
-
-Nếu bạn chỉ muốn rules, agents, commands và core workflow skills, dùng profile tối thiểu:
-
-```bash
-./install.sh --profile minimal --target claude
-```
-
-```powershell
-.\install.ps1 --profile minimal --target claude
-# hoặc
-npx ecc-install --profile minimal --target claude
-```
-
-Profile này cố ý không cài `hooks-runtime`.
-
----
-
-## Reset / Gỡ ECC
-
-Nếu ECC bị trùng, quá xâm lấn, hoặc hoạt động sai, đừng tiếp tục cài đè lên chính nó.
-
-- **Đường plugin:** gỡ plugin trong Claude Code, rồi xoá các rule folder bạn đã copy thủ công dưới `~/.claude/rules/ecc/`.
-- **Đường installer/CLI:** từ root repo, preview trước:
-
-```bash
-node scripts/uninstall.js --dry-run
-```
-
-Sau đó gỡ các file do ECC quản lý:
-
-```bash
-node scripts/uninstall.js
-```
-
-Bạn cũng có thể dùng lifecycle wrapper:
-
-```bash
-node scripts/ecc.js list-installed
-node scripts/ecc.js doctor
-node scripts/ecc.js repair
-node scripts/ecc.js uninstall --dry-run
-```
-
-ECC chỉ xoá file có trong install-state của nó. Nó không xoá file không liên quan.
-
----
-
-## Tài Liệu Quan Trọng
-
-- [README tiếng Anh](../../README.md) - nguồn chuẩn đầy đủ nhất
-- [Hướng dẫn Hermes](../HERMES-SETUP.md)
-- [Release notes v2.0.0-rc.1](../releases/2.0.0-rc.1/release-notes.md)
-- [Kiến trúc cross-harness](../architecture/cross-harness.md)
-- [Troubleshooting](../TROUBLESHOOTING.md)
-- [Hook bug workarounds](../hook-bug-workarounds.md)
-
----
-
-## Dùng Thử
-
-```bash
-# Plugin install dùng namespace đầy đủ
-/ecc:plan "Thêm xác thực người dùng"
-
-# Manual install giữ dạng slash ngắn
-# /plan "Thêm xác thực người dùng"
-
-# Xem plugin đang cài
-/plugin list ecc@ecc
-```
-
-ECC hiện cung cấp hàng chục agent, hơn 200 skill và legacy command shim cho các workflow agent khác nhau. Kiểm tra README tiếng Anh để xem danh sách và hướng dẫn chi tiết nhất.

docs/zh-CN/AGENTS.md

@@ -1,6 +1,6 @@
 # Everything Claude Code (ECC) — 智能体指令
 
-这是一个**生产就绪的 AI 编码插件**，提供 56 个专业代理、217 项技能、72 条命令以及自动化钩子工作流，用于软件开发。
+这是一个**生产就绪的 AI 编码插件**，提供 54 个专业代理、204 项技能、69 条命令以及自动化钩子工作流，用于软件开发。
 
 **版本:** 2.0.0-rc.1
 
@@ -146,9 +146,9 @@
 ## 项目结构
 
 ```
-agents/          — 56 个专业子代理
-skills/          — 217 个工作流技能和领域知识
-commands/        — 72 个斜杠命令
+agents/          — 54 个专业子代理
+skills/          — 204 个工作流技能和领域知识
+commands/        — 69 个斜杠命令
 hooks/           — 基于触发的自动化
 rules/           — 始终遵循的指导方针（通用 + 每种语言）
 scripts/         — 跨平台 Node.js 实用工具

docs/zh-CN/README.md

@@ -1,4 +1,4 @@
-**语言：** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+**语言：** [English](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md)
 
 # Everything Claude Code
 
@@ -23,9 +23,9 @@
 
 <div align="center">
 
-**语言 / Language / 語言 / Dil / Язык / Ngôn ngữ**
+**语言 / Language / 語言 / Dil**
 
-[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](../zh-TW/README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md)
 
 </div>
 
@@ -224,7 +224,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
 /plugin list ecc@ecc
 ```
 
-**搞定！** 你现在可以使用 56 个智能体、217 项技能和 72 个命令了。
+**搞定！** 你现在可以使用 54 个智能体、204 项技能和 69 个命令了。
 
 ***
 
@@ -1132,9 +1132,9 @@ opencode
 
 | 功能特性 | Claude Code | OpenCode | 状态 |
 |---------|-------------|----------|--------|
-| 智能体 | PASS: 56 个 | PASS: 12 个 | **Claude Code 领先** |
-| 命令 | PASS: 72 个 | PASS: 35 个 | **Claude Code 领先** |
-| 技能 | PASS: 217 项 | PASS: 37 项 | **Claude Code 领先** |
+| 智能体 | PASS: 54 个 | PASS: 12 个 | **Claude Code 领先** |
+| 命令 | PASS: 69 个 | PASS: 31 个 | **Claude Code 领先** |
+| 技能 | PASS: 204 项 | PASS: 37 项 | **Claude Code 领先** |
 | 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多！** |
 | 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
 | MCP 服务器 | PASS: 14 个 | PASS: 完整 | **完全对等** |
@@ -1240,9 +1240,9 @@ ECC 是**第一个最大化利用每个主要 AI 编码工具的插件**。以
 
 | 功能特性 | Claude Code | Cursor IDE | Codex CLI | OpenCode |
 |---------|------------|------------|-----------|----------|
-| **智能体** | 56 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
-| **命令** | 72 | 共享 | 基于指令 | 35 |
-| **技能** | 217 | 共享 | 10 (原生格式) | 37 |
+| **智能体** | 54 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
+| **命令** | 69 | 共享 | 基于指令 | 31 |
+| **技能** | 204 | 共享 | 10 (原生格式) | 37 |
 | **钩子事件** | 8 种类型 | 15 种类型 | 暂无 | 11 种类型 |
 | **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | N/A | 插件钩子 |
 | **规则** | 34 (通用 + 语言) | 34 (YAML 前页) | 基于指令 | 13 条指令 |

docs/zh-TW/README.md

@@ -11,9 +11,9 @@
 
 <div align="center">
 
-**Language / 语言 / 語言 / Dil / Язык / Ngôn ngữ**
+**Language / 语言 / 語言 / Dil**
 
-[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md) | [Русский](../ru/README.md) | [Tiếng Việt](../vi-VN/README.md)
+[**English**](../../README.md) | [Português (Brasil)](../pt-BR/README.md) | [简体中文](../../README.zh-CN.md) | [繁體中文](README.md) | [日本語](../ja-JP/README.md) | [한국어](../ko-KR/README.md) | [Türkçe](../tr/README.md)
 
 </div>
 

ecc2/src/session/manager.rs

@@ -908,10 +908,11 @@ pub async fn drain_inbox(
     use_worktree: bool,
     limit: usize,
 ) -> Result<Vec<InboxDrainOutcome>> {
+    let repo_root =
+        std::env::current_dir().context("Failed to resolve current working directory")?;
     let runner_program =
         std::env::current_exe().context("Failed to resolve ECC executable path")?;
     let lead = resolve_session(db, lead_id)?;
-    let repo_root = lead.working_dir.clone();
     let messages = db.unread_task_handoffs_for_session(&lead.id, limit)?;
     let mut outcomes = Vec::new();
 
@@ -1056,10 +1057,11 @@ pub async fn rebalance_team_backlog(
     use_worktree: bool,
     limit: usize,
 ) -> Result<Vec<RebalanceOutcome>> {
+    let repo_root =
+        std::env::current_dir().context("Failed to resolve current working directory")?;
     let runner_program =
         std::env::current_exe().context("Failed to resolve ECC executable path")?;
     let lead = resolve_session(db, lead_id)?;
-    let repo_root = lead.working_dir.clone();
     let mut outcomes = Vec::new();
 
     if limit == 0 {

examples/harmonyos-app-CLAUDE.md

@@ -1,88 +0,0 @@
-# HarmonyOS App Project CLAUDE.md
-
-This is a project-level CLAUDE.md example for HarmonyOS applications. Place it at your project root.
-
-## Project Overview
-
-[Briefly describe your app - features, target devices, API level]
-
-## Core Rules
-
-### 1. Tech Stack Constraints
-
-- Platform: HarmonyOS (ArkTS/TypeScript), prefer latest stable official APIs
-- State Management: **V2 only** (`@ComponentV2`, `@Local`, `@Param`, `@Event`, `@Provider`, `@Consumer`, `@Monitor`, `@Computed`)
-- Routing: **Navigation only** (`Navigation` + `NavPathStack` + `NavDestination`)
-- Architecture: MVVM with modular layers - View renders only, all business logic in ViewModel
-- Component priority: in-module reusable components > cross-module shared components > third-party libraries
-
-### 2. Code Organization
-
-- Prefer many small files over few large files
-- High cohesion, low coupling
-- Target 200-400 lines per file, max 800 lines
-- Organize by feature/domain, not by type
-
-### 3. Code Style
-
-- No emojis in code, comments, or documentation
-- Immutability - never mutate objects directly
-- Double quotes for strings; semicolons required
-- Never use `var` - prefer `const`, then `let`
-- No `any` type - complete type annotations for all methods, parameters, return values
-- Naming: `camelCase` for variables/functions, `PascalCase` for classes/interfaces, `UPPER_SNAKE_CASE` for constants
-- File header: `@file` + `@author`; all methods need JSDoc with `@param` and `@returns`
-
-### 4. Layout & Interaction
-
-- Use `layoutWeight(1)` for even distribution - avoid `SpaceAround`/`SpaceBetween`
-- Use percentages / layout weights / adaptive units - no hardcoded fixed dimensions (except icons)
-- Define UI constants as resources, reference via `$r()`
-- Support both light and dark themes for new color resources
-
-### 5. Build & Validation
-
-```bash
-# Build HAP package
-hvigorw assembleHap -p product=default
-```
-
-- Run build after every implementation to verify compilation
-- Refer to official Huawei developer docs for uncertain API usage - never guess
-
-### 6. Testing
-
-- TDD: write tests first
-- Unit tests for utility functions and ViewModels
-- UI tests for critical user flows
-- Minimum 80% coverage for business logic
-
-### 7. Security
-
-- No hardcoded secrets
-- Verify permissions in `module.json5` before using system APIs
-- Validate all user input
-- Use HTTPS for all network requests
-
-## File Structure
-
-```
-src/
-|-- entry/            # App entry, framework initialization
-|-- core/             # Core framework layer
-|-- shared/           # Shared contracts layer
-|-- packages/         # Business feature packages
-```
-
-## Available Commands
-
-- `/plan` - Create implementation plan
-- `/code-review` - Code quality review
-- `/build-fix` - Fix build errors
-
-## Git Workflow
-
-- Conventional commits: `feat:`, `fix:`, `refactor:`, `docs:`, `test:`
-- No direct commits to main branch
-- PRs require review
-- All tests must pass before merge

examples/statusline.json

@@ -1,20 +1,19 @@
 {
   "statusLine": {
     "type": "command",
-    "command": "node \"<plugin-root>/scripts/hooks/ecc-statusline.js\"",
-    "description": "ECC statusline: model | task | $cost tools files duration | dir | context bar"
+    "command": "input=$(cat); user=$(whoami); cwd=$(echo \"$input\" | jq -r '.workspace.current_dir' | sed \"s|$HOME|~|g\"); model=$(echo \"$input\" | jq -r '.model.display_name'); time=$(date +%H:%M); remaining=$(echo \"$input\" | jq -r '.context_window.remaining_percentage // empty'); transcript=$(echo \"$input\" | jq -r '.transcript_path'); todo_count=$([ -f \"$transcript\" ] && grep -c '\"type\":\"todo\"' \"$transcript\" 2>/dev/null || echo 0); cd \"$(echo \"$input\" | jq -r '.workspace.current_dir')\" 2>/dev/null; branch=$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo ''); status=''; [ -n \"$branch\" ] && { [ -n \"$(git status --porcelain 2>/dev/null)\" ] && status='*'; }; B='\\033[38;2;30;102;245m'; G='\\033[38;2;64;160;43m'; Y='\\033[38;2;223;142;29m'; M='\\033[38;2;136;57;239m'; C='\\033[38;2;23;146;153m'; R='\\033[0m'; T='\\033[38;2;76;79;105m'; printf \"${C}${user}${R}:${B}${cwd}${R}\"; [ -n \"$branch\" ] && printf \" ${G}${branch}${Y}${status}${R}\"; [ -n \"$remaining\" ] && printf \" ${M}ctx:${remaining}%%${R}\"; printf \" ${T}${model}${R} ${Y}${time}${R}\"; [ \"$todo_count\" -gt 0 ] && printf \" ${C}todos:${todo_count}${R}\"; echo",
+    "description": "Custom status line showing: user:path branch* ctx:% model time todos:N"
   },
   "_comments": {
-    "setup": "Replace <plugin-root> with your ECC installation path. For plugin installs, use the resolved path from CLAUDE_PLUGIN_ROOT.",
-    "display": "Shows model name, current task, session cost, tool count, files modified, session duration, directory, and context usage bar with color thresholds.",
     "colors": {
-      "green": "Context used < 50%",
-      "yellow": "Context used < 65%",
-      "orange": "Context used < 80%",
-      "red_blink": "Context used >= 80%"
+      "B": "Blue - directory path",
+      "G": "Green - git branch",
+      "Y": "Yellow - dirty status, time",
+      "M": "Magenta - context remaining",
+      "C": "Cyan - username, todos",
+      "T": "Gray - model name"
     },
-    "output_example": "Opus 4.6 | Fixing auth bug | $1.23 47t 5f 15m | myproject ███████░░░ 68%",
-    "dependencies": "Reads bridge file from ecc-metrics-bridge.js PostToolUse hook. Both must be installed for full metrics display.",
+    "output_example": "affoon:~/projects/myapp main* ctx:73% sonnet-4.6 14:30 todos:3",
     "usage": "Copy the statusLine object to your ~/.claude/settings.json"
   }
 }

hooks/README.md

@@ -16,9 +16,6 @@ User request → Claude picks a tool → PreToolUse hook runs → Tool executes
 
 ## Hooks in This Plugin
 
-Memory persistence lifecycle definitions live in `hooks/memory-persistence/`.
-The executable hook graph remains `hooks/hooks.json`; the memory persistence directory is the stable contract for SessionStart, PreCompact, observation, activity tracking, and SessionEnd behavior.
-
 ## Installing These Hooks Manually
 
 For Claude Code manual installs, do not paste the raw repo `hooks.json` into `~/.claude/settings.json` or copy it directly into `~/.claude/hooks/hooks.json`. The checked-in file is plugin/repo-oriented and is meant to be installed through the ECC installer or loaded as a plugin.

hooks/hooks.json

@@ -219,30 +219,6 @@
         ],
         "description": "Capture tool use results for continuous learning",
         "id": "post:observe:continuous-learning"
-      },
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node -e \"const p=require('path');const r=(()=>{var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var p=require('path'),f=require('fs'),h=require('os').homedir(),d=p.join(h,'.claude'),q=p.join('scripts','lib','utils.js');if(f.existsSync(p.join(d,q)))return d;for(var s of [[\\\"ecc\\\"],[\\\"ecc@ecc\\\"],[\\\"marketplaces\\\",\\\"ecc\\\"],[\\\"everything-claude-code\\\"],[\\\"everything-claude-code@everything-claude-code\\\"],[\\\"marketplaces\\\",\\\"everything-claude-code\\\"]]){var l=p.join(d,'plugins',...s);if(f.existsSync(p.join(l,q)))return l}try{for(var g of [\\\"ecc\\\",\\\"everything-claude-code\\\"]){var b=p.join(d,'plugins','cache',g);for(var o of f.readdirSync(b,{withFileTypes:true})){if(!o.isDirectory())continue;for(var v of f.readdirSync(p.join(b,o.name),{withFileTypes:true})){if(!v.isDirectory())continue;var c=p.join(b,o.name,v.name);if(f.existsSync(p.join(c,q)))return c}}}}catch(x){}return d})();const s=p.join(r,'scripts/hooks/plugin-hook-bootstrap.js');process.env.CLAUDE_PLUGIN_ROOT=r;process.argv.splice(1,0,s);require(s)\" node scripts/hooks/run-with-flags.js post:ecc-metrics-bridge scripts/hooks/ecc-metrics-bridge.js minimal,standard,strict",
-            "timeout": 10
-          }
-        ],
-        "description": "Maintain running session metrics aggregate for statusline and context monitor",
-        "id": "post:ecc-metrics-bridge"
-      },
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node -e \"const p=require('path');const r=(()=>{var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var p=require('path'),f=require('fs'),h=require('os').homedir(),d=p.join(h,'.claude'),q=p.join('scripts','lib','utils.js');if(f.existsSync(p.join(d,q)))return d;for(var s of [[\\\"ecc\\\"],[\\\"ecc@ecc\\\"],[\\\"marketplaces\\\",\\\"ecc\\\"],[\\\"everything-claude-code\\\"],[\\\"everything-claude-code@everything-claude-code\\\"],[\\\"marketplaces\\\",\\\"everything-claude-code\\\"]]){var l=p.join(d,'plugins',...s);if(f.existsSync(p.join(l,q)))return l}try{for(var g of [\\\"ecc\\\",\\\"everything-claude-code\\\"]){var b=p.join(d,'plugins','cache',g);for(var o of f.readdirSync(b,{withFileTypes:true})){if(!o.isDirectory())continue;for(var v of f.readdirSync(p.join(b,o.name),{withFileTypes:true})){if(!v.isDirectory())continue;var c=p.join(b,o.name,v.name);if(f.existsSync(p.join(c,q)))return c}}}}catch(x){}return d})();const s=p.join(r,'scripts/hooks/plugin-hook-bootstrap.js');process.env.CLAUDE_PLUGIN_ROOT=r;process.argv.splice(1,0,s);require(s)\" node scripts/hooks/run-with-flags.js post:ecc-context-monitor scripts/hooks/ecc-context-monitor.js standard,strict",
-            "timeout": 10
-          }
-        ],
-        "description": "Inject agent warnings on context exhaustion, high cost, scope creep, or tool loops",
-        "id": "post:ecc-context-monitor"
       }
     ],
     "PostToolUseFailure": [

hooks/memory-persistence/README.md

@@ -1,44 +0,0 @@
-# Memory Persistence Hooks
-
-These lifecycle hook definitions document ECC's memory persistence contract for Claude Code plugin and manual installs.
-
-The executable implementations live in `scripts/hooks/`:
-
-- `session-start.js` loads bounded prior context, detects project state, and prepares session metadata.
-- `pre-compact.js` captures state before context compaction.
-- `session-end.js` persists session-end summaries when transcript metadata is available.
-- `observe-runner.js` records tool-use observations for continuous learning.
-- `session-activity-tracker.js` records tool usage and file activity for ECC2 status and observability.
-
-The installed hook graph is still `hooks/hooks.json`. This directory is the stable, human-readable lifecycle definition surface referenced by the harness audit and longform docs.
-
-## Lifecycle Contract
-
-| Event | Hook | Purpose | Blocking |
-|---|---|---|---|
-| `SessionStart` | `session:start` | Load bounded prior context and project metadata | no |
-| `PreCompact` | `pre:compact` | Save state before compaction | no |
-| `PreToolUse` | `pre:observe:continuous-learning` | Capture tool intent for learning signals | no |
-| `PostToolUse` | `post:observe:continuous-learning` | Capture tool result for learning signals | no |
-| `PostToolUse` | `post:session-activity-tracker` | Record tool and file activity for ECC2 metrics | no |
-| `Stop` | `stop:format-typecheck` | Batch quality gate after edits | yes on hook failure |
-| `Stop` | `stop:check-console-log` | Audit modified files for debug logging | warn/error by hook output |
-
-## Operator Expectations
-
-- Keep persistence local by default.
-- Avoid sending transcripts or tool traces to hosted services unless a user explicitly enables an integration.
-- Bound context loaded at session start with `ECC_SESSION_START_MAX_CHARS`.
-- Allow opt-out with `ECC_SESSION_START_CONTEXT=off`.
-- Keep lifecycle hooks profile-gated through `ECC_HOOK_PROFILE` and `ECC_DISABLED_HOOKS`.
-
-## Related Files
-
-- `hooks/hooks.json`
-- `hooks/README.md`
-- `scripts/hooks/session-start.js`
-- `scripts/hooks/pre-compact.js`
-- `scripts/hooks/session-end.js`
-- `scripts/hooks/observe-runner.js`
-- `scripts/hooks/session-activity-tracker.js`
-- `docs/architecture/observability-readiness.md`

hooks/memory-persistence/hooks.json

@@ -1,47 +0,0 @@
-{
-  "description": "Reference lifecycle hook definitions for ECC memory persistence. The production hook graph is hooks/hooks.json.",
-  "events": [
-    {
-      "event": "SessionStart",
-      "id": "session:start",
-      "script": "scripts/hooks/session-start-bootstrap.js",
-      "purpose": "Load bounded prior context and detect project state at session start.",
-      "blocking": false
-    },
-    {
-      "event": "PreCompact",
-      "id": "pre:compact",
-      "script": "scripts/hooks/pre-compact.js",
-      "purpose": "Persist session state before context compaction.",
-      "blocking": false
-    },
-    {
-      "event": "PreToolUse",
-      "id": "pre:observe:continuous-learning",
-      "script": "scripts/hooks/observe-runner.js",
-      "purpose": "Record tool intent for continuous learning signals.",
-      "blocking": false
-    },
-    {
-      "event": "PostToolUse",
-      "id": "post:observe:continuous-learning",
-      "script": "scripts/hooks/observe-runner.js",
-      "purpose": "Record tool results for continuous learning signals.",
-      "blocking": false
-    },
-    {
-      "event": "PostToolUse",
-      "id": "post:session-activity-tracker",
-      "script": "scripts/hooks/session-activity-tracker.js",
-      "purpose": "Record per-session tool calls and file activity for ECC2 metrics.",
-      "blocking": false
-    },
-    {
-      "event": "SessionEnd",
-      "id": "session:end",
-      "script": "scripts/hooks/session-end.js",
-      "purpose": "Persist session-end summaries when transcript metadata is available.",
-      "blocking": false
-    }
-  ]
-}

manifests/install-components.json

@@ -81,14 +81,6 @@
         "framework-language"
       ]
     },
-    {
-      "id": "framework:angular",
-      "family": "framework",
-      "description": "Angular-focused engineering guidance and rules. Currently resolves through the shared framework-language module.",
-      "modules": [
-        "framework-language"
-      ]
-    },
     {
       "id": "framework:react",
       "family": "framework",
@@ -121,15 +113,6 @@
         "framework-language"
       ]
     },
-    {
-      "id": "framework:quarkus",
-      "family": "framework",
-      "description": "Quarkus-focused engineering guidance for REST, Panache, security, testing, and verification.",
-      "modules": [
-        "framework-language",
-        "security"
-      ]
-    },
     {
       "id": "capability:database",
       "family": "capability",
@@ -226,14 +209,6 @@
         "framework-language"
       ]
     },
-    {
-      "id": "lang:arkts",
-      "family": "language",
-      "description": "HarmonyOS, ArkTS, and ArkUI development guidance including V2 state management, Navigation routing, and HarmonyOS API best practices.",
-      "modules": [
-        "framework-language"
-      ]
-    },
     {
       "id": "lang:perl",
       "family": "language",
@@ -259,14 +234,6 @@
         "framework-language"
       ]
     },
-    {
-      "id": "lang:fsharp",
-      "family": "language",
-      "description": "F# functional patterns and testing guidance. Currently resolves through the shared framework-language module.",
-      "modules": [
-        "framework-language"
-      ]
-    },
     {
       "id": "framework:laravel",
       "family": "framework",
@@ -372,22 +339,6 @@
         "agents-core"
       ]
     },
-    {
-      "id": "agent:harmonyos-app-resolver",
-      "family": "agent",
-      "description": "HarmonyOS application development expert agent.",
-      "modules": [
-        "agents-core"
-      ]
-    },
-    {
-      "id": "agent:fsharp-reviewer",
-      "family": "agent",
-      "description": "F# code review agent for functional idioms, type safety, and .NET testing.",
-      "modules": [
-        "agents-core"
-      ]
-    },
     {
       "id": "agent:refactor-cleaner",
       "family": "agent",
@@ -444,14 +395,6 @@
         "workflow-quality"
       ]
     },
-    {
-      "id": "skill:windows-desktop-e2e",
-      "family": "skill",
-      "description": "E2E testing for Windows native desktop apps with pywinauto and Windows UI Automation.",
-      "modules": [
-        "workflow-quality"
-      ]
-    },
     {
       "id": "skill:strategic-compact",
       "family": "skill",

manifests/install-modules.json

@@ -122,13 +122,11 @@
       "description": "Core framework, language, and application-engineering skills.",
       "paths": [
         "skills/android-clean-architecture",
-        "skills/angular-developer",
         "skills/api-design",
         "skills/backend-patterns",
         "skills/coding-standards",
         "skills/compose-multiplatform-patterns",
         "skills/csharp-testing",
-        "skills/fsharp-testing",
         "skills/cpp-coding-standards",
         "skills/cpp-testing",
         "skills/dart-flutter-patterns",
@@ -139,7 +137,6 @@
         "skills/fastapi-patterns",
         "skills/frontend-patterns",
         "skills/frontend-slides",
-        "skills/motion-ui",
         "skills/golang-patterns",
         "skills/golang-testing",
         "skills/java-coding-standards",
@@ -158,9 +155,6 @@
         "skills/perl-testing",
         "skills/python-patterns",
         "skills/python-testing",
-        "skills/quarkus-patterns",
-        "skills/quarkus-tdd",
-        "skills/quarkus-verification",
         "skills/rust-patterns",
         "skills/rust-testing",
         "skills/springboot-patterns",
@@ -230,7 +224,6 @@
         "skills/continuous-learning-v2",
         "skills/council",
         "skills/e2e-testing",
-        "skills/error-handling",
         "skills/eval-harness",
         "skills/hookify-rules",
         "skills/iterative-retrieval",
@@ -239,8 +232,7 @@
         "skills/skill-stocktake",
         "skills/strategic-compact",
         "skills/tdd-workflow",
-        "skills/verification-loop",
-        "skills/windows-desktop-e2e"
+        "skills/verification-loop"
       ],
       "targets": [
         "claude",
@@ -272,7 +264,6 @@
         "skills/llm-trading-agent-security",
         "skills/nodejs-keccak256",
         "skills/perl-security",
-        "skills/quarkus-security",
         "skills/security-review",
         "skills/security-scan",
         "skills/security-bounty-hunter",
@@ -515,10 +506,8 @@
       "kind": "skills",
       "description": "Agentic engineering, autonomous loops, agent harness construction, and LLM pipeline optimization skills.",
       "paths": [
-        "skills/agent-architecture-audit",
         "skills/agent-harness-construction",
         "skills/agentic-engineering",
-        "skills/agentic-os",
         "skills/ai-first-engineering",
         "skills/autonomous-loops",
         "skills/blueprint",
@@ -598,9 +587,7 @@
         "antigravity",
         "codex",
         "opencode",
-        "codebuddy",
-        "joycode",
-        "qwen"
+        "codebuddy"
       ],
       "dependencies": [
         "framework-language",

mcp-configs/mcp-servers.json

@@ -41,11 +41,6 @@
       "args": ["omega-memory", "serve"],
       "description": "Persistent agent memory with semantic search, multi-agent coordination, and knowledge graphs — run via uvx (richer than the basic memory store)"
     },
-    "longhand": {
-      "command": "longhand",
-      "args": ["mcp-server"],
-      "description": "Lossless Claude Code session history — indexes raw tool calls, file edits, and thinking blocks from ~/.claude/projects/*.jsonl into local SQLite + ChromaDB before Claude Code rotates them. Complements memory/omega-memory (synthesized) with verbatim recall. Install: pip install longhand && longhand setup"
-    },
     "sequential-thinking": {
       "command": "npx",
       "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],

package.json

@@ -72,7 +72,6 @@
     "scripts/ecc.js",
     "scripts/gemini-adapt-agents.js",
     "scripts/harness-audit.js",
-    "scripts/observability-readiness.js",
     "scripts/hooks/",
     "scripts/install-apply.js",
     "scripts/install-plan.js",
@@ -90,16 +89,13 @@
     "scripts/status.js",
     "scripts/work-items.js",
     "scripts/uninstall.js",
-    "skills/agent-architecture-audit/",
     "skills/agent-harness-construction/",
     "skills/agent-introspection-debugging/",
     "skills/agent-sort/",
     "skills/agentic-engineering/",
-    "skills/agentic-os/",
     "skills/ai-first-engineering/",
     "skills/ai-regression-testing/",
     "skills/android-clean-architecture/",
-    "skills/angular-developer/",
     "skills/api-connector-builder/",
     "skills/api-design/",
     "skills/article-writing/",
@@ -149,7 +145,6 @@
     "skills/email-ops/",
     "skills/energy-procurement/",
     "skills/enterprise-agent-ops/",
-    "skills/error-handling/",
     "skills/eval-harness/",
     "skills/evm-token-decimals/",
     "skills/exa-search/",
@@ -159,7 +154,6 @@
     "skills/foundation-models-on-device/",
     "skills/frontend-patterns/",
     "skills/frontend-slides/",
-    "skills/fsharp-testing/",
     "skills/github-ops/",
     "skills/golang-patterns/",
     "skills/golang-testing/",
@@ -196,7 +190,6 @@
     "skills/mcp-server-patterns/",
     "skills/messages-ops/",
     "skills/mle-workflow/",
-    "skills/motion-ui/",
     "skills/mysql-patterns/",
     "skills/nanoclaw-repl/",
     "skills/nestjs-patterns/",
@@ -219,10 +212,6 @@
     "skills/python-patterns/",
     "skills/python-testing/",
     "skills/quality-nonconformance/",
-    "skills/quarkus-patterns/",
-    "skills/quarkus-security/",
-    "skills/quarkus-tdd/",
-    "skills/quarkus-verification/",
     "skills/ralphinho-rfc-pipeline/",
     "skills/regex-vs-llm-structured-text/",
     "skills/remotion-video-creation/",
@@ -262,7 +251,6 @@
     "skills/video-editing/",
     "skills/videodb/",
     "skills/visa-doc-translate/",
-    "skills/windows-desktop-e2e/",
     "skills/workspace-surface-audit/",
     "skills/x-api/",
     "the-security-guide.md"
@@ -277,7 +265,6 @@
     "catalog:sync": "node scripts/ci/catalog.js --write --text",
     "lint": "eslint . && markdownlint '**/*.md' --ignore node_modules",
     "harness:audit": "node scripts/harness-audit.js",
-    "observability:ready": "node scripts/observability-readiness.js",
     "claw": "node scripts/claw.js",
     "orchestrate:status": "node scripts/orchestration-status.js",
     "orchestrate:worker": "bash scripts/orchestrate-codex-worker.sh",

rules/README.md

@@ -15,13 +15,11 @@ rules/
 │   ├── agents.md
 │   └── security.md
 ├── typescript/      # TypeScript/JavaScript specific
-├── angular/         # Angular specific
 ├── python/          # Python specific
 ├── golang/          # Go specific
 ├── web/             # Web and frontend specific
 ├── swift/           # Swift specific
-├── php/             # PHP specific
-└── arkts/           # HarmonyOS / ArkTS specific
+└── php/             # PHP specific
 ```
 
 - **common/** contains universal principles — no language-specific code examples.
@@ -34,13 +32,11 @@ rules/
 ```bash
 # Install common + one or more language-specific rule sets
 ./install.sh typescript
-./install.sh angular
 ./install.sh python
 ./install.sh golang
 ./install.sh web
 ./install.sh swift
 ./install.sh php
-./install.sh arkts
 
 # Install multiple languages at once
 ./install.sh typescript python
@@ -60,13 +56,11 @@ cp -r rules/common ~/.claude/rules/common
 
 # Install language-specific rules based on your project's tech stack
 cp -r rules/typescript ~/.claude/rules/typescript
-cp -r rules/angular ~/.claude/rules/angular
 cp -r rules/python ~/.claude/rules/python
 cp -r rules/golang ~/.claude/rules/golang
 cp -r rules/web ~/.claude/rules/web
 cp -r rules/swift ~/.claude/rules/swift
 cp -r rules/php ~/.claude/rules/php
-cp -r rules/arkts ~/.claude/rules/arkts
 
 # Attention ! ! ! Configure according to your actual project requirements; the configuration here is for reference only.
 ```

rules/angular/coding-style.md

@@ -1,182 +0,0 @@
----
-paths:
-  - "**/*.component.ts"
-  - "**/*.component.html"
-  - "**/*.service.ts"
-  - "**/*.directive.ts"
-  - "**/*.pipe.ts"
-  - "**/*.guard.ts"
-  - "**/*.resolver.ts"
-  - "**/*.module.ts"
----
-# Angular Coding Style
-
-> This file extends [common/coding-style.md](../common/coding-style.md) with Angular specific content.
-
-## Version Awareness
-
-Always check the project's Angular version before writing code — features differ significantly between versions. Run `ng version` or inspect `package.json`. When creating a new project, do not pin a version unless the user specifies one.
-
-After generating or modifying Angular code, always run `ng build` to catch errors before finishing.
-
-## File Naming
-
-Follow Angular CLI conventions — one artifact per file:
-
-- `user-profile.component.ts` + `user-profile.component.html` + `user-profile.component.spec.ts`
-- `user.service.ts`, `auth.guard.ts`, `date-format.pipe.ts`
-- Feature folders: `features/users/`, `features/auth/`
-- Generate with the CLI: `ng generate component features/users/user-card`
-
-## Components
-
-Prefer standalone components (v17+ default). Use `OnPush` change detection on all new components.
-
-```typescript
-@Component({
-  selector: 'app-user-card',
-  standalone: true,
-  imports: [RouterModule],
-  templateUrl: './user-card.component.html',
-  changeDetection: ChangeDetectionStrategy.OnPush,
-})
-export class UserCardComponent {
-  user = input.required<User>();
-  select = output<string>();
-}
-```
-
-## Dependency Injection
-
-Use `inject()` over constructor injection. Keep constructors empty or remove them entirely.
-
-```typescript
-// CORRECT
-@Injectable({ providedIn: 'root' })
-export class UserService {
-  private http = inject(HttpClient);
-  private router = inject(Router);
-}
-
-// WRONG: Constructor injection is verbose and harder to tree-shake
-constructor(private http: HttpClient, private router: Router) {}
-```
-
-Use `InjectionToken` for non-class dependencies:
-
-```typescript
-const API_URL = new InjectionToken<string>('API_URL');
-
-// Provide:
-{ provide: API_URL, useValue: 'https://api.example.com' }
-
-// Consume:
-private apiUrl = inject(API_URL);
-```
-
-## Signals
-
-### Core Primitives
-
-```typescript
-count = signal(0);
-doubled = computed(() => this.count() * 2);
-
-increment() {
-  this.count.update(n => n + 1);
-}
-```
-
-### `linkedSignal` — Writable Derived State
-
-Use `linkedSignal` when a signal must reset or adapt when a source changes, but also be independently writable:
-
-```typescript
-selectedOption = linkedSignal(() => this.options()[0]);
-// Resets to first option when options changes, but user can override
-```
-
-### `resource` — Async Data into Signals
-
-Use `resource()` to fetch async data reactively without manual subscriptions:
-
-```typescript
-userResource = resource({
-  request: () => ({ id: this.userId() }),
-  loader: ({ request }) => fetch(`/api/users/${request.id}`).then(r => r.json()),
-});
-
-// Access: userResource.value(), userResource.isLoading(), userResource.error()
-```
-
-### `effect` Usage
-
-Use `effect()` only for side effects that must react to signal changes (logging, third-party DOM manipulation). Never use effects to synchronize signals — use `computed` or `linkedSignal` instead. For DOM work after render, use `afterRenderEffect`.
-
-```typescript
-// CORRECT: Side effect
-effect(() => console.log('User changed:', this.user()));
-
-// WRONG: Use computed instead
-effect(() => { this.fullName.set(`${this.first()} ${this.last()}`); });
-```
-
-## Templates
-
-Use v17+ block syntax. Always provide `track` in `@for`:
-
-```html
-@for (item of items(); track item.id) {
-  <app-item [item]="item" />
-}
-
-@if (isLoading()) {
-  <app-spinner />
-} @else if (error()) {
-  <app-error [message]="error()" />
-} @else {
-  <app-content [data]="data()" />
-}
-```
-
-No logic in templates beyond simple conditionals — move to component methods or pipes.
-
-## Forms
-
-Choose the form strategy that matches the project's existing approach:
-
-- **Signal Forms** (v21+): Preferred for new projects on v21+. Signal-based form state.
-- **Reactive Forms**: `FormBuilder` + `FormGroup` + `FormControl`. Best for complex forms with dynamic validation.
-- **Template-Driven Forms**: `ngModel`. Suitable for simple forms only.
-
-```typescript
-// Reactive Forms — standard approach for most apps
-export class LoginComponent {
-  private fb = inject(FormBuilder);
-
-  form = this.fb.group({
-    email: ['', [Validators.required, Validators.email]],
-    password: ['', [Validators.required, Validators.minLength(8)]],
-  });
-
-  submit() {
-    if (this.form.valid) {
-      // use this.form.value
-    }
-  }
-}
-```
-
-## Component Styles
-
-Use component-level styles with `ViewEncapsulation.Emulated` (default). Avoid `ViewEncapsulation.None` unless building a design system that intentionally bleeds styles.
-
-- Scope styles to the component — do not use global class names inside component stylesheets
-- Use `:host` for host element styling
-- Prefer CSS custom properties for themeable values
-
-## Change Detection
-
-- Default to `ChangeDetectionStrategy.OnPush` on all new components
-- Signals and `async` pipe handle detection automatically — avoid `markForCheck()` and `detectChanges()`
-- Never mutate `@Input()` objects in place when using OnPush

rules/angular/hooks.md

@@ -1,25 +0,0 @@
----
-paths:
-  - "**/*.component.ts"
-  - "**/*.component.html"
-  - "**/*.service.ts"
-  - "**/*.directive.ts"
-  - "**/*.pipe.ts"
-  - "**/*.spec.ts"
----
-# Angular Hooks
-
-> This file extends [common/hooks.md](../common/hooks.md) with Angular specific content.
-
-## PostToolUse Hooks
-
-Configure in `~/.claude/settings.json`:
-
-- **Prettier**: Auto-format `.ts` and `.html` files after edit
-- **ESLint / ng lint**: Run `ng lint` after editing Angular source files to catch decorator misuse, template errors, and style violations
-- **TypeScript check**: Run `tsc --noEmit` after editing `.ts` files
-- **Build check**: Run `ng build` after generating or significantly changing Angular code to catch template and type errors early
-
-## Stop Hooks
-
-- **Lint audit**: Run `ng lint` across modified files before session ends to catch any outstanding violations

rules/angular/patterns.md

@@ -1,249 +0,0 @@
----
-paths:
-  - "**/*.component.ts"
-  - "**/*.component.html"
-  - "**/*.service.ts"
-  - "**/*.store.ts"
-  - "**/*.routes.ts"
----
-# Angular Patterns
-
-> This file extends [common/patterns.md](../common/patterns.md) with Angular specific content.
-
-## Smart / Dumb Component Split
-
-Smart (container) components own data fetching and state. Dumb (presentational) components receive inputs and emit outputs only — no service injection.
-
-```typescript
-// Smart — owns data
-@Component({ standalone: true, changeDetection: ChangeDetectionStrategy.OnPush })
-export class UserPageComponent {
-  private userService = inject(UserService);
-  user = toSignal(this.userService.getUser(this.userId));
-}
-```
-
-```html
-<!-- Dumb — pure presentation -->
-<app-user-card [user]="user()" (select)="onSelect($event)" />
-```
-
-## Service Layer
-
-Services own all data access and business logic. Components delegate — no `HttpClient` in components.
-
-```typescript
-@Injectable({ providedIn: 'root' })
-export class UserService {
-  private http = inject(HttpClient);
-
-  getUsers(): Observable<User[]> {
-    return this.http.get<User[]>('/api/users');
-  }
-}
-```
-
-## Async Data with `resource`
-
-Use `resource()` for reactive async fetching. Prefer over manual RxJS pipelines for simple data loading:
-
-```typescript
-export class UserDetailComponent {
-  userId = input.required<string>();
-
-  userResource = resource({
-    request: () => ({ id: this.userId() }),
-    loader: ({ request }) =>
-      firstValueFrom(inject(UserService).getUser(request.id)),
-  });
-}
-```
-
-Access state: `userResource.value()`, `userResource.isLoading()`, `userResource.error()`, `userResource.reload()`.
-
-## Signal State Patterns
-
-```typescript
-// Local mutable state
-count = signal(0);
-
-// Derived (never duplicated)
-doubled = computed(() => this.count() * 2);
-
-// Writable derived state that resets with source
-selectedItem = linkedSignal(() => this.items()[0]);
-
-// Bridge Observable to signal
-users = toSignal(this.userService.getUsers(), { initialValue: [] });
-```
-
-Never store derived values in separate signals — use `computed`. Never use `effect` to sync signals — use `computed` or `linkedSignal`.
-
-## Subscription Cleanup
-
-Use `takeUntilDestroyed()` for all manual subscriptions. Never use manual `ngOnDestroy` + `Subject` + `takeUntil` on new code.
-
-```typescript
-export class UserComponent {
-  private destroyRef = inject(DestroyRef);
-
-  ngOnInit() {
-    this.userService.updates$
-      .pipe(takeUntilDestroyed(this.destroyRef))
-      .subscribe(update => this.handleUpdate(update));
-  }
-}
-```
-
-## Routing
-
-### Route Definition
-
-```typescript
-// app.routes.ts
-export const routes: Routes = [
-  { path: '', component: HomeComponent },
-  {
-    path: 'admin',
-    canMatch: [authGuard],           // CanMatch prevents loading the chunk at all
-    loadChildren: () => import('./admin/admin.routes').then(m => m.ADMIN_ROUTES),
-  },
-  {
-    path: 'users/:id',
-    resolve: { user: userResolver },
-    component: UserDetailComponent,
-  },
-];
-```
-
-- Use `canMatch` over `canActivate` when the route module should not load for unauthorized users
-- Lazy-load all feature modules with `loadChildren`
-- Pre-fetch data with `resolve` to avoid loading states in components
-
-### Functional Guards
-
-```typescript
-export const authGuard: CanActivateFn = () => {
-  const auth = inject(AuthService);
-  return auth.isAuthenticated()
-    ? true
-    : inject(Router).createUrlTree(['/login']);
-};
-```
-
-### Data Resolvers
-
-```typescript
-export const userResolver: ResolveFn<User> = (route) => {
-  return inject(UserService).getUser(route.paramMap.get('id')!);
-};
-```
-
-### View Transitions
-
-Enable smooth route transitions with the View Transitions API:
-
-```typescript
-// app.config.ts
-provideRouter(routes, withViewTransitions())
-```
-
-## Dependency Injection Patterns
-
-### Scoped Providers
-
-Provide services at component or route level when they should not be singletons:
-
-```typescript
-@Component({
-  providers: [UserEditService],   // scoped to this component subtree
-})
-export class UserEditComponent {}
-```
-
-### `InjectionToken`
-
-```typescript
-export const CONFIG = new InjectionToken<AppConfig>('APP_CONFIG');
-
-// In providers:
-{ provide: CONFIG, useValue: appConfig }
-{ provide: CONFIG, useFactory: () => loadConfig(), deps: [] }
-
-// Consume:
-private config = inject(CONFIG);
-```
-
-### `viewProviders` vs `providers`
-
-- `providers`: Available to the component and all its content children
-- `viewProviders`: Available only to the component's own view (not projected content)
-
-## HTTP Interceptors
-
-Use functional interceptors (v15+) for auth, error handling, and retries:
-
-```typescript
-export const authInterceptor: HttpInterceptorFn = (req, next) => {
-  const token = inject(AuthService).token();
-  if (!token) return next(req);
-  return next(req.clone({ setHeaders: { Authorization: `Bearer ${token}` } }));
-};
-```
-
-Register in `app.config.ts`:
-
-```typescript
-provideHttpClient(withInterceptors([authInterceptor, errorInterceptor]))
-```
-
-## RxJS Operators
-
-- `switchMap` — search, navigation (cancels previous)
-- `mergeMap` — independent parallel requests
-- `exhaustMap` — form submissions (ignores until complete)
-- Always handle errors with `catchError` — never let streams die silently
-
-```typescript
-search$ = this.query$.pipe(
-  debounceTime(300),
-  distinctUntilChanged(),
-  switchMap(q => this.service.search(q).pipe(catchError(() => of([])))),
-);
-```
-
-## Forms
-
-Match the project's existing form strategy. For new v21+ apps, prefer signal forms.
-
-```typescript
-// Reactive Forms — standard for complex forms
-export class UserFormComponent {
-  private fb = inject(FormBuilder);
-
-  form = this.fb.group({
-    name: ['', Validators.required],
-    email: ['', [Validators.required, Validators.email]],
-  });
-}
-```
-
-## Rendering Strategies
-
-- **CSR** (default): Standard SPA
-- **SSR + Hydration**: `ng add @angular/ssr` — improves FCP and SEO
-- **SSG (Prerendering)**: Static pages at build time for content-heavy routes
-
-When using SSR, avoid `window`, `document`, `localStorage` directly — use `isPlatformBrowser` or `DOCUMENT` token.
-
-## Accessibility
-
-Use Angular CDK for headless, accessible components (Accordion, Listbox, Combobox, Menu, Tabs, Toolbar, Tree, Grid). Style ARIA attributes rather than managing them manually:
-
-```css
-[aria-selected="true"] { background: var(--color-selected); }
-```
-
-## Skill Reference
-
-See skill: `angular-developer` for deep guidance on signals, forms, routing, DI, SSR, and accessibility patterns.

rules/angular/security.md

@@ -1,87 +0,0 @@
----
-paths:
-  - "**/*.component.ts"
-  - "**/*.component.html"
-  - "**/*.service.ts"
-  - "**/*.interceptor.ts"
----
-# Angular Security
-
-> This file extends [common/security.md](../common/security.md) with Angular specific content.
-
-## XSS Prevention
-
-Angular auto-sanitizes bound values. Never bypass the sanitizer on user-controlled input.
-
-```typescript
-// WRONG: Bypasses sanitization — XSS risk
-this.safeHtml = this.sanitizer.bypassSecurityTrustHtml(userInput);
-
-// CORRECT: Sanitize explicitly before trusting
-this.safeHtml = this.sanitizer.sanitize(SecurityContext.HTML, userInput);
-```
-
-- Never use `bypassSecurityTrust*` methods without a documented, reviewed reason
-- Avoid `[innerHTML]` with untrusted content — use `innerText` or a sanitizing pipe
-- Never bind `[href]` to user input — Angular does not block `javascript:` URLs in all contexts
-- Never construct template strings from user data
-
-## HTTP Security
-
-Use `HttpClient` exclusively — never raw `fetch()` or `XHR` unless no alternative exists.
-
-```typescript
-// WRONG: Bypasses interceptors (auth headers, error handling, logging)
-const res = await fetch('/api/users');
-
-// CORRECT
-users$ = this.http.get<User[]>('/api/users');
-```
-
-- Attach auth tokens via interceptors — never hardcode in individual service calls
-- Type and validate API responses — treat external data as `unknown` at the boundary
-- Never log HTTP responses that may contain tokens, PII, or credentials
-
-## Secret Management
-
-```typescript
-// WRONG: Hardcoded secret in source
-const apiKey = 'sk-live-xxxx';
-
-// CORRECT: Injected via environment
-import { environment } from '../environments/environment';
-const apiKey = environment.apiKey;
-```
-
-- Treat `environment.ts` as a config shape — never store real secrets in source-controlled environment files
-- Inject production secrets via CI/CD (environment variables, secret managers)
-
-## Route Guards
-
-Every authenticated or role-restricted route must have a guard. Never rely on hiding UI elements alone.
-
-```typescript
-{
-  path: 'admin',
-  canMatch: [authGuard, roleGuard('admin')],
-  loadChildren: () => import('./admin/admin.routes'),
-}
-```
-
-Use `canMatch` for sensitive routes — it prevents the route module from loading at all for unauthorized users.
-
-## SSR Security
-
-When using Angular SSR:
-
-- Never expose server-side environment variables to the client via `TransferState` unless they are intentionally public
-- Sanitize all inputs before server-side rendering — DOM-based XSS can occur server-side too
-- Avoid `window`, `document`, `localStorage` on the server — gate with `isPlatformBrowser` or inject via `DOCUMENT` token
-
-## Content Security Policy
-
-Configure CSP headers server-side. Avoid `unsafe-inline` in `script-src`. When using SSR with inline scripts, use nonces via Angular's CSP support.
-
-## Agent Support
-
-- Use **security-reviewer** skill for comprehensive security audits

rules/angular/testing.md

@@ -1,164 +0,0 @@
----
-paths:
-  - "**/*.spec.ts"
-  - "**/*.test.ts"
----
-# Angular Testing
-
-> This file extends [common/testing.md](../common/testing.md) with Angular specific content.
-
-## Test Runner
-
-Use the test runner configured by the project. Check `angular.json` and `package.json`; Angular projects commonly use Vitest, Jest, or Jasmine + Karma.
-
-```bash
-ng test               # watch mode
-ng test --no-watch    # CI mode
-```
-
-## TestBed Setup
-
-For standalone components, import the component directly. Call `compileComponents()` for components with external templates.
-
-```typescript
-describe('UserCardComponent', () => {
-  let fixture: ComponentFixture<UserCardComponent>;
-
-  beforeEach(async () => {
-    await TestBed.configureTestingModule({
-      imports: [UserCardComponent],
-    }).compileComponents();
-
-    fixture = TestBed.createComponent(UserCardComponent);
-  });
-});
-```
-
-## Signal Inputs
-
-Set signal-based inputs via `fixture.componentRef.setInput()`:
-
-```typescript
-fixture.componentRef.setInput('user', mockUser);
-fixture.detectChanges();
-```
-
-## Component Harnesses
-
-Prefer Angular CDK component harnesses over direct DOM queries for UI interaction. Harnesses are more resilient to markup changes.
-
-```typescript
-import { HarnessLoader } from '@angular/cdk/testing';
-import { TestbedHarnessEnvironment } from '@angular/cdk/testing/testbed';
-import { MatButtonHarness } from '@angular/material/button/testing';
-
-let loader: HarnessLoader;
-
-beforeEach(() => {
-  loader = TestbedHarnessEnvironment.loader(fixture);
-});
-
-it('triggers save on button click', async () => {
-  const button = await loader.getHarness(MatButtonHarness.with({ text: 'Save' }));
-  await button.click();
-  expect(saveSpy).toHaveBeenCalled();
-});
-```
-
-## Router Testing
-
-Use `RouterTestingHarness` for components that depend on the router:
-
-```typescript
-import { RouterTestingHarness } from '@angular/router/testing';
-
-it('renders user on navigation', async () => {
-  const harness = await RouterTestingHarness.create();
-  const component = await harness.navigateByUrl('/users/1', UserDetailComponent);
-  expect(component.userId()).toBe('1');
-});
-```
-
-## Async Testing
-
-Use `fakeAsync` + `tick` for controlled async. Use `waitForAsync` for real async with `fixture.whenStable()`.
-
-```typescript
-it('loads user after delay', fakeAsync(() => {
-  const service = TestBed.inject(UserService);
-  vi.spyOn(service, 'getUser').mockReturnValue(of(mockUser));
-
-  fixture.detectChanges();
-  tick();
-  fixture.detectChanges();
-
-  expect(fixture.nativeElement.querySelector('.name').textContent).toBe(mockUser.name);
-}));
-```
-
-## HTTP Testing
-
-```typescript
-import { provideHttpClientTesting } from '@angular/common/http/testing';
-import { HttpTestingController } from '@angular/common/http/testing';
-
-beforeEach(() => {
-  TestBed.configureTestingModule({
-    providers: [provideHttpClient(), provideHttpClientTesting()],
-  });
-  httpMock = TestBed.inject(HttpTestingController);
-});
-
-afterEach(() => httpMock.verify());
-```
-
-## Service Testing
-
-Inject services directly without a component fixture:
-
-```typescript
-describe('UserService', () => {
-  let service: UserService;
-
-  beforeEach(() => {
-    TestBed.configureTestingModule({
-      providers: [provideHttpClient(), provideHttpClientTesting()],
-    });
-    service = TestBed.inject(UserService);
-  });
-});
-```
-
-## What to Test
-
-- **Services**: All public methods, error paths, HTTP interactions
-- **Components**: Input/output bindings, rendered output for key states, user interactions via harnesses
-- **Pipes**: Pure transformation — plain unit tests, no TestBed needed
-- **Guards/Resolvers**: Return values for allowed and denied states using `RouterTestingHarness`
-
-## E2E Testing
-
-Use the project's configured E2E framework, such as Cypress or Playwright, for critical user flows.
-
-```typescript
-describe('Login flow', () => {
-  it('redirects to dashboard on valid credentials', () => {
-    cy.visit('/login');
-    cy.get('[data-cy=email]').type('user@example.com');
-    cy.get('[data-cy=password]').type('password123');
-    cy.get('[data-cy=submit]').click();
-    cy.url().should('include', '/dashboard');
-  });
-});
-```
-
-- Add `data-cy` attributes to interactive elements for stable selectors
-- Do not rely on CSS classes or text content for selectors in E2E tests
-
-## Coverage
-
-Target ≥80% for services and pipes. Components: test behaviour, not implementation details.
-
-## Skill Reference
-
-See skill: `angular-developer` for comprehensive testing patterns, harness usage, and async best practices.

rules/arkts/coding-style.md

@@ -1,153 +0,0 @@
----
-paths:
-  - "**/*.ets"
-  - "**/*.ts"
-  - "**/module.json5"
-  - "**/oh-package.json5"
-  - "**/build-profile.json5"
----
-# HarmonyOS / ArkTS Coding Style
-
-> This file extends [common/coding-style.md](../common/coding-style.md) with HarmonyOS and ArkTS-specific content.
-
-## ArkTS Language Constraints
-
-ArkTS is a strict, statically-typed subset of TypeScript. Violating these constraints causes **compilation failures**.
-
-### Type System
-
-- No `any` or `unknown` types - always use explicit types
-- No index access types - use type names directly
-- No conditional type aliases or `infer` keyword
-- No intersection types - use inheritance
-- No mapped types - use classes and regular idioms
-- No `typeof` for type annotations - use explicit type declarations
-- No `as const` assertions - use explicit type annotations
-- No structural typing - use inheritance, interfaces, or type aliases
-- No TypeScript utility types except `Partial`, `Required`, `Readonly`, `Record`
-- For `Record<K, V>`, index expression type is `V | undefined`
-- Omit type annotations in `catch` clauses (ArkTS does not support `any`/`unknown`)
-
-### Functions & Classes
-
-- No function expressions - use arrow functions
-- No nested functions - use lambdas
-- No generator functions - use `async`/`await` for multitasking
-- No `Function.apply`, `Function.call`, `Function.bind` - follow traditional OOP for `this`
-- No constructor type expressions - use lambdas
-- No constructor signatures in interfaces or object types - use methods or classes
-- No declaring class fields in constructors - declare in class body
-- No `this` in standalone functions or static methods - only in instance methods
-- No `new.target`
-- No definite assignment assertions (`let v!: T`) - use initialized declarations
-- No class literals - introduce named class types
-- No using classes as objects (assigning to variables) - class declarations introduce types, not values
-- Only one static block per class - merge all static statements
-
-### Object & Property Access
-
-- No dynamic field declaration or `obj["field"]` access - use `obj.field` syntax
-- No `delete` operator - use nullable type with `null` to mark absence
-- No prototype assignment - use classes and interfaces
-- No `in` operator - use `instanceof`
-- No reassigning object methods - use wrapper functions or inheritance
-- No `Symbol()` API (except `Symbol.iterator`)
-- No `globalThis` or global scope - use explicit module exports/imports
-- No namespaces as objects - use classes or modules
-- No statements inside namespaces - use functions
-
-### Destructuring & Spread
-
-- No destructuring assignments or variable declarations - use intermediate objects and field-by-field access
-- No destructuring parameter declarations - pass parameters directly, assign local names manually
-- Spread operator only for expanding arrays (or array-derived classes) into rest parameters or array literals
-
-### Modules & Imports
-
-- No `require()` - use regular `import` syntax
-- No `export = ...` - use normal export/import
-- No import assertions - imports are compile-time in ArkTS
-- No UMD modules
-- No wildcards in module names
-- All `import` statements must appear before all other statements
-- TypeScript codebases must not depend on ArkTS codebases via import (reverse is supported)
-
-### Other Restrictions
-
-- No `var` - use `let`
-- No `for...in` loops - use regular `for` loops for arrays
-- No `with` statements
-- No JSX expressions
-- No `#` private identifiers - use `private` keyword
-- No declaration merging (classes, interfaces, enums) - keep definitions compact
-- No index signatures - use arrays
-- Comma operator only in `for` loops
-- Unary operators `+`, `-`, `~` only for numeric types (no implicit string conversion)
-- Enum members: only same-type compile-time expressions for explicit initializers
-- Function return type inference is limited - specify return types explicitly when calling functions with omitted return types
-
-### Object Literals
-
-- Supported only when compiler can infer the corresponding class or interface
-- NOT supported for: `any`/`Object`/`object` types, classes/interfaces with methods, classes with parameterized constructors, classes with `readonly` fields
-
-## Naming Conventions
-
-- Variables / functions: `camelCase` (e.g., `getUserInfo`, `goodsList`)
-- Classes / interfaces: `PascalCase` (e.g., `UserViewModel`, `IGoodsModel`)
-- Constants: `UPPER_SNAKE_CASE` (e.g., `MAX_PAGE_SIZE`, `COLOR_PRIMARY`)
-- File names: `PascalCase` for components (e.g., `HomePage.ets`), `camelCase` for utilities
-
-## Formatting
-
-- Prefer double quotes for strings
-- Semicolons at end of statements
-- Never use `var` - prefer `const`, then `let`
-- All methods, parameters, return values must have complete type annotations
-
-## File Organization
-
-- Component files (`.ets`): one `@ComponentV2` per file
-- ViewModel files: one ViewModel class per file
-- Model files: related data models may share a file
-- Keep files under 400 lines; extract helpers for files approaching 800 lines
-
-## Comments
-
-- File header: `@file` (file purpose) + `@author` (developer), if the project already uses file headers
-- Public methods: JSDoc with `@param`, `@returns`; add `@example` for complex methods
-- Match the project's existing documentation language; use English unless the repository has already standardized on Chinese comments
-
-## Error Handling
-
-```typescript
-// Use try/catch with proper error handling
-try {
-  const result = await riskyOperation()
-  return result
-} catch (error) {
-  hilog.error(0x0000, 'TAG', 'Operation failed: %{public}s', error)
-  throw new Error('User-friendly error message')
-}
-```
-
-## Immutability
-
-Follow the common immutability principles - create new objects instead of mutating:
-
-```typescript
-// BAD: mutation
-function updateUser(user: UserModel, name: string): UserModel {
-  user.name = name  // direct mutation
-  return user
-}
-
-// GOOD: immutable - create new instance
-function updateUser(user: UserModel, name: string): UserModel {
-  const updated = new UserModel()
-  updated.id = user.id
-  updated.name = name
-  updated.email = user.email
-  return updated
-}
-```

rules/arkts/hooks.md

@@ -1,135 +0,0 @@
----
-paths:
-  - "**/*.ets"
-  - "**/*.ts"
-  - "**/module.json5"
-  - "**/oh-package.json5"
----
-# HarmonyOS / ArkTS Hooks
-
-> This file extends [common/hooks.md](../common/hooks.md) with HarmonyOS-specific build and validation hooks.
-
-## Build Commands
-
-### HAP Package Build
-
-```bash
-# Build HAP package (global hvigor environment)
-hvigorw assembleHap -p product=default
-
-# Build with specific module
-hvigorw assembleHap -p module=entry -p product=default
-
-# Clean build
-hvigorw clean
-```
-
-### DevEco Studio CLI
-
-```bash
-# Check project structure
-hvigorw --version
-
-# Install dependencies
-ohpm install
-
-# Update dependencies
-ohpm update
-```
-
-## Recommended PostToolUse Hooks
-
-### After Editing .ets/.ts Files
-
-Run hvigor build to check for ArkTS compilation errors:
-
-```json
-{
-  "type": "PostToolUse",
-  "matcher": {
-    "tool": ["Edit", "Write"],
-    "filePath": ["**/*.ets", "**/*.ts"]
-  },
-  "hooks": [
-    {
-      "command": "hvigorw assembleHap -p product=default 2>&1 | tail -20",
-      "async": true,
-      "timeout": 60000
-    }
-  ]
-}
-```
-
-### After Editing module.json5
-
-Validate permission and ability declarations:
-
-```json
-{
-  "type": "PostToolUse",
-  "matcher": {
-    "tool": "Edit",
-    "filePath": "**/module.json5"
-  },
-  "hooks": [
-    {
-      "command": "echo '[HarmonyOS] module.json5 modified - verify permissions and abilities'",
-      "async": false
-    }
-  ]
-}
-```
-
-### After Editing oh-package.json5
-
-Reinstall dependencies:
-
-```json
-{
-  "type": "PostToolUse",
-  "matcher": {
-    "tool": "Edit",
-    "filePath": "**/oh-package.json5"
-  },
-  "hooks": [
-    {
-      "command": "ohpm install 2>&1 | tail -10",
-      "async": true,
-      "timeout": 30000
-    }
-  ]
-}
-```
-
-## PreToolUse Hooks
-
-### V1 Decorator Guard
-
-Warn when code contains V1 state management decorators:
-
-```json
-{
-  "type": "PreToolUse",
-  "matcher": {
-    "tool": ["Write", "Edit"],
-    "filePath": "**/*.ets"
-  },
-  "hooks": [
-    {
-      "command": "echo '[HarmonyOS] Reminder: Use @ComponentV2 / @Local / @Param - V1 decorators (@State, @Prop, @Link) are prohibited'"
-    }
-  ]
-}
-```
-
-## Validation Checklist
-
-After each implementation cycle, verify:
-
-- [ ] `hvigorw assembleHap` completes without errors
-- [ ] No V1 decorators in new or modified `.ets` files
-- [ ] No `@ohos.router` imports in new or modified files
-- [ ] All API permissions declared in `module.json5`
-- [ ] All dependencies listed in `oh-package.json5`
-- [ ] Resource strings added to all i18n directories
-- [ ] Dark theme colors provided for new color resources

rules/arkts/patterns.md

@@ -1,236 +0,0 @@
----
-paths:
-  - "**/*.ets"
-  - "**/*.ts"
----
-# HarmonyOS / ArkTS Patterns
-
-> This file extends [common/patterns.md](../common/patterns.md) with HarmonyOS and ArkTS-specific patterns.
-
-## State Management: V2 Only
-
-**MUST use** ArkUI State Management V2. V1 decorators are deprecated and must not be used.
-
-### V2 Decorators
-
-| Decorator | Purpose |
-|-----------|---------|
-| `@ComponentV2` | Marks a struct as a V2 component |
-| `@Local` | Local state within a component |
-| `@Param` | Props received from parent (read-only) |
-| `@Event` | Callback events from child to parent |
-| `@Provider` | Provides state to descendant components |
-| `@Consumer` | Consumes state from ancestor `@Provider` |
-| `@Monitor` | Watches for state changes (replaces V1 `@Watch`) |
-| `@Computed` | Derived/computed values |
-| `@ObservedV2` | Makes a class observable for V2 state management |
-| `@Trace` | Marks observable properties in `@ObservedV2` classes |
-
-### Prohibited V1 Decorators
-
-Never use: `@State`, `@Prop`, `@Link`, `@ObjectLink`, `@Observed`, `@Provide`, `@Consume`, `@Watch`, `@Component` (use `@ComponentV2` instead).
-
-### V2 Component Example
-
-```typescript
-@ObservedV2
-class UserModel {
-  @Trace name: string = ''
-  @Trace age: number = 0
-}
-
-@ComponentV2
-struct UserCard {
-  @Param user: UserModel = new UserModel()
-  @Event onDelete: () => void = () => {}
-
-  build() {
-    Column() {
-      Text(this.user.name)
-        .fontSize($r('app.float.font_size_title'))
-      Text(`${this.user.age}`)
-        .fontSize($r('app.float.font_size_body'))
-      Button($r('app.string.delete'))
-        .onClick(() => this.onDelete())
-    }
-  }
-}
-```
-
-### State Synchronization
-
-```typescript
-@ComponentV2
-struct ParentPage {
-  @Provider('userState') userModel: UserModel = new UserModel()
-
-  build() {
-    Column() {
-      ChildComponent()  // automatically receives @Consumer('userState')
-    }
-  }
-}
-
-@ComponentV2
-struct ChildComponent {
-  @Consumer('userState') userModel: UserModel = new UserModel()
-
-  build() {
-    Text(this.userModel.name)
-  }
-}
-```
-
-## Routing: Navigation Only
-
-**MUST use** `Navigation` component with `NavPathStack`. Never use `@ohos.router`.
-
-### Navigation Setup
-
-```typescript
-@ComponentV2
-struct MainPage {
-  @Local navPathStack: NavPathStack = new NavPathStack()
-
-  build() {
-    Navigation(this.navPathStack) {
-      // Home content
-    }
-    .navDestination(this.routerMap)
-  }
-
-  @Builder
-  routerMap(name: string, param: ESObject) {
-    if (name === 'detail') {
-      DetailPage()
-    } else if (name === 'settings') {
-      SettingsPage()
-    }
-  }
-}
-```
-
-### Page Navigation
-
-```typescript
-// Push a new page
-this.navPathStack.pushPath({ name: 'detail', param: { id: '123' } })
-
-// Replace current page
-this.navPathStack.replacePath({ name: 'settings' })
-
-// Pop back
-this.navPathStack.pop()
-
-// Pop to root
-this.navPathStack.clear()
-```
-
-### NavDestination Sub-page
-
-```typescript
-@ComponentV2
-struct DetailPage {
-  build() {
-    NavDestination() {
-      Column() {
-        Text($r('app.string.detail_title'))
-      }
-    }
-    .title($r('app.string.detail_nav_title'))
-  }
-}
-```
-
-## Architecture Pattern: MVVM
-
-Recommended architecture for HarmonyOS applications:
-
-```
-feature/
-  |-- model/           # Data models (@ObservedV2 classes)
-  |-- viewmodel/       # Business logic (ViewModel classes)
-  |-- view/            # UI components (@ComponentV2 structs)
-  |-- service/         # API calls, data access
-```
-
-- **View**: Only rendering logic, no business logic in `build()`
-- **ViewModel**: All business logic encapsulated here
-- **Model**: Pure data classes with `@ObservedV2` and `@Trace`
-- **Service**: Network requests, database operations, file I/O
-
-## ArkUI Animation Patterns
-
-### State-Driven Animation
-
-```typescript
-@ComponentV2
-struct AnimatedCard {
-  @Local isExpanded: boolean = false
-  @Local cardScale: number = 0.8
-
-  build() {
-    Column() {
-      // Content
-    }
-    .scale({ x: this.cardScale, y: this.cardScale })
-    .animation({ duration: 300, curve: Curve.EaseInOut })
-    .onClick(() => {
-      this.isExpanded = !this.isExpanded
-      this.cardScale = this.isExpanded ? 1.0 : 0.8
-    })
-  }
-}
-```
-
-### Animation Rules
-
-- Prefer native HarmonyOS animation APIs and advanced templates
-- Use declarative UI with state-driven animations (change state variables to trigger animations)
-- Set `renderGroup(true)` for complex sub-component animations to reduce render batches
-- **NEVER** frequently change `width`, `height`, `padding`, `margin` during animations - severe performance impact
-- Use `animateTo` for explicit animation control
-- Prefer `transform` (translate, scale, rotate) and `opacity` for performant animations
-
-## Performance Patterns
-
-### LazyForEach for Large Lists
-
-```typescript
-@ComponentV2
-struct LargeList {
-  @Local dataSource: MyDataSource = new MyDataSource()
-
-  build() {
-    List() {
-      LazyForEach(this.dataSource, (item: ItemModel) => {
-        ListItem() {
-          ItemComponent({ item: item })
-        }
-      }, (item: ItemModel) => item.id)
-    }
-  }
-}
-```
-
-### Component Reuse
-
-- Extract reusable components into separate files
-- Use `@Builder` for lightweight UI fragments within a component
-- Use `@Param` for configurable components
-
-## Resource References
-
-Always define UI constants as resources and reference via `$r()`:
-
-```typescript
-// BAD: hardcoded values
-Text('Hello')
-  .fontSize(16)
-  .fontColor('#333333')
-
-// GOOD: resource references
-Text($r('app.string.greeting'))
-  .fontSize($r('app.float.font_size_body'))
-  .fontColor($r('app.color.text_primary'))
-```

rules/arkts/security.md

@@ -1,141 +0,0 @@
----
-paths:
-  - "**/*.ets"
-  - "**/*.ts"
-  - "**/module.json5"
----
-# HarmonyOS / ArkTS Security
-
-> This file extends [common/security.md](../common/security.md) with HarmonyOS-specific security practices.
-
-## Permission Management
-
-### Declare Permissions in module.json5
-
-All system API calls requiring permissions must be declared:
-
-```json5
-{
-  "module": {
-    "requestPermissions": [
-      {
-        "name": "ohos.permission.INTERNET",
-        "reason": "$string:internet_permission_reason",
-        "usedScene": {
-          "abilities": ["EntryAbility"],
-          "when": "always"
-        }
-      }
-    ]
-  }
-}
-```
-
-### Permission Checklist
-
-Before calling system APIs, verify:
-
-- [ ] Permission declared in `module.json5`
-- [ ] Permission reason string defined in resources (for user-facing permissions)
-- [ ] Runtime permission request implemented for sensitive permissions (camera, location, etc.)
-- [ ] Permission check before API call with graceful fallback on denial
-
-### Runtime Permission Request
-
-```typescript
-import { abilityAccessCtrl, bundleManager, Permissions } from '@kit.AbilityKit';
-
-async function checkAndRequestPermission(permission: Permissions): Promise<boolean> {
-  const atManager = abilityAccessCtrl.createAtManager();
-  const bundleInfo = await bundleManager.getBundleInfoForSelf(
-    bundleManager.BundleFlag.GET_BUNDLE_INFO_WITH_APPLICATION
-  );
-  const tokenId = bundleInfo.appInfo.accessTokenId;
-  const grantStatus = await atManager.checkAccessToken(tokenId, permission);
-
-  if (grantStatus === abilityAccessCtrl.GrantStatus.PERMISSION_GRANTED) {
-    return true;
-  }
-
-  const result = await atManager.requestPermissionsFromUser(getContext(), [permission]);
-  return result.authResults[0] === abilityAccessCtrl.GrantStatus.PERMISSION_GRANTED;
-}
-```
-
-## Secret Management
-
-- **NEVER** hardcode API keys, tokens, or passwords in `.ets`/`.ts` source files
-- Use HarmonyOS Preferences API for non-sensitive configuration
-- Use HarmonyOS Keystore for sensitive credentials
-- Environment-specific configs should be managed via build profiles
-
-```typescript
-// BAD: hardcoded secret
-const API_KEY: string = 'sk-xxxxxxxxxxxx';
-
-// GOOD: from build profile config (non-sensitive)
-import { BuildProfile } from 'BuildProfile';
-const endpoint = BuildProfile.API_ENDPOINT;
-
-// GOOD: use HUKS to encrypt/decrypt data without exposing key material
-import { huks } from '@kit.UniversalKeystoreKit';
-async function decryptWithKeystore(alias: string, nonce: Uint8Array, aad: Uint8Array, cipherData: Uint8Array): Promise<Uint8Array> {
-  const options: huks.HuksOptions = {
-    properties: [
-      { tag: huks.HuksTag.HUKS_TAG_ALGORITHM, value: huks.HuksKeyAlg.HUKS_ALG_AES },
-      { tag: huks.HuksTag.HUKS_TAG_PURPOSE, value: huks.HuksKeyPurpose.HUKS_KEY_PURPOSE_DECRYPT },
-      { tag: huks.HuksTag.HUKS_TAG_BLOCK_MODE, value: huks.HuksCipherMode.HUKS_MODE_GCM },
-      { tag: huks.HuksTag.HUKS_TAG_PADDING, value: huks.HuksKeyPadding.HUKS_PADDING_NONE },
-      { tag: huks.HuksTag.HUKS_TAG_NONCE, value: nonce },
-      { tag: huks.HuksTag.HUKS_TAG_ASSOCIATED_DATA, value: aad }
-    ],
-    inData: cipherData
-  };
-  const handle = await huks.initSession(alias, options);
-  const result = await huks.finishSession(handle.handle, options);
-  return result.outData;
-}
-```
-
-## Input Validation
-
-- Validate all user input before processing
-- Sanitize data before displaying in UI to prevent injection
-- Validate deep link parameters before navigation
-
-```typescript
-// Validate before navigation
-function handleDeepLink(uri: string): void {
-  const allowedPaths: string[] = ['detail', 'settings', 'profile'];
-  const parsed = new URL(uri);
-  const path = parsed.pathname.replace('/', '');
-
-  if (!allowedPaths.includes(path)) {
-    hilog.warn(0x0000, 'DeepLink', 'Invalid deep link path: %{public}s', path);
-    return;
-  }
-
-  navPathStack.pushPath({ name: path });
-}
-```
-
-## Network Security
-
-- Always use HTTPS for network requests
-- Validate server certificates
-- Implement request timeout and retry policies
-- Never log sensitive data (tokens, user credentials) in network request/response logs
-
-## Data Storage Security
-
-- Use encrypted preferences for sensitive local data
-- Clear sensitive data from memory when no longer needed
-- Implement proper data lifecycle management
-- Consider data classification (public, internal, confidential) when choosing storage mechanisms
-
-## Dependency Security
-
-- Only use dependencies from trusted sources (official ohpm registry)
-- Verify dependency versions in `oh-package.json5`
-- Regularly check for known vulnerabilities in third-party libraries
-- Pin dependency versions to avoid unexpected updates

rules/arkts/testing.md

@@ -1,126 +0,0 @@
----
-paths:
-  - "**/*.ets"
-  - "**/*.ts"
-  - "**/ohosTest/**"
----
-# HarmonyOS / ArkTS Testing
-
-> This file extends [common/testing.md](../common/testing.md) with HarmonyOS-specific testing practices.
-
-## Test Framework
-
-HarmonyOS uses the built-in test framework with `@ohos.test` capabilities:
-
-- **Unit tests**: Located in `src/ohosTest/ets/test/`
-- **UI tests**: Use `@ohos.UiTest` for component testing
-- **Instrument tests**: Run on device/emulator
-
-## Test Directory Structure
-
-```
-module/
-  |-- src/
-  |   |-- main/ets/          # Production code
-  |   |-- ohosTest/ets/      # Test code
-  |       |-- test/
-  |       |   |-- Ability.test.ets
-  |       |   |-- List.test.ets
-  |       |-- TestAbility.ets
-  |       |-- TestRunner.ets
-```
-
-## Running Tests
-
-```bash
-# Run all tests for a module
-hvigorw testHap -p product=default
-
-# Run tests on connected device
-hdc shell aa test -b com.example.app -m entry_test -s unittest /ets/TestRunner/OpenHarmonyTestRunner
-```
-
-## Unit Test Example
-
-```typescript
-import { describe, it, expect } from '@ohos/hypium';
-
-export default function UserViewModelTest() {
-  describe('UserViewModel', () => {
-    it('should_initialize_with_empty_state', 0, () => {
-      const vm = new UserViewModel();
-      expect(vm.userName).assertEqual('');
-      expect(vm.isLoading).assertFalse();
-    });
-
-    it('should_update_user_name', 0, () => {
-      const vm = new UserViewModel();
-      vm.updateUserName('Alice');
-      expect(vm.userName).assertEqual('Alice');
-    });
-
-    it('should_handle_empty_input', 0, () => {
-      const vm = new UserViewModel();
-      vm.updateUserName('');
-      expect(vm.userName).assertEqual('');
-      expect(vm.hasError).assertFalse();
-    });
-  });
-}
-```
-
-## UI Test Example
-
-```typescript
-import { describe, it, expect } from '@ohos/hypium';
-import { Driver, ON } from '@ohos.UiTest';
-
-export default function HomePageUITest() {
-  describe('HomePage_UI', () => {
-    it('should_display_title', 0, async () => {
-      const driver = Driver.create();
-      await driver.delayMs(1000);
-
-      const title = await driver.findComponent(ON.text('Home'));
-      expect(title !== null).assertTrue();
-    });
-
-    it('should_navigate_to_detail_on_click', 0, async () => {
-      const driver = Driver.create();
-      const button = await driver.findComponent(ON.id('detailButton'));
-      await button.click();
-      await driver.delayMs(500);
-
-      const detailTitle = await driver.findComponent(ON.text('Detail'));
-      expect(detailTitle !== null).assertTrue();
-    });
-  });
-}
-```
-
-## TDD Workflow for HarmonyOS
-
-Follow the standard TDD cycle adapted for HarmonyOS:
-
-1. **RED**: Write a failing test in `ohosTest/ets/test/`
-2. **GREEN**: Implement minimal code in `main/ets/` to pass
-3. **REFACTOR**: Clean up while keeping tests green
-4. **BUILD**: Run `hvigorw assembleHap` to verify compilation
-5. **VERIFY**: Run tests on device/emulator
-
-## Test Coverage Requirements
-
-- Minimum 80% coverage for all critical application code (ViewModels, services, utilities)
-- **Unit tests**: All utility functions, ViewModel logic, data models
-- **Integration tests**: API calls, database operations, cross-module interactions
-- **E2E / UI tests**: Critical user flows (login, navigation, data submission)
-- Test edge cases: empty data, network errors, permission denials
-
-## Testing Best Practices
-
-- Keep tests independent - no shared mutable state between tests
-- Mock network calls and system APIs in unit tests
-- Use meaningful test names: `should_[expected_behavior]_when_[condition]`
-- Test V2 state management reactivity: verify `@Trace` properties trigger UI updates
-- Test Navigation flows: verify `NavPathStack` push/pop/replace operations
-- Avoid testing framework internals - focus on business logic and user-visible behavior

rules/common/agents.md

@@ -16,7 +16,6 @@ Located in `~/.claude/agents/`:
 | refactor-cleaner | Dead code cleanup | Code maintenance |
 | doc-updater | Documentation | Updating docs |
 | rust-reviewer | Rust code review | Rust projects |
-| harmonyos-app-resolver | HarmonyOS app development | HarmonyOS/ArkTS projects |
 
 ## Immediate Agent Usage
 

rules/fsharp/coding-style.md

@@ -1,112 +0,0 @@
----
-paths:
-  - "**/*.fs"
-  - "**/*.fsx"
----
-# F# Coding Style
-
-> This file extends [common/coding-style.md](../common/coding-style.md) with F#-specific content.
-
-## Standards
-
-- Follow standard F# conventions and leverage the type system for correctness
-- Prefer immutability by default; use `mutable` only when justified by performance
-- Keep modules focused and cohesive
-
-## Types and Models
-
-- Prefer discriminated unions for domain modeling over class hierarchies
-- Use records for data with named fields
-- Use single-case unions for type-safe wrappers around primitives
-- Avoid classes unless interop or mutable state requires them
-
-```fsharp
-type EmailAddress = EmailAddress of string
-
-type OrderStatus =
-    | Pending
-    | Confirmed of confirmedAt: DateTimeOffset
-    | Shipped of trackingNumber: string
-    | Cancelled of reason: string
-
-type Order =
-    { Id: Guid
-      CustomerId: string
-      Status: OrderStatus
-      Items: OrderItem list }
-```
-
-## Immutability
-
-- Records are immutable by default; use `with` expressions for updates
-- Prefer `list`, `map`, `set` over mutable collections
-- Avoid `ref` cells and mutable fields in domain logic
-
-```fsharp
-let rename (profile: UserProfile) newName =
-    { profile with Name = newName }
-```
-
-## Function Style
-
-- Prefer small, composable functions over large methods
-- Use the pipe operator `|>` to build readable data pipelines
-- Prefer pattern matching over if/else chains
-- Use `Option` instead of null; use `Result` for operations that can fail
-
-```fsharp
-let processOrder order =
-    order
-    |> validateItems
-    |> Result.bind calculateTotal
-    |> Result.map applyDiscount
-    |> Result.mapError OrderError
-```
-
-## Async and Error Handling
-
-- Use `task { }` for interop with .NET async APIs
-- Use `async { }` for F#-native async workflows
-- Propagate `CancellationToken` through public async APIs
-- Prefer `Result` and railway-oriented programming over exceptions for expected failures
-
-```fsharp
-let loadOrderAsync (orderId: Guid) (ct: CancellationToken) =
-    task {
-        let! order = repository.FindAsync(orderId, ct)
-        return
-            order
-            |> Option.defaultWith (fun () ->
-                failwith $"Order {orderId} was not found.")
-    }
-```
-
-## Formatting
-
-- Use `fantomas` for automatic formatting
-- Prefer significant whitespace; avoid unnecessary parentheses
-- Remove unused `open` declarations
-
-### Open Declaration Order
-
-Group `open` statements into four sections separated by a blank line, each section sorted lexically within itself:
-
-1. `System.*`
-2. `Microsoft.*`
-3. Third-party namespaces
-4. First-party / project namespaces
-
-```fsharp
-open System
-open System.Collections.Generic
-open System.Threading.Tasks
-
-open Microsoft.AspNetCore.Http
-open Microsoft.Extensions.Logging
-
-open FsCheck.Xunit
-open Swensen.Unquote
-
-open MyApp.Domain
-open MyApp.Infrastructure
-```

rules/fsharp/hooks.md

@@ -1,26 +0,0 @@
----
-paths:
-  - "**/*.fs"
-  - "**/*.fsx"
-  - "**/*.fsproj"
-  - "**/*.sln"
-  - "**/*.slnx"
-  - "**/Directory.Build.props"
-  - "**/Directory.Build.targets"
----
-# F# Hooks
-
-> This file extends [common/hooks.md](../common/hooks.md) with F#-specific content.
-
-## PostToolUse Hooks
-
-Configure in `~/.claude/settings.json`:
-
-- **fantomas**: Auto-format edited F# files
-- **dotnet build**: Verify the solution or project still compiles after edits
-- **dotnet test --no-build**: Re-run the nearest relevant test project after behavior changes
-
-## Stop Hooks
-
-- Run a final `dotnet build` before ending a session with broad F# changes
-- Warn on modified `appsettings*.json` files so secrets do not get committed

rules/fsharp/patterns.md

@@ -1,111 +0,0 @@
----
-paths:
-  - "**/*.fs"
-  - "**/*.fsx"
----
-# F# Patterns
-
-> This file extends [common/patterns.md](../common/patterns.md) with F#-specific content.
-
-## Result Type for Error Handling
-
-Use `Result<'T, 'TError>` with railway-oriented programming instead of exceptions for expected failures.
-
-```fsharp
-type OrderError =
-    | InvalidCustomer of string
-    | EmptyItems
-    | ItemOutOfStock of sku: string
-
-let validateOrder (request: CreateOrderRequest) : Result<ValidatedOrder, OrderError> =
-    if String.IsNullOrWhiteSpace request.CustomerId then
-        Error(InvalidCustomer "CustomerId is required")
-    elif request.Items |> List.isEmpty then
-        Error EmptyItems
-    else
-        Ok { CustomerId = request.CustomerId; Items = request.Items }
-```
-
-## Option for Missing Values
-
-Prefer `Option<'T>` over null. Use `Option.map`, `Option.bind`, and `Option.defaultValue` to transform.
-
-```fsharp
-let findUser (id: Guid) : User option =
-    users |> Map.tryFind id
-
-let getUserEmail userId =
-    findUser userId
-    |> Option.map (fun u -> u.Email)
-    |> Option.defaultValue "unknown@example.com"
-```
-
-## Discriminated Unions for Domain Modeling
-
-Model business states explicitly. The compiler enforces exhaustive handling.
-
-```fsharp
-type PaymentState =
-    | AwaitingPayment of amount: decimal
-    | Paid of paidAt: DateTimeOffset * transactionId: string
-    | Refunded of refundedAt: DateTimeOffset * reason: string
-    | Failed of error: string
-
-let describePayment = function
-    | AwaitingPayment amount -> $"Awaiting payment of {amount:C}"
-    | Paid (at, txn) -> $"Paid at {at} (txn: {txn})"
-    | Refunded (at, reason) -> $"Refunded at {at}: {reason}"
-    | Failed error -> $"Payment failed: {error}"
-```
-
-## Computation Expressions
-
-Use computation expressions to simplify sequential operations that may fail.
-
-```fsharp
-let placeOrder request =
-    result {
-        let! validated = validateOrder request
-        let! inventory = checkInventory validated.Items
-        let! order = createOrder validated inventory
-        return order
-    }
-```
-
-## Module Organization
-
-- Group related functions in modules rather than classes
-- Use `[<RequireQualifiedAccess>]` to prevent name collisions
-- Keep modules small and focused on a single responsibility
-
-```fsharp
-[<RequireQualifiedAccess>]
-module Order =
-    let create customerId items = { Id = Guid.NewGuid(); CustomerId = customerId; Items = items; Status = Pending }
-    let confirm order = { order with Status = Confirmed(DateTimeOffset.UtcNow) }
-    let cancel reason order = { order with Status = Cancelled reason }
-```
-
-## Dependency Injection
-
-- Define dependencies as function parameters or record-of-functions
-- Use interfaces sparingly, primarily at the boundary with .NET libraries
-- Prefer partial application for injecting dependencies into pipelines
-
-```fsharp
-type OrderDeps =
-    { FindOrder: Guid -> Task<Order option>
-      SaveOrder: Order -> Task<unit>
-      SendNotification: Order -> Task<unit> }
-
-let processOrder (deps: OrderDeps) orderId =
-    task {
-        match! deps.FindOrder orderId with
-        | None -> return Error "Order not found"
-        | Some order ->
-            let confirmed = Order.confirm order
-            do! deps.SaveOrder confirmed
-            do! deps.SendNotification confirmed
-            return Ok confirmed
-    }
-```

rules/fsharp/security.md

@@ -1,76 +0,0 @@
----
-paths:
-  - "**/*.fs"
-  - "**/*.fsx"
-  - "**/*.fsproj"
-  - "**/appsettings*.json"
----
-# F# Security
-
-> This file extends [common/security.md](../common/security.md) with F#-specific content.
-
-## Secret Management
-
-- Never hardcode API keys, tokens, or connection strings in source code
-- Use environment variables, user secrets for local development, and a secret manager in production
-- Keep `appsettings.*.json` free of real credentials
-
-```fsharp
-// BAD
-let apiKey = "sk-live-123"
-
-// GOOD
-let apiKey =
-    configuration["OpenAI:ApiKey"]
-    |> Option.ofObj
-    |> Option.defaultWith (fun () -> failwith "OpenAI:ApiKey is not configured.")
-```
-
-## SQL Injection Prevention
-
-- Always use parameterized queries with ADO.NET, Dapper, or EF Core
-- Never concatenate user input into SQL strings
-- Validate sort fields and filter operators before using dynamic query composition
-
-```fsharp
-let findByCustomer (connection: IDbConnection) customerId =
-    task {
-        let sql = "SELECT * FROM Orders WHERE CustomerId = @customerId"
-        return! connection.QueryAsync<Order>(sql, {| customerId = customerId |})
-    }
-```
-
-## Input Validation
-
-- Validate inputs at the application boundary using types
-- Use single-case discriminated unions for validated values
-- Reject invalid input before it enters domain logic
-
-```fsharp
-type ValidatedEmail = private ValidatedEmail of string
-
-module ValidatedEmail =
-    let create (input: string) =
-        if System.Text.RegularExpressions.Regex.IsMatch(input, @"^[^@]+@[^@]+\.[^@]+$") then
-            Ok(ValidatedEmail input)
-        else
-            Error "Invalid email address"
-
-    let value (ValidatedEmail v) = v
-```
-
-## Authentication and Authorization
-
-- Prefer framework auth handlers instead of custom token parsing
-- Enforce authorization policies at endpoint or handler boundaries
-- Never log raw tokens, passwords, or PII
-
-## Error Handling
-
-- Return safe client-facing messages
-- Log detailed exceptions with structured context server-side
-- Do not expose stack traces, SQL text, or filesystem paths in API responses
-
-## References
-
-See skill: `security-review` for broader application security review checklists.

rules/fsharp/testing.md

@@ -1,62 +0,0 @@
----
-paths:
-  - "**/*.fs"
-  - "**/*.fsx"
-  - "**/*.fsproj"
----
-# F# Testing
-
-> This file extends [common/testing.md](../common/testing.md) with F#-specific content.
-
-## Test Framework
-
-- Prefer **xUnit** with **FsUnit.xUnit** for F#-friendly assertions
-- Use **Unquote** for quotation-based assertions with clear failure messages
-- Use **FsCheck.xUnit** for property-based testing
-- Use **NSubstitute** or function stubs for mocking dependencies
-- Use **Testcontainers** when integration tests need real infrastructure
-
-## Test Organization
-
-- Mirror `src/` structure under `tests/`
-- Separate unit, integration, and end-to-end coverage clearly
-- Name tests by behavior, not implementation details
-
-```fsharp
-open Xunit
-open Swensen.Unquote
-
-[<Fact>]
-let ``PlaceOrder returns success when request is valid`` () =
-    let request = { CustomerId = "cust-123"; Items = [ validItem ] }
-    let result = OrderService.placeOrder request
-    test <@ Result.isOk result @>
-
-[<Fact>]
-let ``PlaceOrder returns error when items are empty`` () =
-    let request = { CustomerId = "cust-123"; Items = [] }
-    let result = OrderService.placeOrder request
-    test <@ Result.isError result @>
-```
-
-## Property-Based Testing with FsCheck
-
-```fsharp
-open FsCheck.Xunit
-
-[<Property>]
-let ``order total is never negative`` (items: OrderItem list) =
-    let total = Order.calculateTotal items
-    total >= 0m
-```
-
-## ASP.NET Core Integration Tests
-
-- Use `WebApplicationFactory<TEntryPoint>` for API integration coverage
-- Test auth, validation, and serialization through HTTP, not by bypassing middleware
-
-## Coverage
-
-- Target 80%+ line coverage
-- Focus coverage on domain logic, validation, auth, and failure paths
-- Run `dotnet test` in CI with coverage collection enabled where available

rules/java/patterns.md

@@ -143,5 +143,4 @@ public record ApiResponse<T>(boolean success, T data, String error) {
 ## References
 
 See skill: `springboot-patterns` for Spring Boot architecture patterns.
-See skill: `quarkus-patterns` for Quarkus architecture patterns with REST, Panache, and messaging.
 See skill: `jpa-patterns` for entity design and query optimization.

rules/java/security.md

@@ -97,5 +97,4 @@ try {
 ## References
 
 See skill: `springboot-security` for Spring Security authentication and authorization patterns.
-See skill: `quarkus-security` for Quarkus security with JWT/OIDC, RBAC, and CDI.
 See skill: `security-review` for general security checklists.

rules/java/testing.md

@@ -112,7 +112,6 @@ class OrderRepositoryIT {
 ```
 
 For Spring Boot integration tests, see skill: `springboot-tdd`.
-For Quarkus integration tests, see skill: `quarkus-tdd`.
 
 ## Test Naming
 
@@ -129,5 +128,4 @@ Use descriptive names with `@DisplayName`:
 ## References
 
 See skill: `springboot-tdd` for Spring Boot TDD patterns with MockMvc and Testcontainers.
-See skill: `quarkus-tdd` for Quarkus TDD patterns with REST Assured and Dev Services.
 See skill: `java-coding-standards` for testing expectations.

scripts/ci/catalog.js

@@ -141,7 +141,7 @@ function parseReadmeExpectations(readmeContent) {
     },
     {
       category: 'commands',
-      regex: /^\|\s*(?:\*\*)?Commands(?:\*\*)?\s*\|\s*(\d+)\s*\|\s*Shared\s*\|\s*Instruction-based\s*\|\s*\d+\s*\|$/im,
+      regex: /^\|\s*(?:\*\*)?Commands(?:\*\*)?\s*\|\s*(\d+)\s*\|\s*Shared\s*\|\s*Instruction-based\s*\|\s*31\s*\|$/im,
       source: 'README.md parity table'
     },
     {
@@ -223,7 +223,7 @@ function parseZhDocsReadmeExpectations(readmeContent) {
     },
     {
       category: 'commands',
-      regex: /^\|\s*(?:\*\*)?命令(?:\*\*)?\s*\|\s*(\d+)\s*\|\s*共享\s*\|\s*基于指令\s*\|\s*\d+\s*\|$/im,
+      regex: /^\|\s*(?:\*\*)?命令(?:\*\*)?\s*\|\s*(\d+)\s*\|\s*共享\s*\|\s*基于指令\s*\|\s*31\s*\|$/im,
       source: 'docs/zh-CN/README.md parity table'
     },
     {
@@ -447,7 +447,7 @@ function syncEnglishReadme(content, catalog) {
   );
   nextContent = replaceOrThrow(
     nextContent,
-    /^(\|\s*(?:\*\*)?Commands(?:\*\*)?\s*\|\s*)(\d+)(\s*\|\s*Shared\s*\|\s*Instruction-based\s*\|\s*\d+\s*\|)$/im,
+    /^(\|\s*(?:\*\*)?Commands(?:\*\*)?\s*\|\s*)(\d+)(\s*\|\s*Shared\s*\|\s*Instruction-based\s*\|\s*31\s*\|)$/im,
     (_, prefix, __, suffix) => `${prefix}${catalog.commands.count}${suffix}`,
     'README.md parity table (commands)'
   );
@@ -539,7 +539,7 @@ function syncZhDocsReadme(content, catalog) {
   );
   nextContent = replaceOrThrow(
     nextContent,
-    /^(\|\s*(?:\*\*)?命令(?:\*\*)?\s*\|\s*)(\d+)(\s*\|\s*共享\s*\|\s*基于指令\s*\|\s*\d+\s*\|)$/im,
+    /^(\|\s*(?:\*\*)?命令(?:\*\*)?\s*\|\s*)(\d+)(\s*\|\s*共享\s*\|\s*基于指令\s*\|\s*31\s*\|)$/im,
     (_, prefix, __, suffix) => `${prefix}${catalog.commands.count}${suffix}`,
     'docs/zh-CN/README.md parity table (commands)'
   );

scripts/ci/check-unicode-safety.js

@@ -14,9 +14,7 @@ const ignoredDirs = new Set([
   'node_modules',
   '.dmux',
   '.next',
-  '.venv',
   'coverage',
-  'venv',
 ]);
 
 const textExtensions = new Set([

scripts/consult.js

@@ -11,21 +11,6 @@ const DEFAULT_TARGET = 'claude';
 const DEFAULT_LIMIT = 5;
 const MAX_LIMIT = 20;
 const SCHEMA_VERSION = 'ecc.consult.v1';
-const FUZZY_EXCLUDED_TOKENS = new Set(['review']);
-const MACHINE_LEARNING_CONTEXT_TOKENS = new Set([
-  'data-science',
-  'evals',
-  'evaluation',
-  'inference',
-  'ml',
-  'mle',
-  'mlops',
-  'model',
-  'models',
-  'pytorch',
-  'serving',
-  'training',
-]);
 
 const STOP_WORDS = new Set([
   'a',
@@ -89,7 +74,6 @@ const COMPONENT_ALIASES = Object.freeze({
     'mlops',
     'model',
     'models',
-    'pytorch',
     'training',
     'inference',
     'serving',
@@ -268,7 +252,6 @@ function scoreAgainstQuery(queryTokens, corpusTokens, options = {}) {
 
     if (
       token.length >= 4
-      && !FUZZY_EXCLUDED_TOKENS.has(token)
       && [...corpus].some(corpusToken => (
         corpusToken.length >= 4
         && (corpusToken.includes(token) || token.includes(corpusToken))
@@ -289,7 +272,6 @@ function scoreAgainstQuery(queryTokens, corpusTokens, options = {}) {
 function preferredComponentBonus(component, queryTokens) {
   let bonus = 0;
   const suffix = component.id.split(':')[1];
-  const hasMachineLearningContext = queryTokens.some(token => MACHINE_LEARNING_CONTEXT_TOKENS.has(token));
 
   if (queryTokens[0] === suffix) {
     bonus += 5;
@@ -299,17 +281,7 @@ function preferredComponentBonus(component, queryTokens) {
     bonus += 3;
   }
 
-  if (component.id === 'agent:mle-reviewer' && hasMachineLearningContext) {
-    bonus += 2;
-  }
-
-  if (
-    component.id === 'capability:security'
-    && (
-      queryTokens.some(token => ['audit', 'security', 'threat', 'vulnerability'].includes(token))
-      || (!hasMachineLearningContext && queryTokens.includes('review'))
-    )
-  ) {
+  if (component.id === 'capability:security' && queryTokens.some(token => ['audit', 'review', 'security'].includes(token))) {
     bonus += 4;
   }
 

scripts/harness-audit.js

@@ -187,157 +187,28 @@ function detectTargetMode(rootDir) {
   return 'consumer';
 }
 
-const ECC_PLUGIN_KEY_PATTERNS = [
-  /^ecc@/i,
-  /^everything-claude-code@/i,
-];
-
-const ECC_LEGACY_PLUGIN_DIRS = [
-  'ecc',
-  'ecc@ecc',
-  'everything-claude-code',
-  'everything-claude-code@everything-claude-code',
-];
-
-const ECC_CACHE_MARKETPLACES = ['everything-claude-code', 'ecc'];
-const ECC_CACHE_PLUGIN_NAMES = ['ecc', 'everything-claude-code'];
-
-function uniquePaths(paths) {
-  return [...new Set(paths.filter(Boolean))];
-}
-
-function compareVersionDesc(a, b) {
-  const partsA = String(a).split('.').map(part => parseInt(part, 10) || 0);
-  const partsB = String(b).split('.').map(part => parseInt(part, 10) || 0);
-  const length = Math.max(partsA.length, partsB.length);
-
-  for (let index = 0; index < length; index += 1) {
-    const valueA = partsA[index] || 0;
-    const valueB = partsB[index] || 0;
-    if (valueA !== valueB) {
-      return valueB - valueA;
-    }
-  }
-
-  return 0;
-}
-
-function findPluginJsonUnder(installRoot) {
-  const pluginJson = path.join(installRoot, '.claude-plugin', 'plugin.json');
-  if (fs.existsSync(pluginJson)) {
-    return pluginJson;
-  }
-
-  const fallback = path.join(installRoot, 'plugin.json');
-  return fs.existsSync(fallback) ? fallback : null;
-}
-
-function findPluginInstallFromManifest(installedPluginsPaths) {
-  for (const installedPath of installedPluginsPaths) {
-    if (!fs.existsSync(installedPath)) {
-      continue;
-    }
-
-    const manifest = safeParseJson(safeRead(path.dirname(installedPath), path.basename(installedPath)));
-    if (!manifest || !manifest.plugins) {
-      continue;
-    }
-
-    for (const [key, value] of Object.entries(manifest.plugins)) {
-      if (!ECC_PLUGIN_KEY_PATTERNS.some(pattern => pattern.test(key))) {
-        continue;
-      }
-
-      const entries = Array.isArray(value) ? value : [];
-      for (const entry of entries) {
-        if (!entry || typeof entry.installPath !== 'string' || !entry.installPath.trim()) {
-          continue;
-        }
-
-        const installRoot = path.isAbsolute(entry.installPath)
-          ? entry.installPath
-          : path.resolve(path.dirname(installedPath), entry.installPath);
-        const hit = findPluginJsonUnder(installRoot);
-        if (hit) {
-          return hit;
-        }
-      }
-    }
-  }
-
-  return null;
-}
-
-function findPluginInstallFlatLayout(candidateRoots) {
-  for (const pluginsDir of candidateRoots) {
-    for (const pluginDir of ECC_LEGACY_PLUGIN_DIRS) {
-      const hit = findPluginJsonUnder(path.join(pluginsDir, pluginDir));
-      if (hit) {
-        return hit;
-      }
-    }
-  }
-
-  return null;
-}
-
-function findPluginInstallMarketplaceCache(candidateRoots) {
-  for (const pluginsDir of candidateRoots) {
-    for (const marketplace of ECC_CACHE_MARKETPLACES) {
-      for (const pluginName of ECC_CACHE_PLUGIN_NAMES) {
-        const pluginRoot = path.join(pluginsDir, 'cache', marketplace, pluginName);
-        if (!fs.existsSync(pluginRoot)) {
-          continue;
-        }
-
-        let versions = [];
-        try {
-          versions = fs
-            .readdirSync(pluginRoot, { withFileTypes: true })
-            .filter(entry => entry.isDirectory())
-            .map(entry => entry.name)
-            .sort(compareVersionDesc);
-        } catch {
-          continue;
-        }
-
-        for (const version of versions) {
-          const hit = findPluginJsonUnder(path.join(pluginRoot, version));
-          if (hit) {
-            return hit;
-          }
-        }
-      }
-    }
-  }
-
-  return null;
-}
-
 function findPluginInstall(rootDir) {
-  const homeDirs = uniquePaths([
-    process.env.HOME,
-    process.env.USERPROFILE,
-    os.homedir(),
-  ]);
-  const pluginRoots = uniquePaths([
+  const homeDir = process.env.HOME || process.env.USERPROFILE || os.homedir() || '';
+  const pluginDirs = [
+    'ecc',
+    'ecc@ecc',
+    'everything-claude-code',
+    'everything-claude-code@everything-claude-code',
+  ];
+  const candidateRoots = [
     path.join(rootDir, '.claude', 'plugins'),
-    ...homeDirs.map(homeDir => path.join(homeDir, '.claude', 'plugins')),
-  ]);
-  const installedPluginsPaths = uniquePaths([
-    path.join(rootDir, '.claude', 'plugins', 'installed_plugins.json'),
-    ...homeDirs.map(homeDir => path.join(homeDir, '.claude', 'plugins', 'installed_plugins.json')),
-  ]);
-  const flatRoots = uniquePaths([
-    ...pluginRoots,
-    ...pluginRoots.map(pluginsDir => path.join(pluginsDir, 'marketplaces')),
-  ]);
-
-  return (
-    findPluginInstallFromManifest(installedPluginsPaths)
-    || findPluginInstallFlatLayout(flatRoots)
-    || findPluginInstallMarketplaceCache(pluginRoots)
+    path.join(rootDir, '.claude', 'plugins', 'marketplaces'),
+    homeDir && path.join(homeDir, '.claude', 'plugins'),
+    homeDir && path.join(homeDir, '.claude', 'plugins', 'marketplaces'),
+  ].filter(Boolean);
+  const candidates = candidateRoots.flatMap((pluginsDir) =>
+    pluginDirs.flatMap((pluginDir) => [
+      path.join(pluginsDir, pluginDir, '.claude-plugin', 'plugin.json'),
+      path.join(pluginsDir, pluginDir, 'plugin.json'),
+    ])
   );
+
+  return candidates.find(candidate => fs.existsSync(candidate)) || null;
 }
 
 function getRepoChecks(rootDir) {
@@ -864,6 +735,4 @@ if (require.main === module) {
 module.exports = {
   buildReport,
   parseArgs,
-  findPluginInstall,
-  compareVersionDesc,
 };

scripts/hooks/cost-tracker.js

@@ -8,9 +8,11 @@
 'use strict';
 
 const path = require('path');
-const { ensureDir, appendFile, getClaudeDir } = require('../lib/utils');
-const { estimateCost } = require('../lib/cost-estimate');
-const { sanitizeSessionId } = require('../lib/session-bridge');
+const {
+  ensureDir,
+  appendFile,
+  getClaudeDir,
+} = require('../lib/utils');
 
 const MAX_STDIN = 1024 * 1024;
 let raw = '';
@@ -20,6 +22,23 @@ function toNumber(value) {
   return Number.isFinite(n) ? n : 0;
 }
 
+function estimateCost(model, inputTokens, outputTokens) {
+  // Approximate per-1M-token blended rates. Conservative defaults.
+  const table = {
+    'haiku': { in: 0.8, out: 4.0 },
+    'sonnet': { in: 3.0, out: 15.0 },
+    'opus': { in: 15.0, out: 75.0 },
+  };
+
+  const normalized = String(model || '').toLowerCase();
+  let rates = table.sonnet;
+  if (normalized.includes('haiku')) rates = table.haiku;
+  if (normalized.includes('opus')) rates = table.opus;
+
+  const cost = (inputTokens / 1_000_000) * rates.in + (outputTokens / 1_000_000) * rates.out;
+  return Math.round(cost * 1e6) / 1e6;
+}
+
 process.stdin.setEncoding('utf8');
 process.stdin.on('data', chunk => {
   if (raw.length < MAX_STDIN) {
@@ -36,11 +55,7 @@ process.stdin.on('end', () => {
     const outputTokens = toNumber(usage.output_tokens || usage.completion_tokens || 0);
 
     const model = String(input.model || input._cursor?.model || process.env.CLAUDE_MODEL || 'unknown');
-    const sessionId =
-      sanitizeSessionId(input.session_id) ||
-      sanitizeSessionId(process.env.ECC_SESSION_ID) ||
-      sanitizeSessionId(process.env.CLAUDE_SESSION_ID) ||
-      'default';
+    const sessionId = String(process.env.ECC_SESSION_ID || process.env.CLAUDE_SESSION_ID || 'default');
 
     const metricsDir = path.join(getClaudeDir(), 'metrics');
     ensureDir(metricsDir);
@@ -51,7 +66,7 @@ process.stdin.on('end', () => {
       model,
       input_tokens: inputTokens,
       output_tokens: outputTokens,
-      estimated_cost_usd: estimateCost(model, inputTokens, outputTokens)
+      estimated_cost_usd: estimateCost(model, inputTokens, outputTokens),
     };
 
     appendFile(path.join(metricsDir, 'costs.jsonl'), `${JSON.stringify(row)}\n`);

scripts/hooks/ecc-context-monitor.js

@@ -1,242 +0,0 @@
-#!/usr/bin/env node
-/**
- * ECC Context Monitor — PostToolUse hook
- *
- * Reads bridge file from ecc-metrics-bridge.js and injects agent-facing
- * warnings when thresholds are crossed: context exhaustion, high cost,
- * scope creep, or tool loops.
- */
-
-'use strict';
-
-const fs = require('fs');
-const os = require('os');
-const path = require('path');
-const { sanitizeSessionId, readBridge } = require('../lib/session-bridge');
-
-const CONTEXT_WARNING_PCT = 35;
-const CONTEXT_CRITICAL_PCT = 25;
-const COST_NOTICE_USD = 5;
-const COST_WARNING_USD = 10;
-const COST_CRITICAL_USD = 50;
-const FILES_WARNING_COUNT = 20;
-const LOOP_THRESHOLD = 3;
-const STALE_SECONDS = 60;
-const DEBOUNCE_CALLS = 5;
-
-/**
- * Get debounce state file path.
- * @param {string} sessionId
- * @returns {string}
- */
-function getWarnPath(sessionId) {
-  return path.join(os.tmpdir(), `ecc-ctx-warn-${sessionId}.json`);
-}
-
-/**
- * Read debounce state.
- * @param {string} sessionId
- * @returns {object}
- */
-function readWarnState(sessionId) {
-  try {
-    return JSON.parse(fs.readFileSync(getWarnPath(sessionId), 'utf8'));
-  } catch {
-    return { callsSinceWarn: 0, lastSeverity: null };
-  }
-}
-
-/**
- * Write debounce state.
- * @param {string} sessionId
- * @param {object} state
- */
-function writeWarnState(sessionId, state) {
-  const target = getWarnPath(sessionId);
-  const tmp = `${target}.tmp`;
-  fs.writeFileSync(tmp, JSON.stringify(state), 'utf8');
-  fs.renameSync(tmp, target);
-}
-
-/**
- * Detect tool loops from recent_tools ring buffer.
- * @param {Array} recentTools
- * @returns {{detected: boolean, tool: string, count: number}}
- */
-function detectLoop(recentTools) {
-  if (!Array.isArray(recentTools) || recentTools.length < LOOP_THRESHOLD) {
-    return { detected: false, tool: '', count: 0 };
-  }
-  const counts = {};
-  for (const entry of recentTools) {
-    const key = `${entry.tool}:${entry.hash}`;
-    counts[key] = (counts[key] || 0) + 1;
-  }
-  for (const [key, count] of Object.entries(counts)) {
-    if (count >= LOOP_THRESHOLD) {
-      return { detected: true, tool: key.split(':')[0], count };
-    }
-  }
-  return { detected: false, tool: '', count: 0 };
-}
-
-/**
- * Evaluate all warning conditions against bridge data.
- * Returns array of {severity, type, message} sorted by severity desc.
- */
-function evaluateConditions(bridge) {
-  const warnings = [];
-  const remaining = bridge.context_remaining_pct;
-
-  // Context warnings (skip if no context data)
-  if (remaining !== null && remaining !== undefined) {
-    if (remaining <= CONTEXT_CRITICAL_PCT) {
-      warnings.push({
-        severity: 3,
-        type: 'context',
-        message:
-          `CONTEXT CRITICAL: ${remaining}% remaining. Context nearly exhausted. ` +
-          'Inform the user that context is low and ask how they want to proceed. ' +
-          'Do NOT autonomously save state or write handoff files unless the user asks.'
-      });
-    } else if (remaining <= CONTEXT_WARNING_PCT) {
-      warnings.push({
-        severity: 2,
-        type: 'context',
-        message: `CONTEXT WARNING: ${remaining}% remaining. ` + 'Be aware that context is getting limited. Avoid starting new complex work.'
-      });
-    }
-  }
-
-  // Cost warnings
-  const cost = bridge.total_cost_usd || 0;
-  if (cost > COST_CRITICAL_USD) {
-    warnings.push({
-      severity: 3,
-      type: 'cost',
-      message: `COST CRITICAL: Session cost is $${cost.toFixed(2)}. ` + 'Stop and inform the user about high cost before continuing.'
-    });
-  } else if (cost > COST_WARNING_USD) {
-    warnings.push({
-      severity: 2,
-      type: 'cost',
-      message: `COST WARNING: Session cost is $${cost.toFixed(2)}. ` + 'Review whether the current approach justifies the expense.'
-    });
-  } else if (cost > COST_NOTICE_USD) {
-    warnings.push({
-      severity: 1,
-      type: 'cost',
-      message: `COST NOTICE: Session cost is $${cost.toFixed(2)}. ` + 'Consider whether the current approach is efficient.'
-    });
-  }
-
-  // File scope warning
-  const fileCount = bridge.files_modified_count || 0;
-  if (fileCount > FILES_WARNING_COUNT) {
-    warnings.push({
-      severity: 2,
-      type: 'scope',
-      message: `SCOPE WARNING: ${fileCount} files modified this session. ` + 'Consider whether changes are too scattered.'
-    });
-  }
-
-  // Loop detection
-  const loop = detectLoop(bridge.recent_tools);
-  if (loop.detected) {
-    warnings.push({
-      severity: 2,
-      type: 'loop',
-      message: `LOOP WARNING: Tool '${loop.tool}' called ${loop.count} times ` + 'with same parameters in last 5 calls. This may indicate a stuck loop.'
-    });
-  }
-
-  return warnings.sort((a, b) => b.severity - a.severity);
-}
-
-/**
- * Map numeric severity to label.
- */
-function severityLabel(n) {
-  if (n >= 3) return 'critical';
-  if (n >= 2) return 'warning';
-  return 'notice';
-}
-
-/**
- * @param {string} rawInput - Raw JSON string from stdin
- * @returns {string} JSON output with additionalContext or pass-through
- */
-function run(rawInput) {
-  try {
-    const input = rawInput.trim() ? JSON.parse(rawInput) : {};
-
-    const sessionId = sanitizeSessionId(input.session_id) || sanitizeSessionId(process.env.ECC_SESSION_ID) || sanitizeSessionId(process.env.CLAUDE_SESSION_ID);
-
-    if (!sessionId) return rawInput;
-
-    const bridge = readBridge(sessionId);
-    if (!bridge) return rawInput;
-
-    // Stale check for context warnings
-    const now = Math.floor(Date.now() / 1000);
-    const lastTs = bridge.last_timestamp ? Math.floor(new Date(bridge.last_timestamp).getTime() / 1000) : 0;
-    const isStale = lastTs > 0 && now - lastTs > STALE_SECONDS;
-
-    // If bridge is stale, null out context data (still check cost/scope/loop)
-    const evalBridge = isStale ? { ...bridge, context_remaining_pct: null } : bridge;
-
-    const warnings = evaluateConditions(evalBridge);
-    if (warnings.length === 0) return rawInput;
-
-    // Debounce logic
-    const warnState = readWarnState(sessionId);
-    warnState.callsSinceWarn = (warnState.callsSinceWarn || 0) + 1;
-
-    const topSeverity = severityLabel(warnings[0].severity);
-    const severityEscalated = topSeverity === 'critical' && warnState.lastSeverity !== 'critical';
-
-    const isFirst = !warnState.lastSeverity;
-    if (!isFirst && warnState.callsSinceWarn < DEBOUNCE_CALLS && !severityEscalated) {
-      writeWarnState(sessionId, warnState);
-      return rawInput;
-    }
-
-    // Reset debounce, emit warning
-    warnState.callsSinceWarn = 0;
-    warnState.lastSeverity = topSeverity;
-    writeWarnState(sessionId, warnState);
-
-    // Combine top 2 warnings
-    const message = warnings
-      .slice(0, 2)
-      .map(w => w.message)
-      .join('\n');
-
-    const output = {
-      hookSpecificOutput: {
-        hookEventName: 'PostToolUse',
-        additionalContext: message
-      }
-    };
-
-    return JSON.stringify(output);
-  } catch {
-    // Never block tool execution
-    return rawInput;
-  }
-}
-
-if (require.main === module) {
-  let data = '';
-  const MAX_STDIN = 1024 * 1024;
-  process.stdin.setEncoding('utf8');
-  process.stdin.on('data', chunk => {
-    if (data.length < MAX_STDIN) data += chunk.substring(0, MAX_STDIN - data.length);
-  });
-  process.stdin.on('end', () => {
-    process.stdout.write(run(data));
-    process.exit(0);
-  });
-}
-
-module.exports = { run, evaluateConditions, detectLoop, severityLabel };

scripts/hooks/ecc-metrics-bridge.js

@@ -1,198 +0,0 @@
-#!/usr/bin/env node
-/**
- * ECC Metrics Bridge — PostToolUse hook
- *
- * Maintains a running session aggregate in /tmp/ecc-metrics-{session}.json.
- * This bridge file is read by ecc-statusline.js and ecc-context-monitor.js,
- * avoiding the need to scan large JSONL logs on every invocation.
- */
-
-'use strict';
-
-const crypto = require('crypto');
-const fs = require('fs');
-const path = require('path');
-const { sanitizeSessionId, readBridge, writeBridgeAtomic } = require('../lib/session-bridge');
-const { getClaudeDir } = require('../lib/utils');
-
-const MAX_STDIN = 1024 * 1024;
-const MAX_FILES_TRACKED = 200;
-const RECENT_TOOLS_SIZE = 5;
-const HASH_INPUT_LIMIT = 2048;
-
-function toNumber(value) {
-  const n = Number(value);
-  return Number.isFinite(n) ? n : 0;
-}
-
-function stableStringify(value, depth = 0) {
-  if (depth > 4) return '[depth-limit]';
-  if (value === null || typeof value !== 'object') return JSON.stringify(value);
-  if (Array.isArray(value)) {
-    return `[${value.map(item => stableStringify(item, depth + 1)).join(',')}]`;
-  }
-  return `{${Object.keys(value)
-    .sort()
-    .map(key => `${JSON.stringify(key)}:${stableStringify(value[key], depth + 1)}`)
-    .join(',')}}`;
-}
-
-/**
- * Hash tool call for loop detection.
- * Uses tool name + a key parameter when available, otherwise a stable input digest.
- */
-function hashToolCall(toolName, toolInput) {
-  const name = String(toolName || '');
-  let key = '';
-  if (name === 'Bash') {
-    key = String(toolInput?.command || '').slice(0, 160);
-  } else if (toolInput?.file_path) {
-    key = String(toolInput.file_path);
-  } else {
-    key = stableStringify(toolInput || {}).slice(0, HASH_INPUT_LIMIT);
-  }
-  return crypto.createHash('sha256').update(`${name}:${key}`).digest('hex').slice(0, 8);
-}
-
-/**
- * Extract modified file paths from tool input.
- */
-function extractFilePaths(toolName, toolInput) {
-  const paths = [];
-  if (!toolInput || typeof toolInput !== 'object') return paths;
-
-  const fp = toolInput.file_path;
-  if (fp && typeof fp === 'string') paths.push(fp);
-
-  const edits = toolInput.edits;
-  if (Array.isArray(edits)) {
-    for (const edit of edits) {
-      if (edit?.file_path && typeof edit.file_path === 'string') {
-        paths.push(edit.file_path);
-      }
-    }
-  }
-
-  return paths;
-}
-
-/**
- * Read cumulative cost for a session from the tail of costs.jsonl.
- * Reads last 8KB to avoid scanning entire file.
- */
-function readSessionCost(sessionId) {
-  try {
-    const costsPath = path.join(getClaudeDir(), 'metrics', 'costs.jsonl');
-    const stat = fs.statSync(costsPath);
-    const readSize = Math.min(stat.size, 8192);
-    const fd = fs.openSync(costsPath, 'r');
-    try {
-      const buf = Buffer.alloc(readSize);
-      fs.readSync(fd, buf, 0, readSize, Math.max(0, stat.size - readSize));
-      const lines = buf.toString('utf8').split('\n').filter(Boolean);
-
-      let totalCost = 0;
-      let totalIn = 0;
-      let totalOut = 0;
-      for (const line of lines) {
-        try {
-          const row = JSON.parse(line);
-          if (row.session_id === sessionId) {
-            totalCost += toNumber(row.estimated_cost_usd);
-            totalIn += toNumber(row.input_tokens);
-            totalOut += toNumber(row.output_tokens);
-          }
-        } catch {
-          /* skip malformed lines */
-        }
-      }
-      return { totalCost, totalIn, totalOut };
-    } finally {
-      fs.closeSync(fd);
-    }
-  } catch {
-    return { totalCost: 0, totalIn: 0, totalOut: 0 };
-  }
-}
-
-/**
- * @param {string} rawInput - Raw JSON string from stdin
- * @returns {string} Pass-through
- */
-function run(rawInput) {
-  try {
-    const input = rawInput.trim() ? JSON.parse(rawInput) : {};
-    const toolName = String(input.tool_name || '');
-    const toolInput = input.tool_input || {};
-
-    const sessionId = sanitizeSessionId(input.session_id) || sanitizeSessionId(process.env.ECC_SESSION_ID) || sanitizeSessionId(process.env.CLAUDE_SESSION_ID);
-
-    if (!sessionId) return rawInput;
-
-    const now = new Date().toISOString();
-    const bridge = readBridge(sessionId) || {
-      session_id: sessionId,
-      total_cost_usd: 0,
-      total_input_tokens: 0,
-      total_output_tokens: 0,
-      tool_count: 0,
-      files_modified_count: 0,
-      files_modified: [],
-      recent_tools: [],
-      first_timestamp: now,
-      last_timestamp: now,
-      context_remaining_pct: null
-    };
-
-    // Increment tool count
-    bridge.tool_count = (bridge.tool_count || 0) + 1;
-    bridge.last_timestamp = now;
-    if (!bridge.first_timestamp) bridge.first_timestamp = now;
-
-    // Track modified files (Write/Edit/MultiEdit only)
-    const isWriteOp = /^(Write|Edit|MultiEdit)$/i.test(toolName);
-    if (isWriteOp) {
-      const newPaths = extractFilePaths(toolName, toolInput);
-      const existing = new Set(bridge.files_modified || []);
-      for (const p of newPaths) {
-        if (existing.size < MAX_FILES_TRACKED && !existing.has(p)) {
-          existing.add(p);
-        }
-      }
-      bridge.files_modified = [...existing];
-      bridge.files_modified_count = existing.size;
-    }
-
-    // Ring buffer for loop detection
-    const recent = bridge.recent_tools || [];
-    recent.push({ tool: toolName, hash: hashToolCall(toolName, toolInput) });
-    if (recent.length > RECENT_TOOLS_SIZE) recent.shift();
-    bridge.recent_tools = recent;
-
-    // Update cost from costs.jsonl tail
-    const costs = readSessionCost(sessionId);
-    bridge.total_cost_usd = Math.round(costs.totalCost * 1e6) / 1e6;
-    bridge.total_input_tokens = costs.totalIn;
-    bridge.total_output_tokens = costs.totalOut;
-
-    writeBridgeAtomic(sessionId, bridge);
-  } catch {
-    // Never block tool execution
-  }
-
-  return rawInput;
-}
-
-if (require.main === module) {
-  let data = '';
-  process.stdin.setEncoding('utf8');
-  process.stdin.on('data', chunk => {
-    if (data.length < MAX_STDIN) data += chunk.substring(0, MAX_STDIN - data.length);
-  });
-  process.stdin.on('end', () => {
-    process.stdout.write(run(data));
-    process.exit(0);
-  });
-}
-
-module.exports = { run, hashToolCall, extractFilePaths, readSessionCost, stableStringify };

scripts/hooks/ecc-statusline.js

@@ -1,168 +0,0 @@
-#!/usr/bin/env node
-/**
- * ECC Statusline — statusLine command
- *
- * Displays: model | task | $cost Nt Nf Nm | dir ██░░ N%
- *
- * Registered in settings.json under "statusLine", not in hooks.json.
- * Reads bridge file from ecc-metrics-bridge.js and stdin from Claude Code runtime.
- */
-
-'use strict';
-
-const fs = require('fs');
-const os = require('os');
-const path = require('path');
-const { sanitizeSessionId, readBridge, writeBridgeAtomic } = require('../lib/session-bridge');
-
-const AUTO_COMPACT_BUFFER_PCT = 16.5;
-const MAX_STDIN = 1024 * 1024;
-
-/**
- * Format duration from ISO timestamp to now.
- * @param {string} isoTimestamp
- * @returns {string} e.g. "5s", "12m", "1h23m"
- */
-function formatDuration(isoTimestamp) {
-  if (!isoTimestamp) return '?';
-  const elapsed = Math.floor((Date.now() - new Date(isoTimestamp).getTime()) / 1000);
-  if (elapsed < 0) return '?';
-  if (elapsed < 60) return `${elapsed}s`;
-  const mins = Math.floor(elapsed / 60);
-  if (mins < 60) return `${mins}m`;
-  const hours = Math.floor(mins / 60);
-  const remMins = mins % 60;
-  return remMins > 0 ? `${hours}h${remMins}m` : `${hours}h`;
-}
-
-/**
- * Build context progress bar with ANSI colors.
- * @param {number} remaining - Raw remaining percentage from Claude Code
- * @returns {string} Colored bar string
- */
-function buildContextBar(remaining) {
-  if (remaining === null || remaining === undefined) return '';
-
-  const usableRemaining = Math.max(0, ((remaining - AUTO_COMPACT_BUFFER_PCT) / (100 - AUTO_COMPACT_BUFFER_PCT)) * 100);
-  const used = Math.max(0, Math.min(100, Math.round(100 - usableRemaining)));
-
-  const filled = Math.floor(used / 10);
-  const bar = '\u2588'.repeat(filled) + '\u2591'.repeat(10 - filled);
-
-  if (used < 50) return ` \x1b[32m${bar} ${used}%\x1b[0m`;
-  if (used < 65) return ` \x1b[33m${bar} ${used}%\x1b[0m`;
-  if (used < 80) return ` \x1b[38;5;208m${bar} ${used}%\x1b[0m`;
-  return ` \x1b[5;31m${bar} ${used}%\x1b[0m`;
-}
-
-/**
- * Read current in-progress task from todos directory.
- * @param {string} sessionId
- * @returns {string} Task activeForm text or empty string
- */
-function readCurrentTask(sessionId) {
-  try {
-    const safeSessionId = sanitizeSessionId(sessionId);
-    if (!safeSessionId) return '';
-
-    const claudeDir = process.env.CLAUDE_CONFIG_DIR || path.join(os.homedir(), '.claude');
-    const todosDir = path.join(claudeDir, 'todos');
-    if (!fs.existsSync(todosDir)) return '';
-
-    const files = fs
-      .readdirSync(todosDir)
-      .filter(f => f.startsWith(safeSessionId) && f.includes('-agent-') && f.endsWith('.json'))
-      .map(f => ({ name: f, mtime: fs.statSync(path.join(todosDir, f)).mtime }))
-      .sort((a, b) => b.mtime - a.mtime);
-
-    if (files.length === 0) return '';
-
-    const todos = JSON.parse(fs.readFileSync(path.join(todosDir, files[0].name), 'utf8'));
-    const inProgress = todos.find(t => t.status === 'in_progress');
-    return inProgress?.activeForm || '';
-  } catch {
-    return '';
-  }
-}
-
-function runStatusline() {
-  let input = '';
-  const stdinTimeout = setTimeout(() => process.exit(0), 3000);
-  process.stdin.setEncoding('utf8');
-  process.stdin.on('data', chunk => {
-    if (input.length < MAX_STDIN) {
-      input += chunk.substring(0, MAX_STDIN - input.length);
-    }
-  });
-  process.stdin.on('end', () => {
-    clearTimeout(stdinTimeout);
-    try {
-      const data = JSON.parse(input);
-      const model = data.model?.display_name || 'Claude';
-      const dir = data.workspace?.current_dir || process.cwd();
-      const session = data.session_id || '';
-      const remaining = data.context_window?.remaining_percentage;
-
-      const sessionId = sanitizeSessionId(session);
-      const bridge = sessionId ? readBridge(sessionId) : null;
-
-      // Write context % back to bridge for context-monitor
-      if (sessionId && bridge && remaining !== null && remaining !== undefined) {
-        bridge.context_remaining_pct = remaining;
-        try {
-          writeBridgeAtomic(sessionId, bridge);
-        } catch {
-          /* best effort */
-        }
-      }
-
-      // Current task
-      const task = sessionId ? readCurrentTask(sessionId) : '';
-
-      // Metrics from bridge
-      let metricsStr = '';
-      if (bridge) {
-        const parts = [];
-        if (bridge.total_cost_usd > 0) {
-          parts.push(`$${bridge.total_cost_usd.toFixed(2)}`);
-        }
-        if (bridge.tool_count > 0) {
-          parts.push(`${bridge.tool_count}t`);
-        }
-        if (bridge.files_modified_count > 0) {
-          parts.push(`${bridge.files_modified_count}f`);
-        }
-        const dur = formatDuration(bridge.first_timestamp);
-        if (dur !== '?') {
-          parts.push(dur);
-        }
-        if (parts.length > 0) {
-          metricsStr = `\x1b[36m${parts.join(' ')}\x1b[0m`;
-        }
-      }
-
-      // Context bar
-      const ctx = buildContextBar(remaining);
-
-      // Build output
-      const dirname = path.basename(dir);
-      const segments = [`\x1b[2m${model}\x1b[0m`];
-
-      if (task) {
-        segments.push(`\x1b[1m${task}\x1b[0m`);
-      }
-      if (metricsStr) {
-        segments.push(metricsStr);
-      }
-      segments.push(`\x1b[2m${dirname}\x1b[0m`);
-
-      process.stdout.write(segments.join(' \x1b[2m\u2502\x1b[0m ') + ctx);
-    } catch {
-      // Silent fail
-    }
-  });
-}
-
-module.exports = { formatDuration, buildContextBar, readCurrentTask, MAX_STDIN };
-
-if (require.main === module) runStatusline();

scripts/hooks/session-start.js

@@ -33,8 +33,6 @@ const MAX_INJECTED_LEARNED_SKILLS = 6;
 const MAX_LEARNED_SKILL_SUMMARY_CHARS = 220;
 const DEFAULT_SESSION_START_CONTEXT_MAX_CHARS = 8000;
 const DEFAULT_SESSION_RETENTION_DAYS = 30;
-const SESSION_START_MODE_INVALID = 'invalid';
-const SESSION_START_MODE_SKIP = 'skip';
 
 /**
  * Resolve a filesystem path to its canonical (real) form.
@@ -103,33 +101,6 @@ function getSessionStartMaxContextChars() {
   return Number.isInteger(parsed) && parsed >= 0 ? parsed : DEFAULT_SESSION_START_CONTEXT_MAX_CHARS;
 }
 
-function getSessionStartMode(rawInput) {
-  const input = String(rawInput || '');
-  if (!input.trim()) return null;
-
-  let payload;
-  try {
-    payload = JSON.parse(input);
-  } catch {
-    log(`[SessionStart] Invalid stdin payload; skipping previous session summary injection. Length: ${input.length}`);
-    return SESSION_START_MODE_INVALID;
-  }
-
-  const supportedModes = new Set(['startup', 'resume', 'clear', 'compact']);
-  const hookName = typeof payload.hookName === 'string' ? payload.hookName.trim() : '';
-  if (hookName.startsWith('SessionStart:')) {
-    const mode = hookName.slice('SessionStart:'.length).trim().toLowerCase();
-    return supportedModes.has(mode) ? mode : SESSION_START_MODE_SKIP;
-  }
-
-  if (payload.hook_event_name === 'SessionStart') {
-    const mode = typeof payload.source === 'string' ? payload.source.trim().toLowerCase() : '';
-    return supportedModes.has(mode) ? mode : SESSION_START_MODE_SKIP;
-  }
-
-  return SESSION_START_MODE_SKIP;
-}
-
 function limitSessionStartContext(additionalContext, maxChars = getSessionStartMaxContextChars()) {
   const context = String(additionalContext || '');
 
@@ -197,8 +168,8 @@ function pruneExpiredSessions(searchDirs, retentionDays) {
  *
  * Priority (highest to lowest):
  *   1. Exact worktree (cwd) match — most recent
- *   2. Same project name match for legacy sessions without Worktree metadata
- *   3. No injection when sessions belong to a different worktree/project
+ *   2. Same project name match — most recent
+ *   3. Fallback to overall most recent (original behavior)
  *
  * Sessions are already sorted newest-first, so the first match in each
  * category wins.
@@ -218,12 +189,18 @@ function selectMatchingSession(sessions, cwd, currentProject) {
 
   let projectMatch = null;
   let projectMatchContent = null;
-  let readableSessions = 0;
+  let fallbackSession = null;
+  let fallbackContent = null;
 
   for (const session of sessions) {
     const content = readFile(session.path);
     if (!content) continue;
-    readableSessions++;
+
+    // Cache first readable session+content pair for fallback
+    if (!fallbackSession) {
+      fallbackSession = session;
+      fallbackContent = content;
+    }
 
     // Extract **Worktree:** field
     const worktreeMatch = content.match(/\*\*Worktree:\*\*\s*(.+)$/m);
@@ -235,9 +212,8 @@ function selectMatchingSession(sessions, cwd, currentProject) {
       return { session, content, matchReason: 'worktree' };
     }
 
-    // Project name match is only safe for legacy session files written before
-    // Worktree metadata existed. A different explicit Worktree is not a match.
-    if (!projectMatch && currentProject && !sessionWorktree) {
+    // Project name match — keep searching for a worktree match
+    if (!projectMatch && currentProject) {
       const projectFieldMatch = content.match(/\*\*Project:\*\*\s*(.+)$/m);
       const sessionProject = projectFieldMatch ? projectFieldMatch[1].trim() : '';
       if (sessionProject && sessionProject === currentProject) {
@@ -251,9 +227,12 @@ function selectMatchingSession(sessions, cwd, currentProject) {
     return { session: projectMatch, content: projectMatchContent, matchReason: 'project' };
   }
 
-  log(readableSessions > 0
-    ? '[SessionStart] No worktree/project session match found'
-    : '[SessionStart] All session files were unreadable');
+  // Fallback: most recent readable session (original behavior)
+  if (fallbackSession) {
+    return { session: fallbackSession, content: fallbackContent, matchReason: 'recency-fallback' };
+  }
+
+  log('[SessionStart] All session files were unreadable');
   return null;
 }
 
@@ -519,7 +498,6 @@ async function main() {
   const maxContextChars = getSessionStartMaxContextChars();
   const explicitContextDisabled = isSessionStartContextDisabled();
   const shouldInjectContext = !explicitContextDisabled && maxContextChars !== 0;
-  const sessionStartMode = getSessionStartMode(fs.readFileSync(0, 'utf8'));
 
   // Ensure directories exist
   ensureDir(sessionsDir);
@@ -554,59 +532,50 @@ async function main() {
       additionalContextParts.push(instinctSummary);
     }
 
-    if (sessionStartMode && sessionStartMode !== 'startup') {
-      const reason = sessionStartMode === SESSION_START_MODE_INVALID
-        ? 'invalid stdin payload'
-        : sessionStartMode === SESSION_START_MODE_SKIP
-          ? 'unrecognized SessionStart payload'
-          : `non-startup SessionStart mode: ${sessionStartMode}`;
-      log(`[SessionStart] Skipping previous session summary injection for ${reason}`);
-    } else {
-      // Check for recent session files (last 7 days)
-      const recentSessions = dedupeRecentSessions(sessionSearchDirs);
+    // Check for recent session files (last 7 days)
+    const recentSessions = dedupeRecentSessions(sessionSearchDirs);
 
-      if (recentSessions.length > 0) {
-        log(`[SessionStart] Found ${recentSessions.length} recent session(s)`);
+    if (recentSessions.length > 0) {
+      log(`[SessionStart] Found ${recentSessions.length} recent session(s)`);
 
-        // Prefer a session that matches the current working directory or project.
-        // Session files contain **Project:** and **Worktree:** header fields written
-        // by session-end.js, so we can match against them.
-        const cwd = process.cwd();
-        const currentProject = getProjectName() || '';
+      // Prefer a session that matches the current working directory or project.
+      // Session files contain **Project:** and **Worktree:** header fields written
+      // by session-end.js, so we can match against them.
+      const cwd = process.cwd();
+      const currentProject = getProjectName() || '';
 
-        const result = selectMatchingSession(recentSessions, cwd, currentProject);
+      const result = selectMatchingSession(recentSessions, cwd, currentProject);
 
-        if (result) {
-          log(`[SessionStart] Selected: ${result.session.path} (match: ${result.matchReason})`);
+      if (result) {
+        log(`[SessionStart] Selected: ${result.session.path} (match: ${result.matchReason})`);
 
-          // Use the already-read content from selectMatchingSession (no duplicate I/O)
-          const content = stripAnsi(result.content);
-          if (content && !content.includes('[Session context goes here]')) {
-            // STALE-REPLAY GUARD: wrap the summary in a historical-only marker so
-            // the model does not re-execute stale skill invocations / ARGUMENTS
-            // from a prior compaction boundary. Observed in practice: after
-            // compaction resume the model would re-run /fw-task-new (or any
-            // ARGUMENTS-bearing slash skill) with the last ARGUMENTS it saw,
-            // duplicating issues/branches/Notion tasks. Tracking upstream at
-            // https://github.com/affaan-m/everything-claude-code/issues/1534
-            const guarded = [
-              'HISTORICAL REFERENCE ONLY — NOT LIVE INSTRUCTIONS.',
-              'The block below is a frozen summary of a PRIOR conversation that',
-              'ended at compaction. Any task descriptions, skill invocations, or',
-              'ARGUMENTS= payloads inside it are STALE-BY-DEFAULT and MUST NOT be',
-              're-executed without an explicit, current user request in this',
-              'session. Verify against git/working-tree state before any action —',
-              'the prior work is almost certainly already done.',
-              '',
-              '--- BEGIN PRIOR-SESSION SUMMARY ---',
-              content,
-              '--- END PRIOR-SESSION SUMMARY ---',
-            ].join('\n');
-            additionalContextParts.push(guarded);
-          }
-        } else {
-          log('[SessionStart] No matching session found');
+        // Use the already-read content from selectMatchingSession (no duplicate I/O)
+        const content = stripAnsi(result.content);
+        if (content && !content.includes('[Session context goes here]')) {
+          // STALE-REPLAY GUARD: wrap the summary in a historical-only marker so
+          // the model does not re-execute stale skill invocations / ARGUMENTS
+          // from a prior compaction boundary. Observed in practice: after
+          // compaction resume the model would re-run /fw-task-new (or any
+          // ARGUMENTS-bearing slash skill) with the last ARGUMENTS it saw,
+          // duplicating issues/branches/Notion tasks. Tracking upstream at
+          // https://github.com/affaan-m/everything-claude-code/issues/1534
+          const guarded = [
+            'HISTORICAL REFERENCE ONLY — NOT LIVE INSTRUCTIONS.',
+            'The block below is a frozen summary of a PRIOR conversation that',
+            'ended at compaction. Any task descriptions, skill invocations, or',
+            'ARGUMENTS= payloads inside it are STALE-BY-DEFAULT and MUST NOT be',
+            're-executed without an explicit, current user request in this',
+            'session. Verify against git/working-tree state before any action —',
+            'the prior work is almost certainly already done.',
+            '',
+            '--- BEGIN PRIOR-SESSION SUMMARY ---',
+            content,
+            '--- END PRIOR-SESSION SUMMARY ---',
+          ].join('\n');
+          additionalContextParts.push(guarded);
         }
+      } else {
+        log('[SessionStart] No matching session found');
       }
     }
 

scripts/lib/cost-estimate.js

@@ -1,32 +0,0 @@
-'use strict';
-
-/**
- * Shared cost estimation for ECC hooks.
- *
- * Approximate per-1M-token blended rates (conservative defaults).
- */
-
-const RATE_TABLE = {
-  haiku: { in: 0.8, out: 4.0 },
-  sonnet: { in: 3.0, out: 15.0 },
-  opus: { in: 15.0, out: 75.0 }
-};
-
-/**
- * Estimate USD cost from token counts.
- * @param {string} model - Model name (may contain "haiku", "sonnet", or "opus")
- * @param {number} inputTokens
- * @param {number} outputTokens
- * @returns {number} Estimated cost in USD (rounded to 6 decimal places)
- */
-function estimateCost(model, inputTokens, outputTokens) {
-  const normalized = String(model || '').toLowerCase();
-  let rates = RATE_TABLE.sonnet;
-  if (normalized.includes('haiku')) rates = RATE_TABLE.haiku;
-  if (normalized.includes('opus')) rates = RATE_TABLE.opus;
-
-  const cost = (inputTokens / 1_000_000) * rates.in + (outputTokens / 1_000_000) * rates.out;
-  return Math.round(cost * 1e6) / 1e6;
-}
-
-module.exports = { estimateCost, RATE_TABLE };

scripts/lib/install-manifests.js

@@ -40,11 +40,8 @@ const LEGACY_LANGUAGE_ALIAS_TO_CANONICAL = Object.freeze({
   c: 'c',
   cpp: 'cpp',
   csharp: 'csharp',
-  fsharp: 'fsharp',
   go: 'go',
   golang: 'go',
-  arkts: 'arkts',
-  harmonyos: 'arkts',
   java: 'java',
   javascript: 'typescript',
   kotlin: 'java',
@@ -59,9 +56,7 @@ const LEGACY_LANGUAGE_EXTRA_MODULE_IDS = Object.freeze({
   c: ['framework-language'],
   cpp: ['framework-language'],
   csharp: ['framework-language'],
-  fsharp: ['framework-language'],
   go: ['framework-language'],
-  arkts: ['framework-language'],
   java: ['framework-language'],
   perl: [],
   php: [],

scripts/lib/project-detect.js

@@ -60,11 +60,6 @@ const LANGUAGE_RULES = [
     markers: [],
     extensions: ['.cs', '.csproj', '.sln']
   },
-  {
-    type: 'fsharp',
-    markers: [],
-    extensions: ['.fs', '.fsx', '.fsproj']
-  },
   {
     type: 'swift',
     markers: ['Package.swift'],

scripts/lib/session-bridge.js

@@ -1,81 +0,0 @@
-'use strict';
-
-/**
- * Shared session bridge utilities for ECC hooks.
- *
- * The bridge file is a small JSON aggregate in /tmp that allows
- * statusline, metrics-bridge, and context-monitor to share state
- * without scanning large JSONL logs on every invocation.
- */
-
-const fs = require('fs');
-const os = require('os');
-const path = require('path');
-
-const MAX_SESSION_ID_LENGTH = 64;
-
-/**
- * Sanitize a session ID for safe use in file paths.
- * Rejects path traversal, strips unsafe chars, limits length.
- * @param {string} raw
- * @returns {string|null} Safe session ID or null if invalid
- */
-function sanitizeSessionId(raw) {
-  if (!raw || typeof raw !== 'string') return null;
-  if (/[/\\]|\.\./.test(raw)) return null;
-  const safe = raw.replace(/[^a-zA-Z0-9_-]/g, '_').slice(0, MAX_SESSION_ID_LENGTH);
-  return safe || null;
-}
-
-/**
- * Get the bridge file path for a session.
- * @param {string} sessionId - Already-sanitized session ID
- * @returns {string}
- */
-function getBridgePath(sessionId) {
-  return path.join(os.tmpdir(), `ecc-metrics-${sessionId}.json`);
-}
-
-/**
- * Read bridge data. Returns null on any error.
- * @param {string} sessionId - Already-sanitized session ID
- * @returns {object|null}
- */
-function readBridge(sessionId) {
-  try {
-    const raw = fs.readFileSync(getBridgePath(sessionId), 'utf8');
-    return JSON.parse(raw);
-  } catch {
-    return null;
-  }
-}
-
-/**
- * Write bridge data atomically (write .tmp then rename).
- * @param {string} sessionId - Already-sanitized session ID
- * @param {object} data
- */
-function writeBridgeAtomic(sessionId, data) {
-  const target = getBridgePath(sessionId);
-  const tmp = `${target}.tmp`;
-  fs.writeFileSync(tmp, JSON.stringify(data), 'utf8');
-  fs.renameSync(tmp, target);
-}
-
-/**
- * Resolve session ID from environment variables.
- * @returns {string|null} Sanitized session ID or null
- */
-function resolveSessionId() {
-  const raw = process.env.ECC_SESSION_ID || process.env.CLAUDE_SESSION_ID || '';
-  return sanitizeSessionId(raw);
-}
-
-module.exports = {
-  sanitizeSessionId,
-  getBridgePath,
-  readBridge,
-  writeBridgeAtomic,
-  resolveSessionId,
-  MAX_SESSION_ID_LENGTH
-};

scripts/observability-readiness.js

@@ -1,309 +0,0 @@
-#!/usr/bin/env node
-'use strict';
-
-const fs = require('fs');
-const path = require('path');
-
-const RUBRIC_VERSION = '2026-05-11';
-
-function usage() {
-  console.log([
-    'Usage: node scripts/observability-readiness.js [--format <text|json>] [--root <dir>]',
-    '',
-    'Deterministic ECC 2.0 observability readiness gate.',
-    '',
-    'Options:',
-    '  --format <text|json>  Output format (default: text)',
-    '  --root <dir>          Repository root to inspect (default: cwd)',
-    '  --help, -h            Show this help'
-  ].join('\n'));
-}
-
-function readValue(args, index, flagName) {
-  const value = args[index + 1];
-  if (!value || value.startsWith('--')) {
-    throw new Error(`${flagName} requires a value`);
-  }
-  return value;
-}
-
-function parseArgs(argv) {
-  const args = argv.slice(2);
-  const parsed = {
-    format: 'text',
-    help: false,
-    root: path.resolve(process.cwd())
-  };
-
-  for (let index = 0; index < args.length; index += 1) {
-    const arg = args[index];
-
-    if (arg === '--help' || arg === '-h') {
-      parsed.help = true;
-      continue;
-    }
-
-    if (arg === '--format') {
-      parsed.format = readValue(args, index, arg).toLowerCase();
-      index += 1;
-      continue;
-    }
-
-    if (arg.startsWith('--format=')) {
-      parsed.format = arg.slice('--format='.length).toLowerCase();
-      continue;
-    }
-
-    if (arg === '--root') {
-      parsed.root = path.resolve(readValue(args, index, arg));
-      index += 1;
-      continue;
-    }
-
-    if (arg.startsWith('--root=')) {
-      parsed.root = path.resolve(arg.slice('--root='.length));
-      continue;
-    }
-
-    throw new Error(`Unknown argument: ${arg}`);
-  }
-
-  if (!['text', 'json'].includes(parsed.format)) {
-    throw new Error(`Invalid format: ${parsed.format}. Use text or json.`);
-  }
-
-  return parsed;
-}
-
-function fileExists(rootDir, relativePath) {
-  return fs.existsSync(path.join(rootDir, relativePath));
-}
-
-function readText(rootDir, relativePath) {
-  try {
-    return fs.readFileSync(path.join(rootDir, relativePath), 'utf8');
-  } catch (_error) {
-    return '';
-  }
-}
-
-function safeParseJson(text) {
-  if (!text || !text.trim()) {
-    return null;
-  }
-
-  try {
-    return JSON.parse(text);
-  } catch (_error) {
-    return null;
-  }
-}
-
-function includesAll(text, needles) {
-  return needles.every(needle => text.includes(needle));
-}
-
-function buildChecks(rootDir) {
-  const packageJsonText = readText(rootDir, 'package.json');
-  const packageJson = safeParseJson(packageJsonText) || {};
-  const packageFiles = Array.isArray(packageJson.files) ? packageJson.files : [];
-  const packageScripts = packageJson.scripts || {};
-  const loopStatus = readText(rootDir, 'scripts/loop-status.js');
-  const sessionInspect = readText(rootDir, 'scripts/session-inspect.js');
-  const harnessAudit = readText(rootDir, 'scripts/harness-audit.js');
-  const activityTracker = readText(rootDir, 'scripts/hooks/session-activity-tracker.js');
-  const observabilityRust = readText(rootDir, 'ecc2/src/observability/mod.rs');
-  const sessionStoreRust = readText(rootDir, 'ecc2/src/session/store.rs');
-  const sessionManagerRust = readText(rootDir, 'ecc2/src/session/manager.rs');
-  const readinessDoc = readText(rootDir, 'docs/architecture/observability-readiness.md');
-  const quickstart = readText(rootDir, 'docs/releases/2.0.0-rc.1/quickstart.md');
-  const releaseNotes = readText(rootDir, 'docs/releases/2.0.0-rc.1/release-notes.md');
-
-  return [
-    {
-      id: 'loop-status-live-signal',
-      category: 'Live Status',
-      points: 2,
-      path: 'scripts/loop-status.js',
-      description: 'Loop status supports JSON output, watch mode, and snapshot writes',
-      pass: fileExists(rootDir, 'scripts/loop-status.js')
-        && includesAll(loopStatus, ['--json', '--watch', '--write-dir']),
-      fix: 'Restore loop-status JSON/watch/write-dir support.'
-    },
-    {
-      id: 'session-inspect-adapter-registry',
-      category: 'Session Trace',
-      points: 2,
-      path: 'scripts/session-inspect.js',
-      description: 'Session inspection exposes registered adapters and writable snapshots',
-      pass: fileExists(rootDir, 'scripts/session-inspect.js')
-        && fileExists(rootDir, 'scripts/lib/session-adapters/registry.js')
-        && includesAll(sessionInspect, ['--list-adapters', '--write', 'inspectSessionTarget']),
-      fix: 'Restore session-inspect adapter registry, list-adapters, and write support.'
-    },
-    {
-      id: 'harness-audit-scorecard',
-      category: 'Harness Baseline',
-      points: 2,
-      path: 'scripts/harness-audit.js',
-      description: 'Harness audit emits deterministic text/JSON scorecards',
-      pass: fileExists(rootDir, 'scripts/harness-audit.js')
-        && packageScripts['harness:audit'] === 'node scripts/harness-audit.js'
-        && includesAll(harnessAudit, ['Deterministic harness audit', '--format', 'overall_score']),
-      fix: 'Restore the harness:audit package script and deterministic scorecard output.'
-    },
-    {
-      id: 'hook-activity-jsonl',
-      category: 'Tool Activity',
-      points: 2,
-      path: 'scripts/hooks/session-activity-tracker.js',
-      description: 'Hook activity tracker writes tool usage JSONL for later sync',
-      pass: fileExists(rootDir, 'scripts/hooks/session-activity-tracker.js')
-        && includesAll(activityTracker, ['tool-usage.jsonl', 'session_id', 'tool_name']),
-      fix: 'Restore hook-side tool activity recording to metrics/tool-usage.jsonl.'
-    },
-    {
-      id: 'ecc2-tool-risk-ledger',
-      category: 'Tool Activity',
-      points: 3,
-      path: 'ecc2/src/observability/mod.rs',
-      description: 'ECC2 records tool calls with risk scoring and paginated queries',
-      pass: fileExists(rootDir, 'ecc2/src/observability/mod.rs')
-        && includesAll(observabilityRust, ['ToolCallEvent', 'RiskAssessment', 'ToolLogger'])
-        && includesAll(sessionStoreRust, ['insert_tool_log', 'query_tool_logs'])
-        && includesAll(sessionManagerRust, ['sync_tool_activity_metrics', 'tool-usage.jsonl']),
-      fix: 'Restore ECC2 tool logging, risk scoring, store queries, and metrics sync.'
-    },
-    {
-      id: 'release-observability-onramp',
-      category: 'Operator Onramp',
-      points: 2,
-      path: 'docs/architecture/observability-readiness.md',
-      description: 'Release docs explain the local observability readiness workflow',
-      pass: readinessDoc.includes('node scripts/observability-readiness.js --format json')
-        && quickstart.includes('observability-readiness.md')
-        && releaseNotes.includes('observability-readiness.md'),
-      fix: 'Add the observability readiness doc and link it from rc.1 release docs.'
-    },
-    {
-      id: 'package-exposes-readiness-gate',
-      category: 'Packaging',
-      points: 1,
-      path: 'package.json',
-      description: 'Package exposes the observability readiness gate',
-      pass: packageScripts['observability:ready'] === 'node scripts/observability-readiness.js'
-        && packageFiles.includes('scripts/observability-readiness.js'),
-      fix: 'Add scripts/observability-readiness.js to package files and observability:ready.'
-    }
-  ];
-}
-
-function buildReport(rootDir) {
-  const checks = buildChecks(rootDir);
-  const categories = {};
-
-  for (const check of checks) {
-    if (!categories[check.category]) {
-      categories[check.category] = {
-        score: 0,
-        max_score: 0,
-        passed: 0,
-        total: 0
-      };
-    }
-
-    categories[check.category].max_score += check.points;
-    categories[check.category].total += 1;
-
-    if (check.pass) {
-      categories[check.category].score += check.points;
-      categories[check.category].passed += 1;
-    }
-  }
-
-  const overallScore = checks
-    .filter(check => check.pass)
-    .reduce((sum, check) => sum + check.points, 0);
-  const maxScore = checks.reduce((sum, check) => sum + check.points, 0);
-  const failingChecks = checks.filter(check => !check.pass);
-
-  return {
-    schema_version: 'ecc.observability-readiness.v1',
-    rubric_version: RUBRIC_VERSION,
-    deterministic: true,
-    root_dir: fs.realpathSync(rootDir),
-    overall_score: overallScore,
-    max_score: maxScore,
-    ready: overallScore === maxScore,
-    categories,
-    checks,
-    top_actions: failingChecks
-      .sort((left, right) => right.points - left.points || left.id.localeCompare(right.id))
-      .slice(0, 3)
-      .map(check => ({
-        id: check.id,
-        path: check.path,
-        fix: check.fix
-      }))
-  };
-}
-
-function renderText(report) {
-  const lines = [
-    `Observability Readiness: ${report.overall_score}/${report.max_score}`,
-    `Ready: ${report.ready ? 'yes' : 'no'}`,
-    '',
-    'Categories:'
-  ];
-
-  for (const [name, category] of Object.entries(report.categories)) {
-    lines.push(`- ${name}: ${category.score}/${category.max_score} (${category.passed}/${category.total})`);
-  }
-
-  lines.push('', 'Checks:');
-  for (const check of report.checks) {
-    lines.push(`- ${check.pass ? 'PASS' : 'FAIL'} ${check.id}: ${check.description}`);
-  }
-
-  if (report.top_actions.length > 0) {
-    lines.push('', 'Top Actions:');
-    for (const action of report.top_actions) {
-      lines.push(`- ${action.path}: ${action.fix}`);
-    }
-  }
-
-  return `${lines.join('\n')}\n`;
-}
-
-function main() {
-  const args = parseArgs(process.argv);
-
-  if (args.help) {
-    usage();
-    return;
-  }
-
-  const report = buildReport(args.root);
-
-  if (args.format === 'json') {
-    console.log(JSON.stringify(report, null, 2));
-  } else {
-    process.stdout.write(renderText(report));
-  }
-}
-
-if (require.main === module) {
-  try {
-    main();
-  } catch (error) {
-    console.error(`Error: ${error.message}`);
-    process.exit(1);
-  }
-}
-
-module.exports = {
-  buildChecks,
-  buildReport,
-  parseArgs,
-  renderText
-};

skills/agent-architecture-audit/SKILL.md

@@ -1,256 +0,0 @@
----
-name: agent-architecture-audit
-description: Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
-origin: oh-my-agent-check
-tools: Read, Write, Edit, Bash, Grep, Glob
----
-
-# Agent Architecture Audit
-
-A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations.
-
-## When to Activate
-
-**MANDATORY for:**
-- Releasing any agent or LLM-powered application to production
-- Shipping features with tool calling, memory, or multi-step workflows
-- Agent behavior degrades after adding wrapper layers
-- User reports "the agent is getting worse" or "tools are flaky"
-- Same model works in playground but breaks inside your wrapper
-- Debugging agent behavior for more than 15 minutes without finding root cause
-
-**Especially critical when:**
-- You've added new prompt layers, tool definitions, or memory systems
-- Different agents in your system behave inconsistently
-- The model was fine yesterday but is hallucinating today
-- You suspect hidden repair/retry loops silently mutating responses
-
-**Do not use for:**
-- General code debugging — use `agent-introspection-debugging`
-- Code review — use language-specific reviewer agents
-- Security scanning — use `security-review` or `security-review/scan`
-- Agent performance benchmarking — use `agent-eval`
-- Writing new features — use the appropriate workflow skill
-
-## The 12-Layer Stack
-
-Every agent system has these layers. Any of them can corrupt the answer:
-
-| # | Layer | What Goes Wrong |
-|---|-------|----------------|
-| 1 | System prompt | Conflicting instructions, instruction bloat |
-| 2 | Session history | Stale context injection from previous turns |
-| 3 | Long-term memory | Pollution across sessions, old topics in new conversations |
-| 4 | Distillation | Compressed artifacts re-entering as pseudo-facts |
-| 5 | Active recall | Redundant re-summary layers wasting context |
-| 6 | Tool selection | Wrong tool routing, model skips required tools |
-| 7 | Tool execution | Hallucinated execution — claims to call but doesn't |
-| 8 | Tool interpretation | Misread or ignored tool output |
-| 9 | Answer shaping | Format corruption in final response |
-| 10 | Platform rendering | Transport-layer mutation (UI, API, CLI mutates valid answers) |
-| 11 | Hidden repair loops | Silent fallback/retry agents running second LLM pass |
-| 12 | Persistence | Expired state or cached artifacts reused as live evidence |
-
-## Common Failure Patterns
-
-### 1. Wrapper Regression
-
-The base model produces correct answers, but the wrapper layers make it worse.
-
-**Symptoms:**
-- Model works fine in playground or direct API call, breaks in your agent
-- Added a new prompt layer, existing behavior degraded
-- Agent sounds confident but is confidently wrong
-- "It was working before the last update"
-
-### 2. Memory Contamination
-
-Old topics leak into new conversations through history, memory retrieval, or distillation.
-
-**Symptoms:**
-- Agent brings up unrelated past topics
-- User corrections don't stick (old memory overwrites new)
-- Same-session artifacts re-enter as pseudo-facts
-- Memory grows without bound, degrading response quality over time
-
-### 3. Tool Discipline Failure
-
-Tools are declared in the prompt but not enforced in code. The model skips them or hallucinates execution.
-
-**Symptoms:**
-- "Must use tool X" in prompt, but model answers without calling it
-- Tool results look correct but were never actually executed
-- Different tools fight over the same responsibility
-- Model uses tool when it shouldn't, or skips it when it must
-
-### 4. Rendering/Transport Corruption
-
-The agent's internal answer is correct, but the platform layer mutates it during delivery.
-
-**Symptoms:**
-- Logs show correct answer, user sees broken output
-- Markdown rendering, JSON parsing, or streaming fragments corrupt valid responses
-- Hidden fallback agent quietly replaces the answer before delivery
-- Output differs between terminal and UI
-
-### 5. Hidden Agent Layers
-
-Silent repair, retry, summarization, or recall agents run without explicit contracts.
-
-**Symptoms:**
-- Output changes between internal generation and user delivery
-- "Auto-fix" loops run a second LLM pass the user doesn't know about
-- Multiple agents modify the same output without coordination
-- Answers get "smoothed" or "corrected" by invisible layers
-
-## Audit Workflow
-
-### Phase 1: Scope
-
-Define what you're auditing:
-
-- **Target system** — what agent application?
-- **Entrypoints** — how do users interact with it?
-- **Model stack** — which LLM(s) and providers?
-- **Symptoms** — what does the user report?
-- **Time window** — when did it start?
-- **Layers to audit** — which of the 12 layers apply?
-
-### Phase 2: Evidence Collection
-
-Gather evidence from the codebase:
-
-- **Source code** — agent loop, tool router, memory admission, prompt assembly
-- **Logs** — historical session traces, tool call records
-- **Config** — prompt templates, tool schemas, provider settings
-- **Memory files** — SOPs, knowledge bases, session archives
-
-Use `rg` to search for anti-patterns:
-
-```bash
-# Tool requirements expressed only in prompt text (not code)
-rg "must.*tool|必须.*工具|required.*call" --type md
-
-# Tool execution without validation
-rg "tool_call|toolCall|tool_use" --type py --type ts
-
-# Hidden LLM calls outside main agent loop
-rg "completion|chat\.create|messages\.create|llm\.invoke"
-
-# Memory admission without user-correction priority
-rg "memory.*admit|long.*term.*update|persist.*memory" --type py --type ts
-
-# Fallback loops that run additional LLM calls
-rg "fallback|retry.*llm|repair.*prompt|re-?prompt" --type py --type ts
-
-# Silent output mutation
-rg "mutate|rewrite.*response|transform.*output|shap" --type py --type ts
-```
-
-### Phase 3: Failure Mapping
-
-For each finding, document:
-
-- **Symptom** — what the user sees
-- **Mechanism** — how the wrapper causes it
-- **Source layer** — which of the 12 layers
-- **Root cause** — the deepest cause
-- **Evidence** — file:line or log:row reference
-- **Confidence** — 0.0 to 1.0
-
-### Phase 4: Fix Strategy
-
-Default fix order (code-first, not prompt-first):
-
-1. **Code-gate tool requirements** — enforce in code, not just prompt text
-2. **Remove or narrow hidden repair agents** — make fallback explicit with contracts
-3. **Reduce context duplication** — same info through prompt + history + memory + distillation
-4. **Tighten memory admission** — user corrections > agent assertions
-5. **Tighten distillation triggers** — don't compress what shouldn't be compressed
-6. **Reduce rendering mutation** — pass-through, don't transform
-7. **Convert to typed JSON envelopes** — structured internal flow, not freeform prose
-
-## Severity Model
-
-| Level | Meaning | Action |
-|-------|---------|--------|
-| `critical` | Agent can confidently produce wrong operational behavior | Fix before next release |
-| `high` | Agent frequently degrades correctness or stability | Fix this sprint |
-| `medium` | Correctness usually survives but output is fragile or wasteful | Plan for next cycle |
-| `low` | Mostly cosmetic or maintainability issues | Backlog |
-
-## Output Format
-
-Present findings to the user in this order:
-
-1. **Severity-ranked findings** (most critical first)
-2. **Architecture diagnosis** (which layer corrupted what, and why)
-3. **Ordered fix plan** (code-first, not prompt-first)
-
-Do not lead with compliments or summaries. If the system is broken, say so directly.
-
-## Quick Diagnostic Questions
-
-When auditing an agent system, answer these:
-
-| # | Question | If Yes → |
-|---|----------|----------|
-| 1 | Can the model skip a required tool and still answer? | Tool not code-gated |
-| 2 | Does old conversation content appear in new turns? | Memory contamination |
-| 3 | Is the same info in system prompt AND memory AND history? | Context duplication |
-| 4 | Does the platform run a second LLM pass before delivery? | Hidden repair loop |
-| 5 | Does the output differ between internal generation and user delivery? | Rendering corruption |
-| 6 | Are "must use tool X" rules only in prompt text? | Tool discipline failure |
-| 7 | Can the agent's own monologue become persistent memory? | Memory poisoning |
-
-## Anti-Patterns to Avoid
-
-- Avoid blaming the model before falsifying wrapper-layer regressions.
-- Avoid blaming memory without showing the contamination path.
-- Do not let a clean current state erase a dirty historical incident.
-- Do not treat markdown prose as a trustworthy internal protocol.
-- Do not accept "must use tool" in prompt text when code never enforces it.
-- Keep findings direct, evidence-backed, and severity-ranked.
-
-## Report Schema
-
-Audits should produce structured reports following this shape:
-
-```json
-{
-  "schema_version": "ecc.agent-architecture-audit.report.v1",
-  "executive_verdict": {
-    "overall_health": "high_risk",
-    "primary_failure_mode": "string",
-    "most_urgent_fix": "string"
-  },
-  "scope": {
-    "target_name": "string",
-    "model_stack": ["string"],
-    "layers_to_audit": ["string"]
-  },
-  "findings": [
-    {
-      "severity": "critical|high|medium|low",
-      "title": "string",
-      "mechanism": "string",
-      "source_layer": "string",
-      "root_cause": "string",
-      "evidence_refs": ["file:line"],
-      "confidence": 0.0,
-      "recommended_fix": "string"
-    }
-  ],
-  "ordered_fix_plan": [
-    { "order": 1, "goal": "string", "why_now": "string", "expected_effect": "string" }
-  ]
-}
-```
-
-## Related Skills
-
-- `agent-introspection-debugging` — Debug agent runtime failures (loops, timeouts, state errors)
-- `agent-eval` — Benchmark agent performance head-to-head
-- `security-review` — Security audit for code and configuration
-- `autonomous-agent-harness` — Set up autonomous agent operations
-- `agent-harness-construction` — Build agent harnesses from scratch

skills/agent-payment-x402/SKILL.md

@@ -1,40 +1,21 @@
 ---
 name: agent-payment-x402
-description: Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.
+description: Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.
 origin: community
 ---
 
 # Agent Payment Execution (x402)
 
-Enable AI agents to make policy-gated payments with built-in spending controls. Uses the x402 HTTP payment protocol and MCP tools so agents can pay for external services, APIs, or other agents without custodial risk.
+Enable AI agents to make autonomous payments with built-in spending controls. Uses the x402 HTTP payment protocol and MCP tools so agents can pay for external services, APIs, or other agents without custodial risk.
 
 ## When to Use
 
 Use when: your agent needs to pay for an API call, purchase a service, settle with another agent, enforce per-task spending limits, or manage a non-custodial wallet. Pairs naturally with cost-aware-llm-pipeline and security-review skills.
 
-## Decision Tree
-
-Choose the integration path based on whether your agent is buying access to a paid API or charging others for one:
-
-| Need | Recommended path |
-|------|------------------|
-| Agent pays a 402-gated API on Base or another agentwallet-supported chain | Use `agentwallet-sdk` as an MCP payment server with strict spending policy |
-| Agent pays a 402-gated API on X Layer | Use OKX Agent Payments Protocol from `okx/onchainos-skills`; `okx-x402-payment` is a deprecated legacy alias |
-| TypeScript API charges agents | Use OKX Payments TypeScript seller SDK docs for Express, Hono, Fastify, or Next.js |
-| Go API charges agents | Use OKX Payments Go seller SDK docs for Gin, Echo, or `net/http` |
-| Rust API charges agents | Use OKX Payments Rust seller SDK docs for Axum |
-| Java API charges agents | Use OKX Payments Java seller SDK docs for Spring Boot 2/3, Java EE, or Jakarta |
-| Python API charges agents | Check the current OKX Payments repository before implementation; a Python seller guide may not be available |
-
-## Supported Networks
-
-- `agentwallet-sdk`: use the package docs to confirm current network coverage before production. Base Sepolia is the safest development default; Base mainnet is the production path called out by the original skill.
-- OKX Payments / X Layer: current seller docs target X Layer (`eip155:196`) and USDT0 settlement. Fetch current SDK docs before generating production code because payment packages and facilitator behavior can change quickly.
-
 ## How It Works
 
 ### x402 Protocol
-x402 extends HTTP 402 (Payment Required) into a machine-negotiable flow. When a server returns `402`, the agent's payment tool negotiates price, checks budget, signs a transaction, and retries only inside the policy and confirmation boundary set by the orchestrator.
+x402 extends HTTP 402 (Payment Required) into a machine-negotiable flow. When a server returns `402`, the agent's payment tool automatically negotiates price, checks budget, signs a transaction, and retries — no human in the loop.
 
 ### Spending Controls
 Every payment tool call enforces a `SpendingPolicy`:
@@ -52,8 +33,6 @@ The payment layer exposes standard MCP tools that slot into any Claude Code or a
 
 > **Security note**: Always pin the package version. This tool manages private keys — unpinned `npx` installs introduce supply-chain risk.
 
-### Option A: agentwallet-sdk (Base / multi-chain)
-
 ```json
 {
   "mcpServers": {
@@ -76,28 +55,6 @@ The payment layer exposes standard MCP tools that slot into any Claude Code or a
 
 > **Note**: Spending policy is set by the **orchestrator** before delegating to the agent — not by the agent itself. This prevents agents from escalating their own spending limits. Configure policy via `set_policy` in your orchestration layer or pre-task hook, never as an agent-callable tool.
 
-### Option B: OKX Agent Payments Protocol (X Layer)
-
-Use this path for X Layer x402, Multi-Party Payment (MPP), session payment, charge, and A2A charge flows.
-
-For buyer-side agent flows:
-
-1. Install or reference the current `okx/onchainos-skills` repository.
-2. Use `skills/okx-agent-payments-protocol/SKILL.md` as the dispatcher.
-3. Treat `skills/okx-x402-payment/SKILL.md` as a deprecated compatibility alias, not as the canonical skill.
-4. Require explicit user confirmation before wallet status checks or payment actions. Do not hide payment execution behind a generic tool call.
-
-For seller-side API flows, fetch the latest language-specific guide before generating code:
-
-| Runtime | Current guide |
-|---------|---------------|
-| TypeScript | `https://raw.githubusercontent.com/okx/payments/main/typescript/SELLER.md` |
-| Go | `https://raw.githubusercontent.com/okx/payments/main/go/x402/SELLER.md` |
-| Rust | `https://raw.githubusercontent.com/okx/payments/main/rust/x402/SELLER.md` |
-| Java | `https://raw.githubusercontent.com/okx/payments/main/java/SELLER.md` |
-
-Do not copy examples from older docs without checking the current OKX repository. Current OKX guidance uses `okx-agent-payments-protocol` as the dispatcher, and Java seller docs are now available.
-
 ## Examples
 
 ### Budget enforcement in an MCP client
@@ -219,6 +176,3 @@ main().catch((err) => {
 - **npm**: [`agentwallet-sdk`](https://www.npmjs.com/package/agentwallet-sdk)
 - **Merged into NVIDIA NeMo Agent Toolkit**: [PR #17](https://github.com/NVIDIA/NeMo-Agent-Toolkit-Examples/pull/17) — x402 payment tool for NVIDIA's agent examples
 - **Protocol spec**: [x402.org](https://x402.org)
-- **OKX Payments SDKs**: [`okx/payments`](https://github.com/okx/payments) — TypeScript, Go, Rust, and Java seller integrations for X Layer x402
-- **OKX Agent Payments Protocol skill**: [`okx/onchainos-skills`](https://github.com/okx/onchainos-skills/tree/main/skills/okx-agent-payments-protocol)
-- **OKX Payments overview**: [web3.okx.com/onchainos/dev-docs/payments/overview](https://web3.okx.com/onchainos/dev-docs/payments/overview)

skills/agentic-os/SKILL.md

@@ -1,387 +0,0 @@
----
-name: agentic-os
-description: Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
-origin: ECC
----
-
-# Agentic OS
-
-Treat Claude Code as a persistent runtime / operating system rather than a chat session. This skill codifies the architecture used by production agentic setups: a kernel config that routes tasks to specialist agents, persistent file-based memory, scheduled automation, and a JSON/markdown data layer.
-
-## When to Activate
-
-- Building a multi-agent workflow inside Claude Code
-- Setting up persistent Claude Code automation that survives session restarts
-- Creating a "personal OS" or "agentic OS" for recurring tasks
-- User says "agentic OS", "personal OS", "multi-agent", "agent coordinator", "persistent agent"
-- Structuring long-running projects where context must survive across sessions
-
-## Architecture Overview
-
-The Agentic OS has four layers. Each layer is a directory in your project root.
-
-```
-project-root/
-├── CLAUDE.md          # Kernel: identity, routing rules, agent registry
-├── agents/            # Specialist agent definitions (markdown prompts)
-├── .claude/commands/  # Slash commands: user-facing CLI
-├── scripts/           # Daemon scripts: scheduled or event-driven tasks
-└── data/              # State: JSON/markdown filesystem, no external DB
-```
-
-### Layer Responsibilities
-
-| Layer | Purpose | Persistence |
-|---|---|---|
-| Kernel (`CLAUDE.md`) | Identity, routing, model policies, agent registry | Git-tracked |
-| Agents (`agents/`) | Specialist identities with scoped tools and memory | Git-tracked |
-| Commands (`.claude/commands/`) | User-facing slash commands (`/daily-sync`, `/outreach`) | Git-tracked |
-| Scripts (`scripts/`) | Python/JS daemons triggered by cron or webhooks | Git-tracked |
-| State (`data/`) | Append-only logs, project state, decision records | Git-ignored or tracked |
-
-## The Kernel
-
-`CLAUDE.md` is the kernel. It acts as the COO / orchestrator. Claude reads it at session start and uses it to route work.
-
-### Kernel Structure
-
-```markdown
-# CLAUDE.md - Agentic OS Kernel
-
-## Identity
-You are the COO of [project-name]. You route tasks to specialist agents.
-You never write code directly. You delegate to the right agent and synthesize results.
-
-## Agent Registry
-
-| Agent | Role | Trigger |
-|---|---|---|
-| @dev | Code, architecture, debugging | User says "build", "fix", "refactor" |
-| @writer | Documentation, content, emails | User says "write", "draft", "blog" |
-| @researcher | Research, analysis, fact-checking | User says "research", "analyze", "compare" |
-| @ops | DevOps, deployment, infrastructure | User says "deploy", "CI", "server" |
-
-## Routing Rules
-1. Parse the user request for intent keywords
-2. Match to the Agent Registry trigger column
-3. Load the corresponding agent file from `agents/<name>.md`
-4. Hand off execution with full context
-5. Synthesize and present the result back to the user
-
-## Model Policies
-- Default model: use the repository or harness default.
-- @dev tasks: prefer a higher-reasoning model for complex architecture.
-- @researcher tasks: use the configured research-capable model and approved search tools.
-- Cost ceiling: warn before exceeding the project's configured spend threshold.
-```
-
-### Key Principle
-
-The kernel should be **small and declarative**. Routing logic lives in plain markdown tables, not code. This makes the system inspectable and editable without debugging.
-
-## Specialist Agents
-
-Each agent is a standalone markdown file in `agents/`. Claude loads the relevant agent file when routing a task.
-
-### Agent Definition Format
-
-```markdown
-# @dev - Software Engineer
-
-## Identity
-You are a senior software engineer. You write clean, tested, production-grade code.
-You prefer simple solutions. You ask clarifying questions when requirements are ambiguous.
-
-## Memory Scope
-- Read `data/projects/<current-project>.md` for context
-- Read `data/decisions/` for architectural decisions
-- Append execution logs to `data/logs/<date>-@dev.md`
-
-## Tool Access
-- Full filesystem access within project root
-- Git operations (status, diff, commit, branch)
-- Test runner access
-- MCP servers as configured in `.claude/mcp.json`
-
-## Constraints
-- Always write tests for new features
-- Never commit directly to `main`; use feature branches
-- Prefer editing existing files over creating new ones
-- Keep functions under 50 lines when possible
-```
-
-### Multi-Agent Collaboration Pattern
-
-When a task spans multiple agents, the kernel runs them sequentially or in parallel:
-
-```
-User: "Build a landing page and write the launch blog post"
-
-Kernel routing:
-1. @dev - "Build a landing page with [requirements]"
-2. @writer - "Write a launch blog post for [product] using the landing page copy"
-3. Kernel synthesizes both outputs into a unified response
-```
-
-For parallel execution, use Claude Code's background task capability or shell scripts that invoke Claude Code with specific agent contexts.
-
-## Commands and Daily Workflows
-
-Slash commands are markdown files in `.claude/commands/`. They define reusable workflows.
-
-### Command Structure
-
-```markdown
-# /daily-sync
-
-Run the morning briefing:
-
-1. Read `data/logs/last-sync.md` for context
-2. Check project status: `git status`, pending PRs, CI health
-3. Review `data/inbox/` for new tasks or decisions needed
-4. Generate a summary of blockers, priorities, and next actions
-5. Append the briefing to `data/logs/daily/<date>.md`
-```
-
-### Standard Command Set
-
-| Command | Purpose |
-|---|---|
-| `/daily-sync` | Morning briefing: status, blockers, priorities |
-| `/outreach` | Run outreach workflow (email, LinkedIn, etc.) |
-| `/research <topic>` | Deep research with citation tracking |
-| `/apply-jobs` | Tailor resume + cover letter for a target role |
-| `/analytics` | Pull metrics from Stripe, GitHub, or custom sources |
-| `/interview-prep` | Generate flashcards or mock interview questions |
-| `/decision <topic>` | Log a decision with pros/cons and chosen path |
-
-### Activating Commands
-
-Place command files in `.claude/commands/<command-name>.md`. Claude Code auto-discovers them. Users invoke them with `/<command-name>`.
-
-## Persistent Memory
-
-Memory is file-based. No vector DB, no Redis, no PostgreSQL. JSON and markdown files in `data/` are the database.
-
-### Memory Directory Structure
-
-```
-data/
-├── daily-logs/         # Append-only daily activity logs
-├── projects/           # Per-project context files
-├── decisions/          # Architectural and business decisions (ADR format)
-├── inbox/              # New tasks or ideas awaiting triage
-├── contacts/           # People, companies, relationship notes
-└── templates/          # Reusable prompts and formats
-```
-
-### Daily Log Format
-
-```markdown
-# 2026-04-22 - Daily Log
-
-## Sessions
-- 09:00 - Session 1: Refactored auth module (@dev)
-- 11:30 - Session 2: Drafted investor update (@writer)
-
-## Decisions
-- Switched from JWT to session cookies (see `data/decisions/2026-04-22-auth.md`)
-
-## Blockers
-- Waiting on API key from vendor (follow up 2026-04-24)
-
-## Next Actions
-- [ ] Merge auth refactor PR
-- [ ] Send investor update for review
-```
-
-### Auto-Reflection Pattern
-
-At the end of each session, the kernel appends a reflection:
-
-```markdown
-## Reflection - Session 3
-- What worked: Parallel agent execution saved 20 minutes
-- What didn't: @researcher hit a paywalled source, need better source ranking
-- What to change: Add `source-tier` field to research notes (A/B/C credibility)
-```
-
-This creates a feedback loop that improves the system over time without code changes.
-
-## Scheduled Automation
-
-Agentic OS tasks run on a schedule using external cron, not Claude Code's built-in cron (which dies when the session ends).
-
-### macOS: LaunchAgent
-
-```xml
-<!-- ~/Library/LaunchAgents/com.agentic.daily-sync.plist -->
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" ...>
-<plist version="1.0">
-<dict>
-    <key>Label</key>
-    <string>com.agentic.daily-sync</string>
-    <key>ProgramArguments</key>
-    <array>
-        <string>/claude</string>
-        <string>--cwd</string>
-        <string>/path/to/project</string>
-        <string>--command</string>
-        <string>/daily-sync</string>
-    </array>
-    <key>StartCalendarInterval</key>
-    <dict>
-        <key>Hour</key>
-        <integer>8</integer>
-        <key>Minute</key>
-        <integer>0</integer>
-    </dict>
-    <key>StandardOutPath</key>
-    <string>/tmp/agentic-daily-sync.log</string>
-</dict>
-</plist>
-```
-
-### Linux: systemd Timer
-
-```ini
-# ~/.config/systemd/user/agentic-daily-sync.service
-[Unit]
-Description=Agentic OS Daily Sync
-
-[Service]
-Type=oneshot
-ExecStart=/usr/local/bin/claude --cwd /path/to/project --command /daily-sync
-```
-
-```ini
-# ~/.config/systemd/user/agentic-daily-sync.timer
-[Unit]
-Description=Run daily sync every morning
-
-[Timer]
-OnCalendar=*-*-* 8:00:00
-Persistent=true
-
-[Install]
-WantedBy=timers.target
-```
-
-### Cross-Platform: pm2
-
-```bash
-# ecosystem.config.js
-module.exports = {
-  apps: [{
-    name: 'agentic-daily-sync',
-    script: 'claude',
-    args: '--cwd /path/to/project --command /daily-sync',
-    cron_restart: '0 8 * * *',
-    autorestart: false
-  }]
-};
-```
-
-## Data Layer
-
-The data layer is your filesystem. Use JSON for structured data and markdown for narrative content.
-
-### JSON for Structured State
-
-```json
-// data/projects/website-v2.json
-{
-  "name": "Website v2",
-  "status": "in-progress",
-  "milestone": "beta-launch",
-  "agents_involved": ["@dev", "@writer"],
-  "files": {
-    "spec": "docs/website-v2-spec.md",
-    "design": "designs/website-v2.fig"
-  },
-  "metrics": {
-    "commits": 47,
-    "last_session": "2026-04-22T11:30:00Z"
-  }
-}
-```
-
-### Markdown for Narrative
-
-Use markdown for anything a human reads: decisions, logs, research notes, contact records.
-
-### Schema Evolution
-
-Never rename existing fields. Add new fields and mark old ones deprecated:
-
-```json
-{
-  "name": "Website v2",
-  "status": "in-progress",
-  "milestone": "beta-launch",
-  "_deprecated_priority": "high",
-  "priority_v2": { "level": "high", "rationale": "Blocks investor demo" }
-}
-```
-
-This keeps historical data readable without migration scripts.
-
-## Anti-Patterns
-
-### Monolithic Single Agent
-
-```markdown
-# BAD - One agent does everything
-You are a full-stack developer, writer, researcher, and DevOps engineer.
-```
-
-Split into specialist agents. The kernel handles routing.
-
-### Stateless Sessions
-
-```markdown
-# BAD - No memory between sessions
-Starting fresh every time Claude Code opens.
-```
-
-Always read `data/` at session start and write back at session end.
-
-### Hardcoded Credentials
-
-```markdown
-# BAD - API keys in agent files or CLAUDE.md
-Your OpenAI API key is sk-xxxxxxxx
-```
-
-Use environment variables or a `.env` file loaded by scripts. Agents reference `process.env.API_KEY`.
-
-### External Database for Simple State
-
-```markdown
-# BAD - PostgreSQL for a solo user's agentic OS
-```
-
-Use JSON/markdown files until you have multiple concurrent users or GBs of data.
-
-### Over-Engineered Routing
-
-```markdown
-# BAD - Routing logic in code instead of markdown tables
-if (intent.includes('deploy')) { agent = opsAgent; }
-```
-
-Keep routing declarative in `CLAUDE.md` markdown tables. It is inspectable, editable, and debuggable.
-
-## Best Practices
-
-- [ ] `CLAUDE.md` is under 200 lines and fits in context window
-- [ ] Each agent file is under 100 lines and focused on one domain
-- [ ] `data/` is git-ignored for sensitive logs, git-tracked for decisions and specs
-- [ ] Commands use imperative names: `/daily-sync`, not `/run-daily-sync`
-- [ ] Logs are append-only; never edit past daily logs
-- [ ] Every agent has a `Memory Scope` section defining what files it reads
-- [ ] Reflections are written at the end of every session
-- [ ] Scheduled tasks use external cron (LaunchAgent, systemd, pm2), not Claude Code's session cron
-- [ ] Cost tracking: log API spend per session in `data/logs/<date>-costs.json`
-- [ ] One project = one Agentic OS. Do not share a single `CLAUDE.md` across unrelated projects.

skills/angular-developer/SKILL.md

@@ -1,154 +0,0 @@
----
-name: angular-developer
-description: Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.
-origin: ECC
----
-
-# Angular Developer Guidelines
-
-## When to Activate
-
-- Working in any Angular project or codebase
-- Creating or scaffolding a new Angular project, application, or library
-- Generating components, services, directives, pipes, guards, or resolvers
-- Implementing reactivity with Angular Signals, `linkedSignal`, or `resource`
-- Working with Angular forms (signal forms, reactive forms, or template-driven)
-- Setting up dependency injection, routing, lazy loading, or route guards
-- Adding accessibility (ARIA), animations, or component styling
-- Writing or debugging Angular-specific tests (unit, component harness, E2E)
-- Configuring Angular CLI tooling or the Angular MCP server
-
-1. Always analyze the project's Angular version before providing guidance, as best practices and available features can vary significantly between versions. If creating a new project with Angular CLI, do not specify a version unless prompted by the user.
-
-2. When generating code, follow Angular's style guide and best practices for maintainability and performance. Use the Angular CLI for scaffolding components, services, directives, pipes, and routes to ensure consistency.
-
-3. Once you finish generating code, run `ng build` to ensure there are no build errors. If there are errors, analyze the error messages and fix them before proceeding. Do not skip this step, as it is critical for ensuring the generated code is correct and functional.
-
-## Creating New Projects
-
-If no guidelines are provided by the user, use these defaults when creating a new Angular project:
-
-1. Use the latest stable version of Angular unless the user specifies otherwise.
-2. Prefer Signal Forms for new projects only when the target Angular version supports them. [Find out more](references/signal-forms.md).
-
-**Execution Rules for `ng new`:**
-When asked to create a new Angular project, you must determine the correct execution command by following these strict steps:
-
-**Step 1: Check for an explicit user version.**
-
-- **IF** the user requests a specific version (e.g., Angular 15), bypass local installations and strictly use `npx`.
-- **Command:** `npx @angular/cli@<requested_version> new <project-name>`
-
-**Step 2: Check for an existing Angular installation.**
-
-- **IF** no specific version is requested, run `ng version` in the terminal to check if the Angular CLI is already installed on the system.
-- **IF** the command succeeds and returns an installed version, use the local/global installation directly.
-- **Command:** `ng new <project-name>`
-
-**Step 3: Fallback to Latest.**
-
-- **IF** no specific version is requested AND the `ng version` command fails (indicating no Angular installation exists), you must use `npx` to fetch the latest version.
-- **Command:** `npx @angular/cli@latest new <project-name>`
-
-## Components
-
-When working with Angular components, consult the following references based on the task:
-
-- **Fundamentals**: Anatomy, metadata, core concepts, and template control flow (@if, @for, @switch). Read [components.md](references/components.md)
-- **Inputs**: Signal-based inputs, transforms, and model inputs. Read [inputs.md](references/inputs.md)
-- **Outputs**: Signal-based outputs and custom event best practices. Read [outputs.md](references/outputs.md)
-- **Host Elements**: Host bindings and attribute injection. Read [host-elements.md](references/host-elements.md)
-
-If you require deeper documentation not found in the references above, read the documentation at `https://angular.dev/guide/components`.
-
-## Reactivity and Data Management
-
-When managing state and data reactivity, use Angular Signals and consult the following references:
-
-- **Signals Overview**: Core signal concepts (`signal`, `computed`), reactive contexts, and `untracked`. Read [signals-overview.md](references/signals-overview.md)
-- **Dependent State (`linkedSignal`)**: Creating writable state linked to source signals. Read [linked-signal.md](references/linked-signal.md)
-- **Async Reactivity (`resource`)**: Fetching asynchronous data directly into signal state. Read [resource.md](references/resource.md)
-- **Side Effects (`effect`)**: Logging, third-party DOM manipulation (`afterRenderEffect`), and when NOT to use effects. Read [effects.md](references/effects.md)
-
-## Forms
-
-In most cases for new apps, **prefer signal forms**. When making a forms decision, analyze the project and consider the following guidelines:
-
-- If the application version supports Signal Forms and this is a new form, **prefer signal forms**.
-- For older applications or existing forms, match the application's current form strategy.
-
-- **Signal Forms**: Use signals for form state management. Read [signal-forms.md](references/signal-forms.md)
-- **Template-driven forms**: Use for simple forms. Read [template-driven-forms.md](references/template-driven-forms.md)
-- **Reactive forms**: Use for complex forms. Read [reactive-forms.md](references/reactive-forms.md)
-
-## Dependency Injection
-
-When implementing dependency injection in Angular, follow these guidelines:
-
-- **Fundamentals**: Overview of Dependency Injection, services, and the `inject()` function. Read [di-fundamentals.md](references/di-fundamentals.md)
-- **Creating and Using Services**: Creating services, the `providedIn: 'root'` option, and injecting into components or other services. Read [creating-services.md](references/creating-services.md)
-- **Defining Dependency Providers**: Automatic vs manual provision, `InjectionToken`, `useClass`, `useValue`, `useFactory`, and scopes. Read [defining-providers.md](references/defining-providers.md)
-- **Injection Context**: Where `inject()` is allowed, `runInInjectionContext`, and `assertInInjectionContext`. Read [injection-context.md](references/injection-context.md)
-- **Hierarchical Injectors**: The `EnvironmentInjector` vs `ElementInjector`, resolution rules, modifiers (`optional`, `skipSelf`), and `providers` vs `viewProviders`. Read [hierarchical-injectors.md](references/hierarchical-injectors.md)
-
-## Angular Aria
-
-When building accessible custom components for any of the following patterns: Accordion, Listbox, Combobox, Menu, Tabs, Toolbar, Tree, Grid, consult the following reference:
-
-- **Angular Aria Components**: Building headless, accessible components (Accordion, Listbox, Combobox, Menu, Tabs, Toolbar, Tree, Grid) and styling ARIA attributes. Read [angular-aria.md](references/angular-aria.md)
-
-## Routing
-
-When implementing navigation in Angular, consult the following references:
-
-- **Define Routes**: URL paths, static vs dynamic segments, wildcards, and redirects. Read [define-routes.md](references/define-routes.md)
-- **Route Loading Strategies**: Eager vs lazy loading, and context-aware loading. Read [loading-strategies.md](references/loading-strategies.md)
-- **Show Routes with Outlets**: Using `<router-outlet>`, nested outlets, and named outlets. Read [show-routes-with-outlets.md](references/show-routes-with-outlets.md)
-- **Navigate to Routes**: Declarative navigation with `RouterLink` and programmatic navigation with `Router`. Read [navigate-to-routes.md](references/navigate-to-routes.md)
-- **Control Route Access with Guards**: Implementing `CanActivate`, `CanMatch`, and other guards for security. Read [route-guards.md](references/route-guards.md)
-- **Data Resolvers**: Pre-fetching data before route activation with `ResolveFn`. Read [data-resolvers.md](references/data-resolvers.md)
-- **Router Lifecycle and Events**: Chronological order of navigation events and debugging. Read [router-lifecycle.md](references/router-lifecycle.md)
-- **Rendering Strategies**: CSR, SSG (Prerendering), and SSR with hydration. Read [rendering-strategies.md](references/rendering-strategies.md)
-- **Route Transition Animations**: Enabling and customizing the View Transitions API. Read [route-animations.md](references/route-animations.md)
-
-If you require deeper documentation or more context, visit the [official Angular Routing guide](https://angular.dev/guide/routing).
-
-## Styling and Animations
-
-When implementing styling and animations in Angular, consult the following references:
-
-- **Using Tailwind CSS with Angular**: Integrating Tailwind CSS into Angular projects. Read [tailwind-css.md](references/tailwind-css.md)
-- **Angular Animations**: Using native CSS (recommended) or the legacy DSL for dynamic effects. Read [angular-animations.md](references/angular-animations.md)
-- **Styling components**: Best practices for component styles and encapsulation. Read [component-styling.md](references/component-styling.md)
-
-## Testing
-
-When writing or updating tests, consult the following references based on the task:
-
-- **Fundamentals**: Best practices for unit testing, async patterns, and `TestBed`. Read [testing-fundamentals.md](references/testing-fundamentals.md)
-- **Component Harnesses**: Standard patterns for robust component interaction. Read [component-harnesses.md](references/component-harnesses.md)
-- **Router Testing**: Using `RouterTestingHarness` for reliable navigation tests. Read [router-testing.md](references/router-testing.md)
-- **End-to-End (E2E) Testing**: Best practices for E2E tests with Cypress or Playwright. Read [e2e-testing.md](references/e2e-testing.md)
-
-## Tooling
-
-When working with Angular tooling, consult the following references:
-
-- **Angular CLI**: Creating applications, generating code (components, routes, services), serving, and building. Read [cli.md](references/cli.md)
-- **Angular MCP Server**: Available tools, configuration, and experimental features. Read [mcp.md](references/mcp.md)
-
-## Anti-Patterns
-
-- Using `null` or `undefined` as initial signal form field values — use `''`, `0`, or `[]` instead
-- Accessing form field state flags without calling the field first: `form.field.valid()` — use `form.field().valid()`
-- Starting new forms with older form APIs when the target Angular version supports Signal Forms
-- Setting `min`, `max`, `value`, `disabled`, or `readonly` HTML attributes on `[formField]` inputs — define these as schema rules instead
-- Calling `inject()` outside an injection context — use `runInInjectionContext` when needed
-- Using `effect()` for derived state that should use `computed()`
-- Referencing `$parent.$index` in nested `@for` loops — Angular does not support `$parent`; use `let outerIdx = $index` instead
-
-## Related Skills
-
-- `tdd-workflow` — test-driven development workflow applicable to Angular components and services
-- `security-review` — security checklist for web applications including Angular-specific concerns
-- `frontend-patterns` — general frontend patterns for context on React/Next.js approaches

skills/angular-developer/references/angular-animations.md

@@ -1,160 +0,0 @@
-# Angular Animations
-
-When animating elements in Angular, **first analyze the project's Angular version** in `package.json`.
-For modern applications (**Angular v20.2 and above**), prefer using native CSS with `animate.enter` and `animate.leave`. For older applications, you may need to use the deprecated `@angular/animations` package.
-
-## 1. Native CSS Animations (v20.2+ Recommended)
-
-Modern Angular provides `animate.enter` and `animate.leave` to animate elements as they enter or leave the DOM. They apply CSS classes at the appropriate times.
-
-### `animate.enter` and `animate.leave`
-
-Use these directly on elements to apply CSS classes during the enter or leave phase. Angular automatically removes the enter classes when the animation completes. For `animate.leave`, Angular waits for the animation to finish before removing the element from the DOM.
-
-`animate.enter` example:
-
-```html
-@if (isShown()) {
-<div class="enter-container" animate.enter="enter-animation">
-  <p>The box is entering.</p>
-</div>
-}
-```
-
-```css
-/* Ensure you have a starting style if using transitions instead of keyframes */
-.enter-container {
-  border: 1px solid #dddddd;
-  margin-top: 1em;
-  padding: 20px;
-  font-weight: bold;
-  font-size: 20px;
-}
-.enter-container p {
-  margin: 0;
-}
-.enter-animation {
-  animation: slide-fade 1s;
-}
-@keyframes slide-fade {
-  from {
-    opacity: 0;
-    transform: translateY(20px);
-  }
-  to {
-    opacity: 1;
-    transform: translateY(0);
-  }
-}
-```
-
-_Note: `animate.leave` may be added to child elements being removed._
-
-### Event Bindings and Third-party Libraries
-
-You can bind to `(animate.enter)` and `(animate.leave)` to call functions or use JS libraries like GSAP.
-
-```html
-@if(show()) {
-<div (animate.leave)="onLeave($event)">...</div>
-}
-```
-
-```ts
-import { AnimationCallbackEvent } from '@angular/core';
-
-onLeave(event: AnimationCallbackEvent) {
-  // Custom animation logic here
-  // CRITICAL: You MUST call animationComplete() when done so Angular removes the element!
-  event.animationComplete();
-}
-```
-
-## 2. Advanced CSS Animations
-
-CSS offers robust tools for advanced animation sequences.
-
-### Animating State and Styles
-
-Toggle CSS classes on elements using property binding to trigger transitions.
-
-```html
-<div [class.open]="isOpen">...</div>
-```
-
-```css
-div {
-  transition: height 0.3s ease-out;
-  height: 100px;
-}
-div.open {
-  height: 200px;
-}
-```
-
-### Animating Auto Height
-
-You can use `css-grid` to animate to auto height.
-
-```css
-.container {
-  display: grid;
-  grid-template-rows: 0fr;
-  transition: grid-template-rows 0.3s;
-}
-.container.open {
-  grid-template-rows: 1fr;
-}
-.container > div {
-  overflow: hidden;
-}
-```
-
-### Staggering and Parallel Animations
-
-- **Staggering**: Use `animation-delay` or `transition-delay` with different values for items in a list.
-- **Parallel**: Apply multiple animations in the `animation` shorthand (e.g., `animation: rotate 3s, fade-in 2s;`).
-
-### Programmatic Control
-
-Retrieve animations directly using standard Web APIs:
-
-```ts
-const animations = element.getAnimations();
-animations.forEach((anim) => anim.pause());
-```
-
-## 3. Legacy Animations DSL (Deprecated)
-
-For older projects (pre v20.2 or where `@angular/animations` is already heavily used), you use the component metadata DSL.
-
-**Important:** Do not mix legacy animations and `animate.enter`/`leave` in the same component.
-
-### Setup
-
-```ts
-bootstrapApplication(App, {
-  providers: [provideAnimationsAsync()],
-});
-```
-
-### Defining Transitions
-
-```ts
-import {signal} from '@angular/core';
-import {trigger, state, style, animate, transition} from '@angular/animations';
-
-@Component({
-  animations: [
-    trigger('openClose', [
-      state('open', style({opacity: 1})),
-      state('closed', style({opacity: 0})),
-      transition('open <=> closed', [animate('0.5s')]),
-    ]),
-  ],
-  template: `<div [@openClose]="isOpen() ? 'open' : 'closed'">...</div>`,
-})
-export class OpenClose {
-  isOpen = signal(true);
-}
-```

skills/angular-developer/references/angular-aria.md

@@ -1,410 +0,0 @@
-# Angular Aria
-
-Angular Aria (`@angular/aria`) is a collection of headless, accessible directives that implement common WAI-ARIA patterns. These directives handle keyboard interactions, ARIA attributes, focus management, and screen reader support.
-
-**As an AI Agent, your role is to provide the HTML structure and CSS styling**, while the directives handle the complex accessibility logic.
-
-## Styling Headless Components
-
-Because Angular Aria components are headless, they do not come with default styles. You **must** use CSS to style different states based on the ARIA attributes or structural classes the directives automatically apply.
-
-Common ARIA attributes to target in CSS:
-
-- `[aria-expanded="true"]` / `[aria-expanded="false"]`
-- `[aria-selected="true"]`
-- `[aria-disabled="true"]`
-- `[aria-current="page"]` (for navigation)
-
----
-
-**CRITICAL**: Before using this package, it must be installed via the package manager. Confirm that it has been installed in the project. Use `npm install @angular/aria` to install if necessary.
-
-## 1. Accordion
-
-Organizes related content into expandable/collapsible sections.
-
-**Usage:** The Accordion is a layout component designed to organize content into logical groups that users can expand one at a time to reduce scrolling on content-heavy pages. Use it for FAQs, long forms, or progressive disclosure of information, but avoid it for primary navigation or scenarios where users must view multiple sections of content simultaneously.
-
-**Imports:** `import { AccordionContent, AccordionGroup, AccordionPanel, AccordionTrigger } from '@angular/aria/accordion';`
-
-**Directives:** `ngAccordionGroup`, `ngAccordionTrigger`, `ngAccordionPanel`, `ngAccordionContent` (for lazy loading).
-
-```ts
-@Component({
-  selector: 'app-cmp',
-  imports: [AccordionContent, AccordionGroup, AccordionPanel, AccordionTrigger],
-  template: `...`,
-  styles: [],
-})
-export class App {
-  protected readonly title = signal('angular-app');
-}
-```
-
-```html
-<div ngAccordionGroup [multiExpandable]="false">
-  <div class="accordion-item">
-    <button ngAccordionTrigger panelId="panel-1" class="accordion-header">
-      Section 1
-      <span class="icon">▼</span>
-    </button>
-    <div ngAccordionPanel panelId="panel-1" class="accordion-panel">
-      <ng-template ngAccordionContent>
-        <p>Lazy loaded content here.</p>
-      </ng-template>
-    </div>
-  </div>
-</div>
-```
-
-**Styling Strategy:**
-Target the `[aria-expanded]` attribute on the trigger to rotate icons, and style the panel visibility.
-
-```css
-.accordion-header[aria-expanded='true'] .icon {
-  transform: rotate(180deg);
-}
-
-/* The panel directive handles DOM removal, but you can style the transition */
-.accordion-panel {
-  padding: 1rem;
-  border-top: 1px solid #ccc;
-}
-```
-
----
-
-## 2. Listbox
-
-A foundational directive for displaying a list of options. Used for visible selection lists (not dropdowns).
-
-**Usage:** Visible selectable lists (single or multi-select).
-
-**Imports:** `import {Listbox, Option} from '@angular/aria/listbox';`
-
-**Directives:** `ngListbox`, `ngOption`.
-
-```ts
-@Component({
-  selector: 'app-cmp',
-  imports: [Listbox, Option],
-  template: `...`,
-  styles: [],
-})
-export class App {
-  protected readonly title = signal('angular-app');
-}
-```
-
-```html
-<!-- horizontal or vertical orientation -->
-<ul ngListbox [(values)]="selectedItems" orientation="horizontal" [multi]="true">
-  <li ngOption value="apple" class="option">Apple</li>
-  <li ngOption value="banana" class="option">Banana</li>
-</ul>
-```
-
-**Styling Strategy:**
-Target `[aria-selected="true"]` for selected state and `:focus-visible` or `[data-active]` for the focused item (Angular Aria uses roving tabindex or activedescendant).
-
-```css
-.option {
-  padding: 8px;
-  cursor: pointer;
-}
-.option[aria-selected='true'] {
-  background: #e0f7fa;
-  font-weight: bold;
-}
-/* Focus state managed by aria */
-.option:focus-visible {
-  outline: 2px solid blue;
-}
-```
-
----
-
-## 3. Combobox, Select, and Multiselect
-
-These patterns combine `ngCombobox` with a popup containing an `ngListbox`.
-
-- **Combobox**: Text input + popup (used for Autocomplete).
-- **Select**: Readonly Combobox + single-select Listbox.
-- **Multiselect**: Readonly Combobox + multi-select Listbox.
-
-**Usage:** The Combobox is a low-level primitive directive that synchronizes a text input with a popup, serving as the foundational logic for autocomplete, select, and multiselect patterns. Use it specifically for building custom filtering, unique selection requirements, or specialized input-to-popup coordination that deviates from standard, documented components.
-
-**Imports:**
-
-```
-  import {Combobox, ComboboxInput, ComboboxPopupContainer} from '@angular/aria/combobox';
-  import {Listbox, Option} from '@angular/aria/listbox';
-```
-
-**Directives:** `ngCombobox`, `ngComboboxInput`, `ngComboboxPopupContainer`, `ngListbox`, `ngOption`.
-
-```html
-<!-- Example: Standard Select -->
-<div ngCombobox [readonly]="true">
-  <button ngComboboxInput class="select-trigger">
-    {{ selectedValue() || 'Choose an option' }}
-  </button>
-
-  <ng-template ngComboboxPopupContainer>
-    <ul ngListbox [(values)]="selectedValue" class="dropdown-menu">
-      <li ngOption value="option1">Option 1</li>
-      <li ngOption value="option2">Option 2</li>
-    </ul>
-  </ng-template>
-</div>
-```
-
-**Styling Strategy:**
-Style the popup container to look like a dropdown floating above content (often paired with CDK Overlay).
-
-```css
-.select-trigger {
-  width: 200px;
-  padding: 8px;
-  text-align: left;
-}
-.dropdown-menu {
-  list-style: none;
-  padding: 0;
-  margin: 0;
-  border: 1px solid #ccc;
-  background: white;
-  box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
-}
-```
-
----
-
-## 4. Menu and Menubar
-
-For actions, commands, and context menus (not for form selection).
-
-**Usage:** The Menubar is a high-level navigation pattern designed for building desktop-style application command bars (e.g., File, Edit, View) that stay persistent across an interface. It is best utilized for organizing complex commands into logical top-level categories with full horizontal keyboard support, but it should be avoided for simple standalone action lists or mobile-first layouts where horizontal space is constrained.
-
-**Imports:** `import {MenuBar, Menu, MenuContent, MenuItem} from '@angular/aria/menu';`
-
-**Directives:** `ngMenuBar`, `ngMenu`, `ngMenuItem`, `ngMenuTrigger`.
-
-```html
-<!-- Menubar Example -->
-<ul ngMenuBar class="menubar">
-  <li ngMenuItem value="file">
-    <button ngMenuTrigger [menu]="fileMenu">File</button>
-  </li>
-</ul>
-
-<ul ngMenu #fileMenu="ngMenu" class="menu">
-  <li ngMenuItem value="new">New</li>
-  <li ngMenuItem value="open">Open</li>
-</ul>
-```
-
-**Styling Strategy:**
-Use flexbox for the menubar. Hide/show submenus based on the trigger's state.
-
-```css
-.menubar {
-  display: flex;
-  gap: 10px;
-  list-style: none;
-  padding: 0;
-}
-.menu {
-  background: white;
-  border: 1px solid #ccc;
-  padding: 5px 0;
-}
-.menu li {
-  padding: 5px 15px;
-  cursor: pointer;
-}
-```
-
----
-
-## 5. Tabs
-
-Layered content sections where only one panel is visible.
-
-**Usage:** The Tabs component is used to organize related content into distinct, navigable sections, allowing users to switch between categories or views without leaving the page. It is ideal for settings panels, multi-topic documentation, or dashboards, but should be avoided for sequential workflows (steppers) or when navigation involves more than 7–8 sections.
-
-**Imports:** `import {Tab, Tabs, TabList, TabPanel, TabContent} from '@angular/aria/tabs';`
-
-**Directives:** `ngTabs`, `ngTabList`, `ngTab`, `ngTabPanel`, `ngTabContent`.
-
-```html
-<div ngTabs>
-  <ul ngTabList class="tab-list">
-    <li ngTab value="profile" class="tab-btn">Profile</li>
-    <li ngTab value="security" class="tab-btn">Security</li>
-  </ul>
-
-  <div ngTabPanel value="profile" class="tab-panel">
-    <ng-template ngTabContent>Profile Settings</ng-template>
-  </div>
-  <div ngTabPanel value="security" class="tab-panel">
-    <ng-template ngTabContent>Security Settings</ng-template>
-  </div>
-</div>
-```
-
-**Styling Strategy:**
-Target `[aria-selected="true"]` on the tab buttons.
-
-```css
-.tab-list {
-  display: flex;
-  border-bottom: 2px solid #ccc;
-  list-style: none;
-  padding: 0;
-}
-.tab-btn {
-  padding: 10px 20px;
-  cursor: pointer;
-  border-bottom: 2px solid transparent;
-}
-.tab-btn[aria-selected='true'] {
-  border-bottom-color: blue;
-  font-weight: bold;
-}
-.tab-panel {
-  padding: 20px;
-}
-```
-
----
-
-## 6. Toolbar
-
-Groups related controls (like text formatting).
-
-**Usage:** The Toolbar is an organizational component designed to group frequently accessed, related controls into a single logical container. It is best used to enhance keyboard efficiency (via arrow-key navigation) and visual structure for workflows requiring repeated actions, such as text formatting or media controls.
-
-**Imports:** `import {Toolbar, ToolbarWidget, ToolbarWidgetGroup} from '@angular/aria/toolbar';`
-
-**Directives:** `ngToolbar`, `ngToolbarWidget`, `ngToolbarWidgetGroup`.
-
-```html
-<div ngToolbar class="toolbar">
-  <div ngToolbarWidgetGroup [multi]="true" role="group" aria-label="Formatting">
-    <button ngToolbarWidget value="bold" class="tool-btn">B</button>
-    <button ngToolbarWidget value="italic" class="tool-btn">I</button>
-  </div>
-</div>
-```
-
-**Styling Strategy:**
-Target `[aria-pressed="true"]` (for toggle buttons) or `[aria-checked="true"]` (for radio groups) within the toolbar.
-
-```css
-.toolbar {
-  display: flex;
-  gap: 5px;
-  padding: 8px;
-  background: #f5f5f5;
-}
-.tool-btn {
-  padding: 5px 10px;
-  border: 1px solid #ccc;
-}
-.tool-btn[aria-pressed='true'],
-.tool-btn[aria-checked='true'] {
-  background: #ddd;
-}
-```
-
----
-
-## 7. Tree
-
-Displays hierarchical data (file systems, nested nav).
-
-**Usage:** The Tree component is designed for navigating and displaying deeply nested, hierarchical data structures like file systems, organization charts, or complex site architectures. It should be used specifically for multi-level relationships where users need to expand or collapse branches, but it should be avoided for flat lists, data tables, or simple selection menus.
-
-**Imports:** `import {Tree, TreeItem, TreeItemGroup} from '@angular/aria/tree';`
-
-**Directives:** `ngTree`, `ngTreeItem`, `ngTreeGroup`.
-
-```html
-<ul ngTree class="tree">
-  <li ngTreeItem value="documents">
-    <span class="tree-label">Documents</span>
-    <ul ngTreeGroup class="tree-group">
-      <li ngTreeItem value="resume">Resume.pdf</li>
-    </ul>
-  </li>
-</ul>
-```
-
-**Styling Strategy:**
-Target `[aria-expanded]` to show/hide children or rotate chevron icons. Use `padding-left` on nested groups to show hierarchy.
-
-```css
-.tree,
-.tree-group {
-  list-style: none;
-  padding-left: 20px;
-}
-.tree-label::before {
-  content: '> ';
-  display: inline-block;
-  transition: transform 0.2s;
-}
-li[aria-expanded='true'] > .tree-label::before {
-  transform: rotate(90deg);
-}
-```
-
-## 8. Grid
-
-A two-dimensional interactive collection of cells enabling navigation via arrow keys.
-
-**Usage:** Data tables, calendars, spreadsheets, and layout patterns for interactive elements.
-**Directives:** `ngGrid`, `ngGridRow`, `ngGridCell`, `ngGridCellWidget`.
-
-```html
-<table ngGrid [multi]="true" [enableSelection]="true" class="grid-table">
-  <tr ngGridRow>
-    <th ngGridCell role="columnheader">Name</th>
-    <th ngGridCell role="columnheader">Status</th>
-  </tr>
-  <tr ngGridRow>
-    <td ngGridCell>Project A</td>
-    <td ngGridCell [(selected)]="isSelected">
-      <button ngGridCellWidget (activated)="onActivate()">Active</button>
-    </td>
-  </tr>
-</table>
-```
-
-**Styling Strategy:**
-Target `[aria-selected="true"]` for selected cells and `:focus-visible` for the active cell (roving tabindex) or `[aria-activedescendant]` on the container.
-
-```css
-.grid-table {
-  border-collapse: collapse;
-}
-[ngGridCell] {
-  padding: 8px;
-  border: 1px solid #ddd;
-}
-[ngGridCell][aria-selected='true'] {
-  background: #e3f2fd;
-}
-/* Focus state managed by roving tabindex */
-[ngGridCell]:focus-visible {
-  outline: 2px solid #2196f3;
-  outline-offset: -2px;
-}
-```
-
-## General Rules for Agents
-
-1. **Never use native HTML elements like `<select>`** when asked to implement these specific Aria patterns. Use the `ng*` directives.
-2. **Handle CSS manually**: Remember that `Angular Aria` does NOT provide styles. You must write the CSS, targeting the native ARIA attributes (`aria-expanded`, `aria-selected`, etc.) that the directives automatically toggle.
-3. **Lazy Loading**: Always use the provided structural directives (`ngAccordionContent`, `ngTabContent`) inside `ng-template` for heavy content panels to ensure they are lazily rendered.

skills/angular-developer/references/cli.md

@@ -1,86 +0,0 @@
-# Angular CLI Guide for Agents
-
-The Angular CLI (`ng`) is the primary tool for managing an Angular workspace. Always prefer CLI commands over manual file creation or generic `npm` commands when modifying project structure or adding Angular-specific dependencies.
-
-## 1. Managing Dependencies
-
-**ALWAYS use `ng add` for Angular libraries** instead of `npm install`. `ng add` installs the package AND runs initialization schematics (e.g., configuring `angular.json`, updating root providers).
-
-```bash
-ng add @angular/material
-ng add tailwindcss
-ng add @angular/fire
-```
-
-To update the application and its dependencies (which automatically runs code migrations):
-
-```bash
-ng update @angular/core@<latest or specific version> @angular/cli<latest or specific version>
-```
-
-## 2. Generating Code (`ng generate` or `ng g`)
-
-Always use the CLI to generate code to ensure it adheres to Angular standards and updates necessary configuration files automatically.
-
-| Target       | Command               | Notes                                                                                          |
-| :----------- | :-------------------- | :--------------------------------------------------------------------------------------------- |
-| Component    | `ng g c path/to/name` | Generates a component. Use `--inline-style` (`-s`) or `--inline-template` (`-t`) if requested. |
-| Service      | `ng g s path/to/name` | Generates an `@Injectable({providedIn: 'root'})` service.                                      |
-| Directive    | `ng g d path/to/name` | Generates a directive.                                                                         |
-| Pipe         | `ng g p path/to/name` | Generates a pipe.                                                                              |
-| Guard        | `ng g g path/to/name` | Generates a functional route guard.                                                            |
-| Environments | `ng g environments`   | Scaffolds `src/environments/` and updates `angular.json` with file replacements.               |
-
-_Note: There is no command to generate a single route definition. Generate a component, then manually add it to the `Routes` array in `app.routes.ts`._
-
-## 3. Development Server & Proxying
-
-Start the local development server with hot-module replacement (HMR):
-
-```bash
-ng serve
-```
-
-### Backend API Proxying
-
-To proxy API requests during development (e.g., rerouting `/api` to a local Node server):
-
-1. Create `src/proxy.conf.json`:
-   ```json
-   {
-     "/api/**": {"target": "http://localhost:3000", "secure": false}
-   }
-   ```
-2. Update `angular.json` under the `serve` target:
-   ```json
-   "serve": {
-     "builder": "@angular/build:dev-server",
-     "options": { "proxyConfig": "src/proxy.conf.json" }
-   }
-   ```
-
-## 4. Building the Application
-
-Compile the application into an output directory (default: `dist/<project-name>/browser`). Modern Angular uses the `@angular/build:application` builder (esbuild-based).
-
-```bash
-ng build
-```
-
-- `ng build` defaults to the production configuration, which enables Ahead-of-Time (AOT) compilation, minification, and tree-shaking.
-- Target specific configurations defined in `angular.json` using `--configuration`: `ng build --configuration=staging`.
-
-## 5. Testing
-
-- **Unit Tests**: Run `ng test` to execute unit tests via the configured test runner (e.g., Karma or Vitest).
-- **End-to-End (E2E)**: Run `ng e2e`. If no E2E framework is configured, the CLI will prompt to install one (Cypress, Playwright, Puppeteer, etc.).
-
-## 6. Deployment
-
-To deploy an application, you must first add a deployment builder, then run the deploy command:
-
-```bash
-# Example for Firebase
-ng add @angular/fire
-ng deploy
-```

skills/angular-developer/references/component-harnesses.md

@@ -1,59 +0,0 @@
-# Testing with Component Harnesses
-
-Component harnesses are the standard, preferred way to interact with components in tests. They provide a robust, user-centric API that makes tests less brittle and easier to read by insulating them from changes to a component's internal DOM structure.
-
-## Why Use Harnesses?
-
-- **Robustness:** Tests don't break when you refactor a component's internal HTML or CSS classes.
-- **Readability:** Tests describe interactions from a user's perspective (e.g., `button.click()`, `slider.getValue()`) instead of through DOM queries (`fixture.nativeElement.querySelector(...)`).
-- **Reusability:** The same harness can be used in both unit tests and E2E tests.
-
-Angular Material provides a test harness for every component in its library.
-
-## Using a Harness in a Unit Test
-
-The `TestbedHarnessEnvironment` is the entry point for using harnesses in unit tests.
-
-### Example: Testing with a `MatButtonHarness`
-
-```ts
-import {TestbedHarnessEnvironment} from '@angular/cdk/testing/testbed';
-import {MatButtonHarness} from '@angular/material/button/testing';
-import {MyButtonContainerComponent} from './my-button-container.component';
-
-describe('MyButtonContainerComponent', () => {
-  let fixture: ComponentFixture<MyButtonContainerComponent>;
-  let loader: HarnessLoader;
-
-  beforeEach(async () => {
-    await TestBed.configureTestingModule({
-      imports: [MyButtonContainerComponent, MatButtonModule],
-    }).compileComponents();
-
-    fixture = TestBed.createComponent(MyButtonContainerComponent);
-    // Create a harness loader for the component's fixture
-    loader = TestbedHarnessEnvironment.loader(fixture);
-  });
-
-  it('should find a button with specific text', async () => {
-    // Load the harness for a MatButton with the text "Submit"
-    const submitButton = await loader.getHarness(MatButtonHarness.with({text: 'Submit'}));
-
-    // Use the harness API to interact with the component
-    expect(await submitButton.isDisabled()).toBe(false);
-    await submitButton.click();
-
-    // ... assertions
-  });
-});
-```
-
-### Key Concepts
-
-1. **`HarnessLoader`**: An object used to find and create harness instances. Get a loader for your component's fixture using `TestbedHarnessEnvironment.loader(fixture)`.
-
-2. **`loader.getHarness(HarnessClass)`**: Asynchronously finds and returns a harness instance for the first matching component.
-
-3. **`HarnessClass.with({ ... })`**: Many harnesses provide a static `with` method that returns a `HarnessPredicate`. This allows you to filter and find components based on their properties, like text, selector, or disabled state. Always use this to precisely target the component you want to test.
-
-4. **Harness API:** Once you have a harness instance, use its methods (e.g., `.click()`, `.getText()`, `.getValue()`) to interact with the component. These methods automatically handle waiting for async operations and change detection.

skills/angular-developer/references/component-styling.md

@@ -1,91 +0,0 @@
-# Component Styling
-
-Angular components can define styles that apply specifically to their template, enabling encapsulation and modularity.
-
-## Defining Styles
-
-Styles can be defined inline or in separate files.
-
-```ts
-@Component({
-  selector: 'app-photo',
-  // Inline styles
-  styles: `
-    img {
-      border-radius: 50%;
-    }
-  `,
-  // OR external file
-  styleUrl: 'photo.component.css',
-})
-export class Photo {}
-```
-
-## View Encapsulation
-
-Every component has a view encapsulation setting that determines how styles are scoped.
-
-| Mode                            | Behavior                                                                                      |
-| :------------------------------ | :-------------------------------------------------------------------------------------------- |
-| `Emulated` (Default)            | Scopes styles to the component using unique HTML attributes. Global styles can still leak in. |
-| `ShadowDom`                     | Uses the browser's native Shadow DOM API to isolate styles completely.                        |
-| `None`                          | Disables encapsulation. Component styles become global.                                       |
-| `ExperimentalIsolatedShadowDom` | Strictly guarantees that only the component's styles apply.                                   |
-
-### Usage
-
-```ts
-import { ViewEncapsulation } from '@angular/core';
-
-@Component({
-  ...,
-  encapsulation: ViewEncapsulation.None,
-})
-export class GlobalStyled {}
-```
-
-## Special Selectors
-
-### `:host`
-
-Targets the component's host element (the element matching the component's selector).
-
-```css
-:host {
-  display: block;
-  border: 1px solid black;
-}
-```
-
-### `:host-context()`
-
-Targets the host element based on some condition in its ancestry.
-
-```css
-/* Apply styles if any ancestor has the 'theme-dark' class */
-:host-context(.theme-dark) {
-  background-color: #333;
-}
-```
-
-### `::ng-deep`
-
-Disables view encapsulation for a specific rule, allowing it to "leak" into child components.
-**Note: The Angular team strongly discourages the use of `::ng-deep`.** It is supported only for backwards compatibility.
-
-## Styles in Templates
-
-You can use `<style>` elements directly in a component's template. View encapsulation rules still apply.
-
-```html
-<style>
-  .dynamic-class {
-    color: red;
-  }
-</style>
-<div class="dynamic-class">Hello</div>
-```
-
-## External Styles
-
-Using `<link>` or `@import` in CSS is treated as external styles. **External styles are not affected by emulated view encapsulation.**

skills/angular-developer/references/components.md

@@ -1,117 +0,0 @@
-# Components
-
-Angular components are the fundamental building blocks of an application. Each component consists of a TypeScript class with behaviors, an HTML template, and a CSS selector.
-
-## Component Definition
-
-Use the `@Component` decorator to define a component's metadata.
-
-```ts
-@Component({
-  selector: 'app-profile',
-  template: `
-    <img src="profile.jpg" alt="Profile photo" />
-    <button (click)="save()">Save</button>
-  `,
-  styles: `
-    img {
-      border-radius: 50%;
-    }
-  `,
-})
-export class Profile {
-  save() {
-    /* ... */
-  }
-}
-```
-
-## Metadata Options
-
-- `selector`: The CSS selector that identifies this component in templates.
-- `template`: Inline HTML template (preferred for small templates).
-- `templateUrl`: Path to an external HTML file.
-- `styles`: Inline CSS styles.
-- `styleUrl` / `styleUrls`: Path(s) to external CSS file(s).
-- `imports`: Lists the components, directives, or pipes used in this component's template.
-
-## Using Components
-
-To use a component, add it to the `imports` array of the consuming component and use its selector in the template.
-
-```ts
-@Component({
-  selector: 'app-root',
-  imports: [Profile],
-  template: `<app-profile />`,
-})
-export class App {}
-```
-
-## Template Control Flow
-
-Angular uses built-in blocks for conditional rendering and loops.
-
-### Conditional Rendering (`@if`)
-
-Use `@if` to conditionally show content. You can include `@else if` and `@else` blocks.
-
-```html
-@if (user.isAdmin) {
-<admin-dashboard />
-} @else if (user.isModerator) {
-<mod-dashboard />
-} @else {
-<standard-dashboard />
-}
-```
-
-**Result aliasing**: Save the result of the expression for reuse.
-
-```html
-@if (user.settings(); as settings) {
-<p>Theme: {{ settings.theme }}</p>
-}
-```
-
-### Loops (`@for`)
-
-The `@for` block iterates over collections. The `track` expression is **required** for performance and DOM reuse.
-
-```html
-<ul>
-  @for (item of items(); track item.id; let i = $index, total = $count) {
-  <li>{{ i + 1 }}/{{ total }}: {{ item.name }}</li>
-  } @empty {
-  <li>No items to display.</li>
-  }
-</ul>
-```
-
-**Implicit Variables**: `$index`, `$count`, `$first`, `$last`, `$even`, `$odd`.
-
-### Switching Content (`@switch`)
-
-The `@switch` block renders content based on a value. It uses strict equality (`===`) and has **no fallthrough**.
-
-```html
-@switch (status()) { @case ('loading') { <app-spinner /> } @case ('error') { <app-error-msg /> }
-@case ('success') { <app-data-grid /> } @default {
-<p>Unknown status</p>
-} }
-```
-
-**Exhaustive Type Checking**: Use `@default never;` to ensure all cases of a union type are handled.
-
-```html
-@switch (state) { @case ('on') { ... } @case ('off') { ... } @default never; // Errors if a new
-state like 'standby' is added }
-```
-
-## Core Concepts
-
-- **Host Element**: The DOM element that matches the component's selector.
-- **View**: The DOM rendered by the component's template inside the host element.
-- **Standalone**: By default, components are standalone (since Angular 19, `standalone: true` is default). For older versions, `standalone: true` must be explicit or the component must be part of an `NgModule`.
-- **Component Tree**: Angular applications are structured as a tree of components, where each component can host child components.
-- **Component Naming**: Do not add suffixes the `Component` suffix for Component classes (e.g., AppComponent) unless the project has been configured to use that naming configuration.

skills/angular-developer/references/creating-services.md

@@ -1,97 +0,0 @@
-# Creating and Using Services
-
-Services in Angular are reusable pieces of code that handle data fetching, business logic, or state management that multiple components or other services need to access.
-
-## Creating a Service
-
-You can generate a service using the Angular CLI:
-
-```bash
-ng generate service my-data
-```
-
-Or you can manually create a TypeScript class and decorate it with `@Injectable()`.
-
-```ts
-import {Injectable} from '@angular/core';
-
-@Injectable({
-  providedIn: 'root',
-})
-export class BasicDataStore {
-  private data: string[] = [];
-
-  addData(item: string): void {
-    this.data.push(item);
-  }
-
-  getData(): string[] {
-    return [...this.data];
-  }
-}
-```
-
-### The `providedIn: 'root'` Option
-
-Using `providedIn: 'root'` is the recommended approach for most services. It tells Angular to:
-
-- **Create a single instance (singleton)** for the entire application.
-- **Make it available everywhere** automatically, without needing to list it in any `providers` array.
-- **Enable tree-shaking**, meaning the service is only included in the final JavaScript bundle if it is actually injected somewhere.
-
-## Injecting a Service
-
-Once a service is created, you can inject it into components, directives, or other services using the `inject()` function.
-
-### Injecting into a Component
-
-```ts
-import {Component, inject} from '@angular/core';
-import {BasicDataStore} from './basic-data-store.service';
-
-@Component({
-  selector: 'app-example',
-  template: `
-    <div>
-      <p>Data items: {{ dataStore.getData().length }}</p>
-      <button (click)="dataStore.addData('New Item')">Add Item</button>
-    </div>
-  `,
-})
-export class Example {
-  // Inject the service as a class field
-  dataStore = inject(BasicDataStore);
-}
-```
-
-### Injecting into Another Service
-
-Services can inject other services in the exact same way.
-
-```ts
-import {Injectable, inject} from '@angular/core';
-import {AdvancedDataStore} from './advanced-data-store.service';
-
-@Injectable({
-  providedIn: 'root',
-})
-export class BasicDataStore {
-  // Injecting another service
-  private advancedDataStore = inject(AdvancedDataStore);
-
-  private data: string[] = [];
-
-  getData(): string[] {
-    // Combine data from this service and the injected service
-    return [...this.data, ...this.advancedDataStore.getData()];
-  }
-}
-```
-
-## Advanced Service Patterns
-
-While `providedIn: 'root'` covers most scenarios, you may sometimes need:
-
-- **Component-specific instances**: If a component needs its own isolated instance of a service, provide it directly in the component's `@Component({ providers: [MyService] })` array.
-- **Factory providers**: For dynamic creation.
-- **Value providers**: For injecting configuration objects.

skills/angular-developer/references/data-resolvers.md

@@ -1,69 +0,0 @@
-# Data Resolvers
-
-Data resolvers fetch data before a route activates, ensuring components have the necessary data upon rendering.
-
-## Creating a Resolver
-
-Implement the `ResolveFn` type.
-
-```ts
-export const userResolver: ResolveFn<User> = (route, state) => {
-  const userService = inject(UserService);
-  const id = route.paramMap.get('id')!;
-  return userService.getUser(id);
-};
-```
-
-## Configuring the Route
-
-Add the resolver under the `resolve` key.
-
-```ts
-{
-  path: 'user/:id',
-  component: UserProfile,
-  resolve: {
-    user: userResolver
-  }
-}
-```
-
-## Accessing Resolved Data
-
-### 1. Via `ActivatedRoute` (Traditional)
-
-```ts
-private route = inject(ActivatedRoute);
-data = toSignal(this.route.data);
-user = computed(() => this.data().user);
-```
-
-### 2. Via Component Inputs (Modern)
-
-Enable `withComponentInputBinding()` in `provideRouter` to pass resolved data directly to `@Input` or `input()`.
-
-```ts
-// app.config.ts
-provideRouter(routes, withComponentInputBinding());
-
-// component.ts
-user = input.required<User>();
-```
-
-## Error Handling
-
-Navigation is blocked if a resolver fails.
-
-- Use `withNavigationErrorHandler` for global handling.
-- Use `catchError` within the resolver to return a `RedirectCommand` or fallback data.
-
-```ts
-return userService
-  .get(id)
-  .pipe(catchError(() => of(new RedirectCommand(router.parseUrl('/error')))));
-```
-
-## Best Practices
-
-- **Keep it lightweight**: Fetch only critical data.
-- **Provide feedback**: Listen to router events to show a global loading bar during navigation, as the UI stays on the old page until the resolver finishes.

skills/angular-developer/references/define-routes.md

@@ -1,67 +0,0 @@
-# Define Routes
-
-Routes are objects that define which component should render for a specific URL path.
-
-## Basic Configuration
-
-Define routes in a `Routes` array and provide them using `provideRouter` in your `appConfig`.
-
-```ts
-// app.routes.ts
-export const routes: Routes = [
-  {path: '', component: HomePage},
-  {path: 'admin', component: AdminPage},
-];
-
-// app.config.ts
-export const appConfig: ApplicationConfig = {
-  providers: [provideRouter(routes)],
-};
-```
-
-## URL Paths
-
-- **Static**: Matches an exact string (e.g., `'admin'`).
-- **Route Parameters**: Dynamic segments prefixed with a colon (e.g., `'user/:id'`).
-- **Wildcard**: Matches any URL using `**`. Useful for "Not Found" pages. **Always place at the end of the array.**
-
-## Matching Strategy
-
-Angular uses a **first-match wins** strategy. Specific routes must come before less specific ones.
-
-## Redirects
-
-Use `redirectTo` to point one path to another.
-
-```ts
-{ path: 'articles', redirectTo: '/blog' },
-{ path: 'blog', component: Blog },
-```
-
-## Page Titles
-
-Associate titles with routes for accessibility. Titles can be static or dynamic (via `ResolveFn` or a custom `TitleStrategy`).
-
-```ts
-{ path: 'home', component: Home, title: 'Home Page' }
-```
-
-## Route Data and Providers
-
-- **Static Data**: Attach metadata using the `data` property.
-- **Route Providers**: Scope dependencies to a specific route and its children using the `providers` array.
-
-## Nested (Child) Routes
-
-Define sub-views using the `children` property. Parent components must include a `<router-outlet />`.
-
-```ts
-{
-  path: 'product/:id',
-  component: Product,
-  children: [
-    { path: 'info', component: ProductInfo },
-    { path: 'reviews', component: ProductReviews },
-  ],
-}
-```

skills/angular-developer/references/defining-providers.md

@@ -1,72 +0,0 @@
-# Defining Dependency Providers
-
-Angular offers automatic and manual ways to provide dependencies to its Dependency Injection (DI) system.
-
-## Automatic Provision
-
-The most common way to provide a service is using `providedIn: 'root'` on an `@Injectable()`.
-
-### InjectionToken
-
-Use `InjectionToken` for non-class dependencies (configuration objects, functions, primitives). An `InjectionToken` can also be automatically provided.
-
-```ts
-import {InjectionToken} from '@angular/core';
-
-export interface AppConfig {
-  apiUrl: string;
-}
-
-export const APP_CONFIG = new InjectionToken<AppConfig>('app.config', {
-  providedIn: 'root',
-  factory: () => ({apiUrl: 'https://api.example.com'}),
-});
-```
-
-## Manual Provision
-
-You use the `providers` array when a service lacks `providedIn`, when you want a new instance for a specific component, or when configuring runtime values.
-
-```ts
-@Component({
-  providers: [
-    // Shorthand for { provide: LocalService, useClass: LocalService }
-    LocalService,
-
-    // useClass: Swap implementations
-    {provide: Logger, useClass: BetterLogger},
-
-    // useValue: Provide static values
-    {provide: API_URL_TOKEN, useValue: 'https://api.example.com'},
-
-    // useFactory: Generate value dynamically
-    {
-      provide: ApiClient,
-      useFactory: (http = inject(HttpClient)) => new ApiClient(http),
-    },
-
-    // useExisting: Create an alias
-    {provide: OldLogger, useExisting: NewLogger},
-
-    // multi: Provide multiple values for the same token as an array
-    {provide: INTERCEPTOR_TOKEN, useClass: AuthInterceptor, multi: true},
-  ],
-})
-export class Example {}
-```
-
-## Scopes of Providers
-
-- **Application Bootstrap**: Global singletons. Use for HTTP clients, logging, or app-wide config.
-- **Component/Directive**: Isolated instances. Use for component-specific state or forms. Services are destroyed when the component is destroyed.
-- **Route**: Feature-specific services loaded only with specific routes.
-
-## Library Pattern: `provide*` functions
-
-Library authors should export functions that return provider arrays to encapsulate configuration:
-
-```ts
-export function provideAnalytics(config: AnalyticsConfig): Provider[] {
-  return [{provide: ANALYTICS_CONFIG, useValue: config}, AnalyticsService];
-}
-```

skills/angular-developer/references/di-fundamentals.md

@@ -1,120 +0,0 @@
-# Dependency Injection (DI) Fundamentals
-
-Dependency Injection (DI) is a design pattern used to organize and share code across an application by allowing you to "inject" features into different parts. This improves code maintainability, scalability, and testability.
-
-## How DI Works in Angular
-
-There are two primary ways code interacts with Angular's DI system:
-
-1. **Providing**: Making values (objects, functions, primitives) available to the DI system.
-2. **Injecting**: Asking the DI system for those values.
-
-Angular components, directives, and services automatically participate in DI.
-
-## Services
-
-A **service** is the most common way to share data and functionality across an application. It is a TypeScript class decorated with `@Injectable()`.
-
-### Creating a Service
-
-Use the `providedIn: 'root'` option in the `@Injectable` decorator to make the service a singleton available throughout the entire application. This is the recommended approach for most services.
-
-```ts
-import {Injectable} from '@angular/core';
-
-@Injectable({
-  providedIn: 'root', // Makes this a singleton available everywhere
-})
-export class AnalyticsLogger {
-  trackEvent(category: string, value: string) {
-    console.log('Analytics event logged:', {category, value});
-  }
-}
-```
-
-Common uses for services include:
-
-- Data clients (API calls)
-- State management
-- Authentication and authorization
-- Logging and error handling
-- Utility functions
-
-## Injecting Dependencies
-
-Use Angular's `inject()` function to request dependencies.
-
-### The `inject()` Function
-
-You can use the `inject()` function to get an instance of a service (or any other provided token).
-
-```ts
-import {Component, inject} from '@angular/core';
-import {Router} from '@angular/router';
-import {AnalyticsLogger} from './analytics-logger.service';
-
-@Component({
-  selector: 'app-navbar',
-  template: `<a href="#" (click)="navigateToDetail($event)">Detail Page</a>`,
-})
-export class Navbar {
-  // Injecting dependencies using class field initializers
-  private router = inject(Router);
-  private analytics = inject(AnalyticsLogger);
-
-  navigateToDetail(event: Event) {
-    event.preventDefault();
-    this.analytics.trackEvent('navigation', '/details');
-    this.router.navigate(['/details']);
-  }
-}
-```
-
-### Where can `inject()` be used? (Injection Context)
-
-You can call `inject()` in an **injection context**. The most common injection contexts are during the construction of a component, directive, or service.
-
-Valid places to call `inject()`:
-
-1. **Class field initializers** (Recommended)
-2. **Constructor body**
-3. **Route guards and resolvers** (which are executed in an injection context)
-4. **Factory functions** used in providers
-
-```typescript
-import {Component, Directive, Injectable, inject, ElementRef} from '@angular/core';
-import {HttpClient} from '@angular/common/http';
-
-// 1. In a Component (Field Initializer & Constructor)
-@Component({
-  /*...*/
-})
-export class Example {
-  private service1 = inject(MyService); // Valid field initializer
-
-  private service2: MyService;
-  constructor() {
-    this.service2 = inject(MyService); // Valid constructor body
-  }
-}
-
-// 2. In a Directive
-@Directive({
-  /*...*/
-})
-export class MyDirective {
-  private element = inject(ElementRef); // Valid field initializer
-}
-
-// 3. In a Service
-@Injectable({providedIn: 'root'})
-export class MyService {
-  private http = inject(HttpClient); // Valid field initializer
-}
-
-// 4. In a Route Guard (Functional)
-export const authGuard = () => {
-  const auth = inject(AuthService); // Valid route guard
-  return auth.isAuthenticated();
-};
-```

skills/angular-developer/references/e2e-testing.md

@@ -1,56 +0,0 @@
-# End-to-End (E2E) Testing
-
-Use E2E tests to cover critical user journeys in a real browser. Prefer the framework already configured in the Angular workspace, such as Cypress or Playwright.
-
-## Running E2E Tests
-
-Check `package.json` and `angular.json` for the project-specific command. Common patterns include:
-
-```shell
-npm run e2e
-pnpm e2e
-ng e2e
-```
-
-When the app must be built or served first, use the existing project scripts instead of inventing a parallel test entrypoint.
-
-## Test Structure
-
-- Keep E2E specs close to the configured test framework, such as `cypress/e2e/` or `e2e/`.
-- Put reusable login/setup helpers in the framework support directory.
-- Keep fixtures explicit and small enough that each test can explain the user state it depends on.
-
-### Cypress Example
-
-```typescript
-describe('Login flow', () => {
-  it('redirects to dashboard on valid credentials', () => {
-    cy.visit('/login');
-    cy.get('[data-cy=email]').type('user@example.com');
-    cy.get('[data-cy=password]').type('password123');
-    cy.get('[data-cy=submit]').click();
-    cy.url().should('include', '/dashboard');
-  });
-});
-```
-
-### Playwright Example
-
-```typescript
-import {expect, test} from '@playwright/test';
-
-test('redirects to dashboard on valid credentials', async ({page}) => {
-  await page.goto('/login');
-  await page.getByLabel('Email').fill('user@example.com');
-  await page.getByLabel('Password').fill('password123');
-  await page.getByRole('button', {name: 'Sign in'}).click();
-  await expect(page).toHaveURL(/dashboard/);
-});
-```
-
-## Best Practices
-
-- Prefer accessible locators (`getByRole`, `getByLabel`) or stable `data-*` attributes.
-- Avoid selectors that depend on CSS classes, DOM depth, or incidental text.
-- Wait for specific UI states, routes, or network responses instead of arbitrary sleeps.
-- Keep smoke tests short and reserve full workflow coverage for the highest-value paths.

skills/angular-developer/references/effects.md

@@ -1,83 +0,0 @@
-# Side Effects with `effect` and `afterRenderEffect`
-
-In Angular, an **effect** is an operation that runs whenever one or more signal values it tracks change.
-
-## When to use `effect`
-
-Effects are intended for syncing signal state to imperative, non-signal APIs.
-
-**Valid Use Cases:**
-
-- Logging analytics.
-- Syncing state to `localStorage` or `sessionStorage`.
-- Performing custom rendering to a `<canvas>` or 3rd-party charting library.
-
-**CRITICAL RULE: DO NOT use effects to propagate state.**
-If you find yourself using `.set()` or `.update()` on a signal _inside_ an effect to keep two signals in sync, you are making a mistake. This causes `ExpressionChangedAfterItHasBeenChecked` errors and infinite loops. **Always use `computed()` or `linkedSignal()` for state derivation.**
-
-## Basic Usage
-
-Effects execute asynchronously during the change detection process. They always run at least once.
-
-```ts
-import { Component, signal, effect } from '@angular/core';
-
-@Component({...})
-export class Example {
-  count = signal(0);
-
-  constructor() {
-    // Effect must be created in an injection context (e.g., a constructor)
-    effect((onCleanup) => {
-      console.log(`Count changed to ${this.count()}`);
-
-      const timer = setTimeout(() => console.log('Timer finished'), 1000);
-
-      // Cleanup function runs before the next execution, or when destroyed
-      onCleanup(() => clearTimeout(timer));
-    });
-  }
-}
-```
-
-## DOM Manipulation with `afterRenderEffect`
-
-Standard `effect` runs _before_ Angular updates the DOM. If you need to manually inspect or modify the DOM based on a signal change (e.g., integrating a 3rd party UI library), use `afterRenderEffect`.
-
-`afterRenderEffect` runs after Angular has finished rendering the DOM.
-
-### Render Phases
-
-To prevent reflows (forced layout thrashing), `afterRenderEffect` forces you to divide your DOM reads and writes into specific phases.
-
-```ts
-import { Component, afterRenderEffect, viewChild, ElementRef } from '@angular/core';
-
-@Component({...})
-export class Chart {
-  canvas = viewChild.required<ElementRef>('canvas');
-
-  constructor() {
-    afterRenderEffect({
-      // 1. Read from the DOM
-      earlyRead: () => {
-        return this.canvas().nativeElement.getBoundingClientRect().width;
-      },
-      // 2. Write to the DOM (receives the result of the previous phase)
-      write: (width) => {
-        // NEVER read from the DOM in the write phase.
-        setupChart(this.canvas().nativeElement, width);
-      }
-    });
-  }
-}
-```
-
-**Available Phases (executed in this order):**
-
-1. `earlyRead`
-2. `write` (Never read here)
-3. `mixedReadWrite` (Avoid if possible)
-4. `read` (Never write here)
-
-_Note: `afterRenderEffect` only runs on the client, never during Server-Side Rendering (SSR)._

skills/angular-developer/references/hierarchical-injectors.md

@@ -1,43 +0,0 @@
-# Hierarchical Injectors
-
-Angular's dependency injection system is hierarchical, meaning services can be scoped to different levels of the application.
-
-## Types of Injector Hierarchies
-
-1. **`EnvironmentInjector` Hierarchy**: Configured via `@Injectable({ providedIn: 'root' })` or `ApplicationConfig.providers` during bootstrap. These are global singletons.
-2. **`ElementInjector` Hierarchy**: Created implicitly at each DOM element. Configured via the `providers` or `viewProviders` array in `@Component()` or `@Directive()`.
-
-## Resolution Rules
-
-When a dependency is requested, Angular resolves it in two phases:
-
-1. It searches up the **`ElementInjector`** tree, starting from the requesting component/directive up to the root element.
-2. If not found, it searches the **`EnvironmentInjector`** tree, starting from the closest environment injector up to the root.
-3. If still not found, it throws an error (unless marked optional).
-
-## Resolution Modifiers
-
-You can alter how Angular searches for a dependency using the options object in `inject()`:
-
-- **`optional`**: If the dependency isn't found, return `null` instead of throwing an error.
-- **`self`**: Only check the current `ElementInjector`. Do not look up the parent tree.
-- **`skipSelf`**: Start searching in the parent `ElementInjector`, skipping the current element.
-- **`host`**: Stop searching when reaching the host component's view boundary.
-
-```ts
-@Component({...})
-export class Example {
-  // Returns null if not found instead of crashing
-  optionalService = inject(MyService, { optional: true });
-
-  // Skips this component's providers, looks at parent
-  parentService = inject(ParentService, { skipSelf: true });
-}
-```
-
-## `providers` vs `viewProviders`
-
-When providing a service at the component level:
-
-- **`providers`**: The service is available to the component, its view (template), and any **projected content** (`<ng-content>`).
-- **`viewProviders`**: The service is available to the component and its view, but **NOT** to projected content. Use this to isolate services from content passed in by consumers.

skills/angular-developer/references/host-elements.md

@@ -1,80 +0,0 @@
-# Component Host Elements
-
-The **host element** is the DOM element that matches a component's selector. The component's template renders inside this element.
-
-## Binding to the Host Element
-
-Use the `host` property in the `@Component` decorator to bind properties, attributes, styles, and events to the host element. This is the **preferred approach** over legacy decorators.
-
-```ts
-@Component({
-  selector: 'custom-slider',
-  host: {
-    'role': 'slider', // Static attribute
-    '[attr.aria-valuenow]': 'value', // Attribute binding
-    '[class.active]': 'isActive()', // Class binding
-    '[style.color]': 'color()', // Style binding
-    '[tabIndex]': 'disabled ? -1 : 0', // Property binding
-    '(keydown)': 'onKeyDown($event)', // Event binding
-  },
-})
-export class CustomSlider {
-  value = 0;
-  disabled = false;
-  isActive = signal(false);
-  color = signal('blue');
-
-  onKeyDown(event: KeyboardEvent) {
-    /* ... */
-  }
-}
-```
-
-## Legacy Decorators
-
-`@HostBinding` and `@HostListener` are supported for backwards compatibility but should be avoided in new code.
-
-```ts
-export class CustomSlider {
-  @HostBinding('tabIndex')
-  get tabIndex() {
-    return this.disabled ? -1 : 0;
-  }
-
-  @HostListener('keydown', ['$event'])
-  onKeyDown(event: KeyboardEvent) {
-    /* ... */
-  }
-}
-```
-
-## Binding Collisions
-
-If both the component (host binding) and the consumer (template binding) bind to the same property:
-
-1. **Static vs Static**: The instance (consumer) binding wins.
-2. **Static vs Dynamic**: The dynamic binding wins.
-3. **Dynamic vs Dynamic**: The component's host binding wins.
-
-## Injecting Host Attributes
-
-Use `HostAttributeToken` with the `inject` function to read static attributes from the host element at construction time.
-
-```ts
-import {Component, HostAttributeToken, inject} from '@angular/core';
-
-@Component({
-  selector: 'app-btn',
-  template: `<ng-content />`,
-})
-export class AppButton {
-  // Throws error if 'type' is missing unless injected with { optional: true }
-  type = inject(new HostAttributeToken('type'));
-}
-```
-
-Usage:
-
-```html
-<app-btn type="primary">Click Me</app-btn>
-```

skills/angular-developer/references/injection-context.md

@@ -1,63 +0,0 @@
-# Injection Context
-
-The `inject()` function can only be used when code is executing within an **injection context**.
-
-## Where is an Injection Context Available?
-
-An injection context is automatically available in:
-
-1. **Field initializers** of classes instantiated by DI (`@Injectable`, `@Component`, `@Directive`, `@Pipe`).
-2. **Constructors** of classes instantiated by DI.
-3. **Factory functions** specified in `useFactory` or `InjectionToken` configurations.
-4. **Functional APIs** executed by Angular (e.g., functional route guards, resolvers, interceptors).
-
-```ts
-@Component({...})
-export class Example {
-  // Valid: Field initializer
-  private router = inject(Router);
-
-  constructor() {
-    // Valid: Constructor
-    const http = inject(HttpClient);
-  }
-
-  onClick() {
-    // Invalid: Not an injection context
-    // const auth = inject(AuthService);
-  }
-}
-```
-
-## `runInInjectionContext`
-
-If you need to run a function within an injection context (often needed for dynamic component creation or testing), use `runInInjectionContext`. This requires access to an existing injector (like `EnvironmentInjector` or `Injector`).
-
-```ts
-import {Injectable, inject, EnvironmentInjector, runInInjectionContext} from '@angular/core';
-
-@Injectable({providedIn: 'root'})
-export class MyService {
-  private injector = inject(EnvironmentInjector);
-
-  doSomethingDynamic() {
-    runInInjectionContext(this.injector, () => {
-      // Now valid to use inject() here
-      const router = inject(Router);
-    });
-  }
-}
-```
-
-## `assertInInjectionContext`
-
-Use `assertInInjectionContext` in utility functions to guarantee they are called from a valid context. It throws a clear error if not.
-
-```ts
-import {assertInInjectionContext, inject, ElementRef} from '@angular/core';
-
-export function injectNativeElement<T extends Element>(): T {
-  assertInInjectionContext(injectNativeElement);
-  return inject(ElementRef).nativeElement;
-}
-```

skills/angular-developer/references/inputs.md

@@ -1,101 +0,0 @@
-# Inputs
-
-Inputs allow data to flow from a parent component to a child component. Angular recommends using the signal-based `input` API for modern applications.
-
-## Signal-based Inputs
-
-Declare inputs using the `input()` function. This returns an `InputSignal`.
-
-```ts
-import {Component, input, computed} from '@angular/core';
-
-@Component({
-  selector: 'app-user',
-  template: `<p>User: {{ name() }} ({{ age() }})</p>`,
-})
-export class User {
-  // Optional input with default value
-  name = input('Guest');
-
-  // Required input
-  age = input.required<number>();
-
-  // Inputs are reactive signals
-  label = computed(() => `Name: ${this.name()}`);
-}
-```
-
-### Usage in Template
-
-```html
-<app-user [name]="userName" [age]="25" />
-```
-
-## Configuration Options
-
-The `input` function accepts a config object:
-
-- **Alias**: Change the property name used in templates.
-- **Transform**: Modify the value before it reaches the component.
-
-```ts
-import { input, booleanAttribute } from '@angular/core';
-
-@Component({...})
-export class CustomButton {
-  // Alias example
-  label = input('', { alias: 'btnLabel' });
-
-  // Transform example using built-in helper
-  disabled = input(false, { transform: booleanAttribute });
-}
-```
-
-## Model Inputs (Two-Way Binding)
-
-Use `model()` to create an input that supports two-way data binding.
-
-```ts
-@Component({
-  selector: 'custom-counter',
-  template: `<button (click)="increment()">+</button>`,
-})
-export class CustomCounter {
-  value = model(0);
-
-  increment() {
-    this.value.update((v) => v + 1);
-  }
-}
-```
-
-### Usage
-
-```html
-<!-- Two-way binding with a signal -->
-<custom-counter [(value)]="mySignal" />
-
-<!-- Two-way binding with a plain property -->
-<custom-counter [(value)]="myProperty" />
-```
-
-## Decorator-based Inputs (@Input)
-
-The legacy API remains supported but is not recommended for new code.
-
-```ts
-import { Component, Input } from '@angular/core';
-
-@Component({...})
-export class Legacy {
-  @Input({ required: true }) value = 0;
-  @Input({ transform: trimString }) label = '';
-}
-```
-
-## Best Practices
-
-- **Prefer Signals**: Use `input()` instead of `@Input()` for better reactivity and type safety.
-- **Required Inputs**: Use `input.required()` for mandatory data to get build-time errors.
-- **Pure Transforms**: Ensure input transform functions are pure and statically analyzable.
-- **Avoid Collisions**: Do not use input names that collide with standard DOM properties (e.g., `id`, `title`).

skills/angular-developer/references/linked-signal.md

@@ -1,59 +0,0 @@
-# Dependent State with `linkedSignal`
-
-The `linkedSignal` function lets you create writable state that is intrinsically linked to some other state. It is perfect for state that needs a default value derived from an input or another signal, but can still be independently modified by the user.
-
-If the source state changes, the `linkedSignal` resets to a new computed value.
-
-## Basic Usage
-
-When you only need to recompute based on a source, pass a computation function. `linkedSignal` works like `computed`, but the resulting signal is writable (you can call `.set()` or `.update()` on it).
-
-```ts
-import { Component, signal, linkedSignal } from '@angular/core';
-
-@Component({...})
-export class ShippingMethodPicker {
-  shippingOptions = signal(['Ground', 'Air', 'Sea']);
-
-  // Defaults to the first option.
-  // If shippingOptions changes, selectedOption resets to the new first option.
-  selectedOption = linkedSignal(() => this.shippingOptions()[0]);
-
-  changeShipping(index: number) {
-    // We can still manually update this signal!
-    this.selectedOption.set(this.shippingOptions()[index]);
-  }
-}
-```
-
-## Advanced Usage: Accounting for Previous State
-
-Sometimes, when the source state changes, you want to preserve the user's manual selection if it is still valid. To do this, use the object syntax providing `source` and `computation`.
-
-The `computation` function receives the new value of the source, and a `previous` object containing the previous source value and the previous `linkedSignal` value.
-
-```ts
-interface ShippingMethod { id: number; name: string; }
-
-@Component({...})
-export class ShippingMethodPicker {
-  shippingOptions = signal<ShippingMethod[]>([
-    {id: 0, name: 'Ground'}, {id: 1, name: 'Air'}, {id: 2, name: 'Sea'}
-  ]);
-
-  selectedOption = linkedSignal<ShippingMethod[], ShippingMethod>({
-    source: this.shippingOptions,
-    computation: (newOptions, previous) => {
-      // If the newly loaded options still contain the user's previously
-      // selected option, keep it selected. Otherwise, reset to the first option.
-      return newOptions.find(opt => opt.id === previous?.value.id) ?? newOptions[0];
-    }
-  });
-}
-```
-
-### When to use `linkedSignal` vs `computed` vs `effect`
-
-- Use `computed`: When state is **strictly** derived from other state and should never be manually updated.
-- Use `linkedSignal`: When state is derived from other state, but the user **must** be able to override or manually update it.
-- **Never** use `effect` to sync one piece of state to another. That is an anti-pattern. Use `computed` or `linkedSignal` instead.

skills/angular-developer/references/loading-strategies.md

@@ -1,61 +0,0 @@
-# Route Loading Strategies
-
-Angular supports two main strategies for loading routes and components to balance initial load time and navigation responsiveness.
-
-## Eager Loading
-
-Components are bundled into the initial JavaScript payload and are available immediately.
-
-```ts
-{ path: 'home', component: Home }
-```
-
-- **Pros**: Seamless transitions.
-- **Cons**: Increases initial bundle size.
-
-## Lazy Loading
-
-Components or routes are loaded only when the user navigates to them. This creates separate JavaScript "chunks".
-
-### Lazy Loading Components
-
-Use `loadComponent` to fetch the component on demand.
-
-```ts
-{
-  path: 'admin',
-  loadComponent: () => import('./admin/admin.component').then(m => m.AdminComponent)`,
-}
-```
-
-### Lazy Loading Child Routes
-
-Use `loadChildren` to fetch a set of routes.
-
-```ts
-{
-  path: 'settings',
-  loadChildren: () => import('./settings/settings.routes'),
-}
-```
-
-## Injection Context and Lazy Loading
-
-Loader functions run within the **injection context** of the current route. This allows you to call `inject()` to make context-aware loading decisions.
-
-```ts
-{
-  path: 'dashboard',
-  loadComponent: () => {
-    const flags = inject(FeatureFlags);
-    return flags.isPremium
-      ? import('./premium-dashboard')
-      : import('./basic-dashboard');
-  },
-}
-```
-
-## Recommendation
-
-- Use **Eager Loading** for the primary landing pages.
-- Use **Lazy Loading** for all other feature areas to keep the initial bundle small.

skills/angular-developer/references/mcp.md

@@ -1,108 +0,0 @@
-# Angular CLI MCP Server
-
-The Angular CLI includes a Model Context Protocol (MCP) server that enables AI assistants (like Cursor, Gemini CLI, JetBrains AI, etc.) to interact directly with the Angular CLI. It provides tools for code generation, modernizing code, fetching examples, and running builds/tests.
-
-## Available Tools (Default)
-
-When the MCP server is enabled, AI agents have access to the following tools:
-
-| Name                        | Description                                                                                               |
-| :-------------------------- | :-------------------------------------------------------------------------------------------------------- |
-| `ai_tutor`                  | Launches an interactive AI-powered Angular tutor.                                                         |
-| `find_examples`             | Finds authoritative, best-practice code examples for modern Angular features.                             |
-| `get_best_practices`        | Retrieves the Angular Best Practices Guide (crucial for standalone components, typed forms, etc.).        |
-| `list_projects`             | Lists all applications and libraries in the workspace by reading `angular.json`.                          |
-| `onpush_zoneless_migration` | Analyzes code and provides a plan to migrate it to `OnPush` change detection (prerequisite for zoneless). |
-| `search_documentation`      | Searches the official documentation at `https://angular.dev`.                                             |
-
-## Experimental Tools
-
-Some tools must be enabled explicitly using the `--experimental-tool` (or `-E`) flag.
-
-| Name                       | Description                                                              |
-| :------------------------- | :----------------------------------------------------------------------- |
-| `build`                    | Performs a one-off build using `ng build`.                               |
-| `devserver.start`          | Asynchronously starts a dev server (`ng serve`). Returns immediately.    |
-| `devserver.stop`           | Stops the dev server.                                                    |
-| `devserver.wait_for_build` | Returns the logs of the most recent build in a running dev server.       |
-| `e2e`                      | Executes end-to-end tests.                                               |
-| `modernize`                | Performs code migrations to align with latest best practices and syntax. |
-| `test`                     | Runs the project's unit tests.                                           |
-
-## Configuration
-
-To use the MCP server, you configure your host environment (IDE or CLI) to run `npx @angular/cli mcp`.
-
-### Antigravity IDE
-
-Create a file named `.antigravity/mcp.json` in your project's root:
-
-```json
-{
-  "mcpServers": {
-    "angular-cli": {
-      "command": "npx",
-      "args": ["-y", "@angular/cli", "mcp"]
-    }
-  }
-}
-```
-
-### Gemini CLI
-
-Create `.gemini/settings.json` in the project root:
-
-```json
-{
-  "mcpServers": {
-    "angular-cli": {
-      "command": "npx",
-      "args": ["-y", "@angular/cli", "mcp"]
-    }
-  }
-}
-```
-
-### Cursor
-
-Create `.cursor/mcp.json` in the project root (or globally at `~/.cursor/mcp.json`):
-
-```json
-{
-  "mcpServers": {
-    "angular-cli": {
-      "command": "npx",
-      "args": ["-y", "@angular/cli", "mcp"]
-    }
-  }
-}
-```
-
-### VS Code
-
-Create `.vscode/mcp.json`:
-
-```json
-{
-  "servers": {
-    "angular-cli": {
-      "command": "npx",
-      "args": ["-y", "@angular/cli", "mcp"]
-    }
-  }
-}
-```
-
-## Command Options
-
-You can pass arguments to the MCP server in the `args` array of your configuration:
-
-- `--read-only`: Only registers tools that do not modify the project.
-- `--local-only`: Only registers tools that do not require an internet connection.
-- `--experimental-tool` (`-E`): Enables specific experimental tools (e.g., `-E build`, `-E devserver`).
-
-Example for read-only mode with experimental tools enabled:
-
-```json
-"args": ["-y", "@angular/cli", "mcp", "--read-only", "-E", "build", "-E", "modernize"]
-```