test: cover mcp health edge paths

fix: retry observer wait after SIGUSR1

.agents/plugins/marketplace.json

@@ -1,11 +1,12 @@
 {
-  "name": "everything-claude-code",
+  "name": "ecc",
   "interface": {
     "displayName": "Everything Claude Code"
   },
   "plugins": [
     {
-      "name": "everything-claude-code",
+      "name": "ecc",
+      "version": "2.0.0-rc.1",
       "source": {
         "source": "local",
         "path": "../.."

.agents/skills/agent-introspection-debugging/SKILL.md

@@ -0,0 +1,152 @@
+---
+name: agent-introspection-debugging
+description: Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
+---
+
+# Agent Introspection Debugging
+
+Use this skill when an agent run is failing repeatedly, consuming tokens without progress, looping on the same tools, or drifting away from the intended task.
+
+This is a workflow skill, not a hidden runtime. It teaches the agent to debug itself systematically before escalating to a human.
+
+## When to Activate
+
+- Maximum tool call / loop-limit failures
+- Repeated retries with no forward progress
+- Context growth or prompt drift that starts degrading output quality
+- File-system or environment state mismatch between expectation and reality
+- Tool failures that are likely recoverable with diagnosis and a smaller corrective action
+
+## Scope Boundaries
+
+Activate this skill for:
+- capturing failure state before retrying blindly
+- diagnosing common agent-specific failure patterns
+- applying contained recovery actions
+- producing a structured human-readable debug report
+
+Do not use this skill as the primary source for:
+- feature verification after code changes; use `verification-loop`
+- framework-specific debugging when a narrower ECC skill already exists
+- runtime promises the current harness cannot enforce automatically
+
+## Four-Phase Loop
+
+### Phase 1: Failure Capture
+
+Before trying to recover, record the failure precisely.
+
+Capture:
+- error type, message, and stack trace when available
+- last meaningful tool call sequence
+- what the agent was trying to do
+- current context pressure: repeated prompts, oversized pasted logs, duplicated plans, or runaway notes
+- current environment assumptions: cwd, branch, relevant service state, expected files
+
+Minimum capture template:
+
+```markdown
+## Failure Capture
+- Session / task:
+- Goal in progress:
+- Error:
+- Last successful step:
+- Last failed tool / command:
+- Repeated pattern seen:
+- Environment assumptions to verify:
+```
+
+### Phase 2: Root-Cause Diagnosis
+
+Match the failure to a known pattern before changing anything.
+
+| Pattern | Likely Cause | Check |
+| --- | --- | --- |
+| Maximum tool calls / repeated same command | loop or no-exit observer path | inspect the last N tool calls for repetition |
+| Context overflow / degraded reasoning | unbounded notes, repeated plans, oversized logs | inspect recent context for duplication and low-signal bulk |
+| `ECONNREFUSED` / timeout | service unavailable or wrong port | verify service health, URL, and port assumptions |
+| `429` / quota exhaustion | retry storm or missing backoff | count repeated calls and inspect retry spacing |
+| file missing after write / stale diff | race, wrong cwd, or branch drift | re-check path, cwd, git status, and actual file existence |
+| tests still failing after “fix” | wrong hypothesis | isolate the exact failing test and re-derive the bug |
+
+Diagnosis questions:
+- is this a logic failure, state failure, environment failure, or policy failure?
+- did the agent lose the real objective and start optimizing the wrong subtask?
+- is the failure deterministic or transient?
+- what is the smallest reversible action that would validate the diagnosis?
+
+### Phase 3: Contained Recovery
+
+Recover with the smallest action that changes the diagnosis surface.
+
+Safe recovery actions:
+- stop repeated retries and restate the hypothesis
+- trim low-signal context and keep only the active goal, blockers, and evidence
+- re-check the actual filesystem / branch / process state
+- narrow the task to one failing command, one file, or one test
+- switch from speculative reasoning to direct observation
+- escalate to a human when the failure is high-risk or externally blocked
+
+Do not claim unsupported auto-healing actions like “reset agent state” or “update harness config” unless you are actually doing them through real tools in the current environment.
+
+Contained recovery checklist:
+
+```markdown
+## Recovery Action
+- Diagnosis chosen:
+- Smallest action taken:
+- Why this is safe:
+- What evidence would prove the fix worked:
+```
+
+### Phase 4: Introspection Report
+
+End with a report that makes the recovery legible to the next agent or human.
+
+```markdown
+## Agent Self-Debug Report
+- Session / task:
+- Failure:
+- Root cause:
+- Recovery action:
+- Result: success | partial | blocked
+- Token / time burn risk:
+- Follow-up needed:
+- Preventive change to encode later:
+```
+
+## Recovery Heuristics
+
+Prefer these interventions in order:
+
+1. Restate the real objective in one sentence.
+2. Verify the world state instead of trusting memory.
+3. Shrink the failing scope.
+4. Run one discriminating check.
+5. Only then retry.
+
+Bad pattern:
+- retrying the same action three times with slightly different wording
+
+Good pattern:
+- capture failure
+- classify the pattern
+- run one direct check
+- change the plan only if the check supports it
+
+## Integration with ECC
+
+- Use `verification-loop` after recovery if code was changed.
+- Use `continuous-learning-v2` when the failure pattern is worth turning into an instinct or later skill.
+- Use `council` when the issue is not technical failure but decision ambiguity.
+- Use `workspace-surface-audit` if the failure came from conflicting local state or repo drift.
+
+## Output Standard
+
+When this skill is active, do not end with “I fixed it” alone.
+
+Always provide:
+- the failure pattern
+- the root-cause hypothesis
+- the recovery action
+- the evidence that the situation is now better or still blocked

.agents/skills/agent-introspection-debugging/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Agent Introspection Debugging"
+  short_description: "Structured self-debugging for AI agent failures"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $agent-introspection-debugging to diagnose and recover from an AI agent failure."
+policy:
+  allow_implicit_invocation: true

.agents/skills/agent-sort/SKILL.md

@@ -0,0 +1,214 @@
+---
+name: agent-sort
+description: Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
+---
+
+# Agent Sort
+
+Use this skill when a repo needs a project-specific ECC surface instead of the default full install.
+
+The goal is not to guess what "feels useful." The goal is to classify ECC components with evidence from the actual codebase.
+
+## When to Use
+
+- A project only needs a subset of ECC and full installs are too noisy
+- The repo stack is clear, but nobody wants to hand-curate skills one by one
+- A team wants a repeatable install decision backed by grep evidence instead of opinion
+- You need to separate always-loaded daily workflow surfaces from searchable library/reference surfaces
+- A repo has drifted into the wrong language, rule, or hook set and needs cleanup
+
+## Non-Negotiable Rules
+
+- Use the current repository as the source of truth, not generic preferences
+- Every DAILY decision must cite concrete repo evidence
+- LIBRARY does not mean "delete"; it means "keep accessible without loading by default"
+- Do not install hooks, rules, or scripts that the current repo cannot use
+- Prefer ECC-native surfaces; do not introduce a second install system
+
+## Outputs
+
+Produce these artifacts in order:
+
+1. DAILY inventory
+2. LIBRARY inventory
+3. install plan
+4. verification report
+5. optional `skill-library` router if the project wants one
+
+## Classification Model
+
+Use two buckets only:
+
+- `DAILY`
+  - should load every session for this repo
+  - strongly matched to the repo's language, framework, workflow, or operator surface
+- `LIBRARY`
+  - useful to retain, but not worth loading by default
+  - should remain reachable through search, router skill, or selective manual use
+
+## Evidence Sources
+
+Use repo-local evidence before making any classification:
+
+- file extensions
+- package managers and lockfiles
+- framework configs
+- CI and hook configs
+- build/test scripts
+- imports and dependency manifests
+- repo docs that explicitly describe the stack
+
+Useful commands include:
+
+```bash
+rg --files
+rg -n "typescript|react|next|supabase|django|spring|flutter|swift"
+cat package.json
+cat pyproject.toml
+cat Cargo.toml
+cat pubspec.yaml
+cat go.mod
+```
+
+## Parallel Review Passes
+
+If parallel subagents are available, split the review into these passes:
+
+1. Agents
+   - classify `agents/*`
+2. Skills
+   - classify `skills/*`
+3. Commands
+   - classify `commands/*`
+4. Rules
+   - classify `rules/*`
+5. Hooks and scripts
+   - classify hook surfaces, MCP health checks, helper scripts, and OS compatibility
+6. Extras
+   - classify contexts, examples, MCP configs, templates, and guidance docs
+
+If subagents are not available, run the same passes sequentially.
+
+## Core Workflow
+
+### 1. Read the repo
+
+Establish the real stack before classifying anything:
+
+- languages in use
+- frameworks in use
+- primary package manager
+- test stack
+- lint/format stack
+- deployment/runtime surface
+- operator integrations already present
+
+### 2. Build the evidence table
+
+For every candidate surface, record:
+
+- component path
+- component type
+- proposed bucket
+- repo evidence
+- short justification
+
+Use this format:
+
+```text
+skills/frontend-patterns | skill | DAILY | 84 .tsx files, next.config.ts present | core frontend stack
+skills/django-patterns   | skill | LIBRARY | no .py files, no pyproject.toml       | not active in this repo
+rules/typescript/*       | rules | DAILY | package.json + tsconfig.json            | active TS repo
+rules/python/*           | rules | LIBRARY | zero Python source files             | keep accessible only
+```
+
+### 3. Decide DAILY vs LIBRARY
+
+Promote to `DAILY` when:
+
+- the repo clearly uses the matching stack
+- the component is general enough to help every session
+- the repo already depends on the corresponding runtime or workflow
+
+Demote to `LIBRARY` when:
+
+- the component is off-stack
+- the repo might need it later, but not every day
+- it adds context overhead without immediate relevance
+
+### 4. Build the install plan
+
+Translate the classification into action:
+
+- DAILY skills -> install or keep in `.claude/skills/`
+- DAILY commands -> keep as explicit shims only if still useful
+- DAILY rules -> install only matching language sets
+- DAILY hooks/scripts -> keep only compatible ones
+- LIBRARY surfaces -> keep accessible through search or `skill-library`
+
+If the repo already uses selective installs, update that plan instead of creating another system.
+
+### 5. Create the optional library router
+
+If the project wants a searchable library surface, create:
+
+- `.claude/skills/skill-library/SKILL.md`
+
+That router should contain:
+
+- a short explanation of DAILY vs LIBRARY
+- grouped trigger keywords
+- where the library references live
+
+Do not duplicate every skill body inside the router.
+
+### 6. Verify the result
+
+After the plan is applied, verify:
+
+- every DAILY file exists where expected
+- stale language rules were not left active
+- incompatible hooks were not installed
+- the resulting install actually matches the repo stack
+
+Return a compact report with:
+
+- DAILY count
+- LIBRARY count
+- removed stale surfaces
+- open questions
+
+## Handoffs
+
+If the next step is interactive installation or repair, hand off to:
+
+- `configure-ecc`
+
+If the next step is overlap cleanup or catalog review, hand off to:
+
+- `skill-stocktake`
+
+If the next step is broader context trimming, hand off to:
+
+- `strategic-compact`
+
+## Output Format
+
+Return the result in this order:
+
+```text
+STACK
+- language/framework/runtime summary
+
+DAILY
+- always-loaded items with evidence
+
+LIBRARY
+- searchable/reference items with evidence
+
+INSTALL PLAN
+- what should be installed, removed, or routed
+
+VERIFICATION
+- checks run and remaining gaps
+```

.agents/skills/agent-sort/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Agent Sort"
+  short_description: "Evidence-backed ECC install planning"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $agent-sort to build an evidence-backed ECC install plan."
+policy:
+  allow_implicit_invocation: true

.agents/skills/api-design/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: api-design
 description: REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
-origin: ECC
 ---
 
 # API Design Patterns

.agents/skills/api-design/agents/openai.yaml

@@ -2,6 +2,6 @@ interface:
   display_name: "API Design"
   short_description: "REST API design patterns and best practices"
   brand_color: "#F97316"
-  default_prompt: "Design REST API: resources, status codes, pagination"
+  default_prompt: "Use $api-design to design production REST API resources and responses."
 policy:
   allow_implicit_invocation: true

.agents/skills/article-writing/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: article-writing
 description: Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
-origin: ECC
 ---
 
 # Article Writing
 
-Write long-form content that sounds like a real person or brand, not generic AI output.
+Write long-form content that sounds like an actual person with a point of view, not an LLM smoothing itself into paste.
 
 ## When to Activate
 
@@ -17,69 +16,63 @@ Write long-form content that sounds like a real person or brand, not generic AI
 
 ## Core Rules
 
-1. Lead with the concrete thing: example, output, anecdote, number, screenshot description, or code block.
+1. Lead with the concrete thing: artifact, example, output, anecdote, number, screenshot, or code.
 2. Explain after the example, not before.
-3. Prefer short, direct sentences over padded ones.
-4. Use specific numbers when available and sourced.
-5. Never invent biographical facts, company metrics, or customer evidence.
+3. Keep sentences tight unless the source voice is intentionally expansive.
+4. Use proof instead of adjectives.
+5. Never invent facts, credibility, or customer evidence.
 
-## Voice Capture Workflow
+## Voice Handling
 
-If the user wants a specific voice, collect one or more of:
-- published articles
-- newsletters
-- X / LinkedIn posts
-- docs or memos
-- a short style guide
+If the user wants a specific voice, run `brand-voice` first and reuse its `VOICE PROFILE`.
+Do not duplicate a second style-analysis pass here unless the user explicitly asks for one.
 
-Then extract:
-- sentence length and rhythm
-- whether the voice is formal, conversational, or sharp
-- favored rhetorical devices such as parentheses, lists, fragments, or questions
-- tolerance for humor, opinion, and contrarian framing
-- formatting habits such as headers, bullets, code blocks, and pull quotes
-
-If no voice references are given, default to a direct, operator-style voice: concrete, practical, and low on hype.
+If no voice references are given, default to a sharp operator voice: concrete, unsentimental, useful.
 
 ## Banned Patterns
 
 Delete and rewrite any of these:
-- generic openings like "In today's rapidly evolving landscape"
-- filler transitions such as "Moreover" and "Furthermore"
-- hype phrases like "game-changer", "cutting-edge", or "revolutionary"
-- vague claims without evidence
-- biography or credibility claims not backed by provided context
+- "In today's rapidly evolving landscape"
+- "game-changer", "cutting-edge", "revolutionary"
+- "here's why this matters" as a standalone bridge
+- fake vulnerability arcs
+- a closing question added only to juice engagement
+- biography padding that does not move the argument
+- generic AI throat-clearing that delays the point
 
 ## Writing Process
 
 1. Clarify the audience and purpose.
-2. Build a skeletal outline with one purpose per section.
-3. Start each section with evidence, example, or scene.
-4. Expand only where the next sentence earns its place.
-5. Remove anything that sounds templated or self-congratulatory.
+2. Build a hard outline with one job per section.
+3. Start sections with proof, artifact, conflict, or example.
+4. Expand only where the next sentence earns space.
+5. Cut anything that sounds templated, overexplained, or self-congratulatory.
 
 ## Structure Guidance
 
 ### Technical Guides
-- open with what the reader gets
-- use code or terminal examples in every major section
-- end with concrete takeaways, not a soft summary
 
-### Essays / Opinion Pieces
-- start with tension, contradiction, or a sharp observation
+- open with what the reader gets
+- use code, commands, screenshots, or concrete output in major sections
+- end with actionable takeaways, not a soft recap
+
+### Essays / Opinion
+
+- start with tension, contradiction, or a specific observation
 - keep one argument thread per section
-- use examples that earn the opinion
+- make opinions answer to evidence
 
 ### Newsletters
-- keep the first screen strong
-- mix insight with updates, not diary filler
-- use clear section labels and easy skim structure
+
+- keep the first screen doing real work
+- do not front-load diary filler
+- use section labels only when they improve scanability
 
 ## Quality Gate
 
 Before delivering:
-- verify factual claims against provided sources
-- remove filler and corporate language
-- confirm the voice matches the supplied examples
-- ensure every section adds new information
-- check formatting for the intended platform
+- factual claims are backed by provided sources
+- generic AI transitions are gone
+- the voice matches the supplied examples or the agreed `VOICE PROFILE`
+- every section adds something new
+- formatting matches the intended medium

.agents/skills/article-writing/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Article Writing"
-  short_description: "Write long-form content in a supplied voice without sounding templated"
+  short_description: "Long-form content in a supplied voice"
   brand_color: "#B45309"
-  default_prompt: "Draft a sharp long-form article from these notes and examples"
+  default_prompt: "Use $article-writing to draft polished long-form content in the supplied voice."
 policy:
   allow_implicit_invocation: true

.agents/skills/backend-patterns/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: backend-patterns
 description: Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
-origin: ECC
 ---
 
 # Backend Development Patterns

.agents/skills/backend-patterns/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Backend Patterns"
-  short_description: "API design, database, and server-side patterns"
+  short_description: "API, database, and server-side patterns"
   brand_color: "#F59E0B"
-  default_prompt: "Apply backend patterns: API design, repository, caching"
+  default_prompt: "Use $backend-patterns to apply backend architecture and API patterns."
 policy:
   allow_implicit_invocation: true

.agents/skills/brand-voice/SKILL.md

@@ -0,0 +1,96 @@
+---
+name: brand-voice
+description: Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
+---
+
+# Brand Voice
+
+Build a durable voice profile from real source material, then use that profile everywhere instead of re-deriving style from scratch or defaulting to generic AI copy.
+
+## When to Activate
+
+- the user wants content or outreach in a specific voice
+- writing for X, LinkedIn, email, launch posts, threads, or product updates
+- adapting a known author's tone across channels
+- the existing content lane needs a reusable style system instead of one-off mimicry
+
+## Source Priority
+
+Use the strongest real source set available, in this order:
+
+1. recent original X posts and threads
+2. articles, essays, memos, launch notes, or newsletters
+3. real outbound emails or DMs that worked
+4. product docs, changelogs, README framing, and site copy
+
+Do not use generic platform exemplars as source material.
+
+## Collection Workflow
+
+1. Gather 5 to 20 representative samples when available.
+2. Prefer recent material over old material unless the user says the older writing is more canonical.
+3. Separate "public launch voice" from "private working voice" if the source set clearly splits.
+4. If live X access is available, use `x-api` to pull recent original posts before drafting.
+5. If site copy matters, include the current ECC landing page and repo/plugin framing.
+
+## What to Extract
+
+- rhythm and sentence length
+- compression vs explanation
+- capitalization norms
+- parenthetical use
+- question frequency and purpose
+- how sharply claims are made
+- how often numbers, mechanisms, or receipts show up
+- how transitions work
+- what the author never does
+
+## Output Contract
+
+Produce a reusable `VOICE PROFILE` block that downstream skills can consume directly. Use the schema in [references/voice-profile-schema.md](references/voice-profile-schema.md).
+
+Keep the profile structured and short enough to reuse in session context. The point is not literary criticism. The point is operational reuse.
+
+## Affaan / ECC Defaults
+
+If the user wants Affaan / ECC voice and live sources are thin, start here unless newer source material overrides it:
+
+- direct, compressed, concrete
+- specifics, mechanisms, receipts, and numbers beat adjectives
+- parentheticals are for qualification, narrowing, or over-clarification
+- capitalization is conventional unless there is a real reason to break it
+- questions are rare and should not be used as bait
+- tone can be sharp, blunt, skeptical, or dry
+- transitions should feel earned, not smoothed over
+
+## Hard Bans
+
+Delete and rewrite any of these:
+
+- fake curiosity hooks
+- "not X, just Y"
+- "no fluff"
+- forced lowercase
+- LinkedIn thought-leader cadence
+- bait questions
+- "Excited to share"
+- generic founder-journey filler
+- corny parentheticals
+
+## Persistence Rules
+
+- Reuse the latest confirmed `VOICE PROFILE` across related tasks in the same session.
+- If the user asks for a durable artifact, save the profile in the requested workspace location or memory surface.
+- Do not create repo-tracked files that store personal voice fingerprints unless the user explicitly asks for that.
+
+## Downstream Use
+
+Use this skill before or inside:
+
+- `content-engine`
+- `crosspost`
+- `lead-intelligence`
+- article or launch writing
+- cold or warm outbound across X, LinkedIn, and email
+
+If another skill already has a partial voice capture section, this skill is the canonical source of truth.

.agents/skills/brand-voice/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Brand Voice"
+  short_description: "Source-derived writing style profiles"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $brand-voice to derive and reuse a source-grounded writing style."
+policy:
+  allow_implicit_invocation: true

.agents/skills/brand-voice/references/voice-profile-schema.md

@@ -0,0 +1,55 @@
+# Voice Profile Schema
+
+Use this exact structure when building a reusable voice profile:
+
+```text
+VOICE PROFILE
+=============
+Author:
+Goal:
+Confidence:
+
+Source Set
+- source 1
+- source 2
+- source 3
+
+Rhythm
+- short note on sentence length, pacing, and fragmentation
+
+Compression
+- how dense or explanatory the writing is
+
+Capitalization
+- conventional, mixed, or situational
+
+Parentheticals
+- how they are used and how they are not used
+
+Question Use
+- rare, frequent, rhetorical, direct, or mostly absent
+
+Claim Style
+- how claims are framed, supported, and sharpened
+
+Preferred Moves
+- concrete moves the author does use
+
+Banned Moves
+- specific patterns the author does not use
+
+CTA Rules
+- how, when, or whether to close with asks
+
+Channel Notes
+- X:
+- LinkedIn:
+- Email:
+```
+
+Guidelines:
+
+- Keep the profile concrete and source-backed.
+- Use short bullets, not essay paragraphs.
+- Every banned move should be observable in the source set or explicitly requested by the user.
+- If the source set conflicts, call out the split instead of averaging it into mush.

.agents/skills/bun-runtime/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: bun-runtime
 description: Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
-origin: ECC
 ---
 
 # Bun Runtime

.agents/skills/bun-runtime/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Bun Runtime"
-  short_description: "Bun as runtime, package manager, bundler, and test runner"
+  short_description: "Bun runtime, package manager, and test runner"
   brand_color: "#FBF0DF"
-  default_prompt: "Use Bun for scripts, install, or run"
+  default_prompt: "Use $bun-runtime to choose and apply Bun runtime workflows."
 policy:
   allow_implicit_invocation: true

.agents/skills/claude-api/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: claude-api
 description: Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
-origin: ECC
 ---
 
 # Claude API

.agents/skills/claude-api/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Claude API"
-  short_description: "Anthropic Claude API patterns and SDKs"
+  short_description: "Claude API patterns for Python and TypeScript"
   brand_color: "#D97706"
-  default_prompt: "Build applications with the Claude API using Messages, tool use, streaming, and Agent SDK"
+  default_prompt: "Use $claude-api to build with Claude API and Anthropic SDK patterns."
 policy:
   allow_implicit_invocation: true

.agents/skills/coding-standards/SKILL.md

@@ -1,12 +1,17 @@
 ---
 name: coding-standards
-description: Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
-origin: ECC
+description: Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
 ---
 
 # Coding Standards & Best Practices
 
-Universal coding standards applicable across all projects.
+Baseline coding conventions applicable across projects.
+
+This skill is the shared floor, not the detailed framework playbook.
+
+- Use `frontend-patterns` for React, state, forms, rendering, and UI architecture.
+- Use `backend-patterns` or `api-design` for repository/service layers, endpoint design, validation, and server-specific concerns.
+- Use `rules/common/coding-style.md` when you need the shortest reusable rule layer instead of a full skill walkthrough.
 
 ## When to Activate
 
@@ -17,6 +22,19 @@ Universal coding standards applicable across all projects.
 - Setting up linting, formatting, or type-checking rules
 - Onboarding new contributors to coding conventions
 
+## Scope Boundaries
+
+Activate this skill for:
+- descriptive naming
+- immutability defaults
+- readability, KISS, DRY, and YAGNI enforcement
+- error-handling expectations and code-smell review
+
+Do not use this skill as the primary source for:
+- React composition, hooks, or rendering patterns
+- backend architecture, API design, or database layering
+- domain-specific framework guidance when a narrower ECC skill already exists
+
 ## Code Quality Principles
 
 ### 1. Readability First

.agents/skills/coding-standards/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Coding Standards"
-  short_description: "Universal coding standards and best practices"
+  short_description: "Cross-project coding conventions and review"
   brand_color: "#3B82F6"
-  default_prompt: "Apply standards: immutability, error handling, type safety"
+  default_prompt: "Use $coding-standards to review code against cross-project standards."
 policy:
   allow_implicit_invocation: true

.agents/skills/content-engine/SKILL.md

@@ -1,88 +1,130 @@
 ---
 name: content-engine
 description: Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
-origin: ECC
 ---
 
 # Content Engine
 
-Turn one idea into strong, platform-native content instead of posting the same thing everywhere.
+Build platform-native content without flattening the author's real voice into platform slop.
 
 ## When to Activate
 
 - writing X posts or threads
 - drafting LinkedIn posts or launch updates
 - scripting short-form video or YouTube explainers
-- repurposing articles, podcasts, demos, or docs into social content
-- building a lightweight content plan around a launch, milestone, or theme
+- repurposing articles, podcasts, demos, docs, or internal notes into public content
+- building a launch sequence or ongoing content system around a product, insight, or narrative
 
-## First Questions
+## Non-Negotiables
 
-Clarify:
-- source asset: what are we adapting from
-- audience: builders, investors, customers, operators, or general audience
-- platform: X, LinkedIn, TikTok, YouTube, newsletter, or multi-platform
-- goal: awareness, conversion, recruiting, authority, launch support, or engagement
+1. Start from source material, not generic post formulas.
+2. Adapt the format for the platform, not the persona.
+3. One post should carry one actual claim.
+4. Specificity beats adjectives.
+5. No engagement bait unless the user explicitly asks for it.
 
-## Core Rules
+## Source-First Workflow
 
-1. Adapt for the platform. Do not cross-post the same copy.
-2. Hooks matter more than summaries.
-3. Every post should carry one clear idea.
-4. Use specifics over slogans.
-5. Keep the ask small and clear.
+Before drafting, identify the source set:
+- published articles
+- notes or internal memos
+- product demos
+- docs or changelogs
+- transcripts
+- screenshots
+- prior posts from the same author
 
-## Platform Guidance
+If the user wants a specific voice, build a voice profile from real examples before writing.
+Use `brand-voice` as the canonical workflow when voice consistency matters across more than one output.
+
+## Voice Handling
+
+`brand-voice` is the canonical voice layer.
+
+Run it first when:
+
+- there are multiple downstream outputs
+- the user explicitly cares about writing style
+- the content is launch, outreach, or reputation-sensitive
+
+Reuse the resulting `VOICE PROFILE` here instead of rebuilding a second voice model.
+If the user wants Affaan / ECC voice specifically, still treat `brand-voice` as the source of truth and feed it the best live or source-derived material available.
+
+## Hard Bans
+
+Delete and rewrite any of these:
+- "In today's rapidly evolving landscape"
+- "game-changer", "revolutionary", "cutting-edge"
+- "here's why this matters" unless it is followed immediately by something concrete
+- ending with a LinkedIn-style question just to farm replies
+- forced casualness on LinkedIn
+- fake engagement padding that was not present in the source material
+
+## Platform Adaptation Rules
 
 ### X
-- open fast
-- one idea per post or per tweet in a thread
-- keep links out of the main body unless necessary
-- avoid hashtag spam
+
+- open with the strongest claim, artifact, or tension
+- keep the compression if the source voice is compressed
+- if writing a thread, each post must advance the argument
+- do not pad with context the audience does not need
 
 ### LinkedIn
-- strong first line
-- short paragraphs
-- more explicit framing around lessons, results, and takeaways
 
-### TikTok / Short Video
-- first 3 seconds must interrupt attention
-- script around visuals, not just narration
-- one demo, one claim, one CTA
+- expand only enough for people outside the immediate niche to follow
+- do not turn it into a fake lesson post unless the source material actually is reflective
+- no corporate inspiration cadence
+- no praise-stacking, no "journey" filler
+
+### Short Video
+
+- script around the visual sequence and proof points
+- first seconds should show the result, problem, or punch
+- do not write narration that sounds better on paper than on screen
 
 ### YouTube
-- show the result early
-- structure by chapter
-- refresh the visual every 20-30 seconds
+
+- show the result or tension early
+- organize by argument or progression, not filler sections
+- use chaptering only when it helps clarity
 
 ### Newsletter
-- deliver one clear lens, not a bundle of unrelated items
-- make section titles skimmable
-- keep the opening paragraph doing real work
+
+- open with the point, conflict, or artifact
+- do not spend the first paragraph warming up
+- every section needs to add something new
 
 ## Repurposing Flow
 
-Default cascade:
-1. anchor asset: article, video, demo, memo, or launch doc
-2. extract 3-7 atomic ideas
-3. write platform-native variants
-4. trim repetition across outputs
-5. align CTAs with platform intent
+1. Pick the anchor asset.
+2. Extract 3 to 7 atomic claims or scenes.
+3. Rank them by sharpness, novelty, and proof.
+4. Assign one strong idea per output.
+5. Adapt structure for each platform.
+6. Strip platform-shaped filler.
+7. Run the quality gate.
 
 ## Deliverables
 
 When asked for a campaign, return:
+- a short voice profile if voice matching matters
 - the core angle
-- platform-specific drafts
-- optional posting order
-- optional CTA variants
-- any missing inputs needed before publishing
+- platform-native drafts
+- posting order only if it helps execution
+- gaps that must be filled before publishing
 
 ## Quality Gate
 
 Before delivering:
-- each draft reads natively for its platform
-- hooks are strong and specific
-- no generic hype language
+- every draft sounds like the intended author, not the platform stereotype
+- every draft contains a real claim, proof point, or concrete observation
+- no generic hype language remains
+- no fake engagement bait remains
 - no duplicated copy across platforms unless requested
-- the CTA matches the content and audience
+- any CTA is earned and user-approved
+
+## Related Skills
+
+- `brand-voice` for source-derived voice profiles
+- `crosspost` for platform-specific distribution
+- `x-api` for sourcing recent posts and publishing approved X output

.agents/skills/content-engine/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Content Engine"
-  short_description: "Turn one idea into platform-native social and content outputs"
+  short_description: "Platform-native content systems and campaigns"
   brand_color: "#DC2626"
-  default_prompt: "Turn this source asset into strong multi-platform content"
+  default_prompt: "Use $content-engine to turn source material into platform-native content."
 policy:
   allow_implicit_invocation: true

.agents/skills/crosspost/SKILL.md

@@ -1,188 +1,110 @@
 ---
 name: crosspost
 description: Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.
-origin: ECC
 ---
 
 # Crosspost
 
-Distribute content across multiple social platforms with platform-native adaptation.
+Distribute content across platforms without turning it into the same fake post in four costumes.
 
 ## When to Activate
 
-- User wants to post content to multiple platforms
-- Publishing announcements, launches, or updates across social media
-- Repurposing a post from one platform to others
-- User says "crosspost", "post everywhere", "share on all platforms", or "distribute this"
+- the user wants to publish the same underlying idea across multiple platforms
+- a launch, update, release, or essay needs platform-specific versions
+- the user says "crosspost", "post this everywhere", or "adapt this for X and LinkedIn"
 
 ## Core Rules
 
-1. **Never post identical content cross-platform.** Each platform gets a native adaptation.
-2. **Primary platform first.** Post to the main platform, then adapt for others.
-3. **Respect platform conventions.** Length limits, formatting, link handling all differ.
-4. **One idea per post.** If the source content has multiple ideas, split across posts.
-5. **Attribution matters.** If crossposting someone else's content, credit the source.
-
-## Platform Specifications
-
-| Platform | Max Length | Link Handling | Hashtags | Media |
-|----------|-----------|---------------|----------|-------|
-| X | 280 chars (4000 for Premium) | Counted in length | Minimal (1-2 max) | Images, video, GIFs |
-| LinkedIn | 3000 chars | Not counted in length | 3-5 relevant | Images, video, docs, carousels |
-| Threads | 500 chars | Separate link attachment | None typical | Images, video |
-| Bluesky | 300 chars | Via facets (rich text) | None (use feeds) | Images |
+1. Do not publish identical copy across platforms.
+2. Preserve the author's voice across platforms.
+3. Adapt for constraints, not stereotypes.
+4. One post should still be about one thing.
+5. Do not invent a CTA, question, or moral if the source did not earn one.
 
 ## Workflow
 
-### Step 1: Create Source Content
+### Step 1: Start with the Primary Version
 
-Start with the core idea. Use `content-engine` skill for high-quality drafts:
-- Identify the single core message
-- Determine the primary platform (where the audience is biggest)
-- Draft the primary platform version first
+Pick the strongest source version first:
+- the original X post
+- the original article
+- the launch note
+- the thread
+- the memo or changelog
 
-### Step 2: Identify Target Platforms
+Use `content-engine` first if the source still needs voice shaping.
 
-Ask the user or determine from context:
-- Which platforms to target
-- Priority order (primary gets the best version)
-- Any platform-specific requirements (e.g., LinkedIn needs professional tone)
+### Step 2: Capture the Voice Fingerprint
 
-### Step 3: Adapt Per Platform
+Run `brand-voice` first if the source voice is not already captured in the current session.
 
-For each target platform, transform the content:
+Reuse the resulting `VOICE PROFILE` directly.
+Do not build a second ad hoc voice checklist here unless the user explicitly wants a fresh override for this campaign.
 
-**X adaptation:**
-- Open with a hook, not a summary
-- Cut to the core insight fast
-- Keep links out of main body when possible
-- Use thread format for longer content
+### Step 3: Adapt by Platform Constraint
 
-**LinkedIn adaptation:**
-- Strong first line (visible before "see more")
-- Short paragraphs with line breaks
-- Frame around lessons, results, or professional takeaways
-- More explicit context than X (LinkedIn audience needs framing)
+### X
 
-**Threads adaptation:**
-- Conversational, casual tone
-- Shorter than LinkedIn, less compressed than X
-- Visual-first if possible
+- keep it compressed
+- lead with the sharpest claim or artifact
+- use a thread only when a single post would collapse the argument
+- avoid hashtags and generic filler
 
-**Bluesky adaptation:**
-- Direct and concise (300 char limit)
-- Community-oriented tone
-- Use feeds/lists for topic targeting instead of hashtags
+### LinkedIn
 
-### Step 4: Post Primary Platform
+- add only the context needed for people outside the niche
+- do not turn it into a fake founder-reflection post
+- do not add a closing question just because it is LinkedIn
+- do not force a polished "professional tone" if the author is naturally sharper
 
-Post to the primary platform first:
-- Use `x-api` skill for X
-- Use platform-specific APIs or tools for others
-- Capture the post URL for cross-referencing
+### Threads
 
-### Step 5: Post to Secondary Platforms
+- keep it readable and direct
+- do not write fake hyper-casual creator copy
+- do not paste the LinkedIn version and shorten it
 
-Post adapted versions to remaining platforms:
-- Stagger timing (not all at once — 30-60 min gaps)
-- Include cross-platform references where appropriate ("longer thread on X" etc.)
+### Bluesky
 
-## Content Adaptation Examples
+- keep it concise
+- preserve the author's cadence
+- do not rely on hashtags or feed-gaming language
 
-### Source: Product Launch
+## Posting Order
 
-**X version:**
-```
-We just shipped [feature].
+Default:
+1. post the strongest native version first
+2. adapt for the secondary platforms
+3. stagger timing only if the user wants sequencing help
 
-[One specific thing it does that's impressive]
+Do not add cross-platform references unless useful. Most of the time, the post should stand on its own.
 
-[Link]
-```
+## Banned Patterns
 
-**LinkedIn version:**
-```
-Excited to share: we just launched [feature] at [Company].
+Delete and rewrite any of these:
+- "Excited to share"
+- "Here's what I learned"
+- "What do you think?"
+- "link in bio" unless that is literally true
+- generic "professional takeaway" paragraphs that were not in the source
 
-Here's why it matters:
+## Output Format
 
-[2-3 short paragraphs with context]
-
-[Takeaway for the audience]
-
-[Link]
-```
-
-**Threads version:**
-```
-just shipped something cool — [feature]
-
-[casual explanation of what it does]
-
-link in bio
-```
-
-### Source: Technical Insight
-
-**X version:**
-```
-TIL: [specific technical insight]
-
-[Why it matters in one sentence]
-```
-
-**LinkedIn version:**
-```
-A pattern I've been using that's made a real difference:
-
-[Technical insight with professional framing]
-
-[How it applies to teams/orgs]
-
-#relevantHashtag
-```
-
-## API Integration
-
-### Batch Crossposting Service (Example Pattern)
-If using a crossposting service (e.g., Postbridge, Buffer, or a custom API), the pattern looks like:
-
-```python
-import os
-import requests
-
-resp = requests.post(
-    "https://api.postbridge.io/v1/posts",
-    headers={"Authorization": f"Bearer {os.environ['POSTBRIDGE_API_KEY']}"},
-    json={
-        "platforms": ["twitter", "linkedin", "threads"],
-        "content": {
-            "twitter": {"text": x_version},
-            "linkedin": {"text": linkedin_version},
-            "threads": {"text": threads_version}
-        }
-    }
-)
-```
-
-### Manual Posting
-Without Postbridge, post to each platform using its native API:
-- X: Use `x-api` skill patterns
-- LinkedIn: LinkedIn API v2 with OAuth 2.0
-- Threads: Threads API (Meta)
-- Bluesky: AT Protocol API
+Return:
+- the primary platform version
+- adapted variants for each requested platform
+- a short note on what changed and why
+- any publishing constraint the user still needs to resolve
 
 ## Quality Gate
 
-Before posting:
-- [ ] Each platform version reads naturally for that platform
-- [ ] No identical content across platforms
-- [ ] Length limits respected
-- [ ] Links work and are placed appropriately
-- [ ] Tone matches platform conventions
-- [ ] Media is sized correctly for each platform
+Before delivering:
+- each version reads like the same author under different constraints
+- no platform version feels padded or sanitized
+- no copy is duplicated verbatim across platforms
+- any extra context added for LinkedIn or newsletter use is actually necessary
 
 ## Related Skills
 
-- `content-engine` — Generate platform-native content
-- `x-api` — X/Twitter API integration
+- `brand-voice` for reusable source-derived voice capture
+- `content-engine` for voice capture and source shaping
+- `x-api` for X publishing workflows

.agents/skills/crosspost/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Crosspost"
-  short_description: "Multi-platform content distribution with native adaptation"
+  short_description: "Multi-platform social distribution"
   brand_color: "#EC4899"
-  default_prompt: "Distribute content across X, LinkedIn, Threads, and Bluesky with platform-native adaptation"
+  default_prompt: "Use $crosspost to adapt content for multiple social platforms."
 policy:
   allow_implicit_invocation: true

.agents/skills/deep-research/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: deep-research
 description: Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
-origin: ECC
 ---
 
 # Deep Research

.agents/skills/deep-research/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Deep Research"
-  short_description: "Multi-source deep research with firecrawl and exa MCPs"
+  short_description: "Multi-source cited research reports"
   brand_color: "#6366F1"
-  default_prompt: "Research the given topic using firecrawl and exa, produce a cited report"
+  default_prompt: "Use $deep-research to produce a cited multi-source research report."
 policy:
   allow_implicit_invocation: true

.agents/skills/dmux-workflows/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: dmux-workflows
 description: Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
-origin: ECC
 ---
 
 # dmux Workflows

.agents/skills/dmux-workflows/agents/openai.yaml

@@ -2,6 +2,6 @@ interface:
   display_name: "dmux Workflows"
   short_description: "Multi-agent orchestration with dmux"
   brand_color: "#14B8A6"
-  default_prompt: "Orchestrate parallel agent sessions using dmux pane manager"
+  default_prompt: "Use $dmux-workflows to orchestrate parallel agent sessions with dmux."
 policy:
   allow_implicit_invocation: true

.agents/skills/documentation-lookup/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: documentation-lookup
 description: Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
-origin: ECC
 ---
 
 # Documentation Lookup (Context7)

.agents/skills/documentation-lookup/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Documentation Lookup"
-  short_description: "Fetch up-to-date library docs via Context7 MCP"
+  short_description: "Current library docs via Context7"
   brand_color: "#6366F1"
-  default_prompt: "Look up docs for a library or API"
+  default_prompt: "Use $documentation-lookup to fetch current library documentation via Context7."
 policy:
   allow_implicit_invocation: true

.agents/skills/e2e-testing/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: e2e-testing
 description: Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
-origin: ECC
 ---
 
 # E2E Testing Patterns

.agents/skills/e2e-testing/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "E2E Testing"
-  short_description: "Playwright end-to-end testing"
+  short_description: "Playwright E2E testing patterns"
   brand_color: "#06B6D4"
-  default_prompt: "Generate Playwright E2E tests with Page Object Model"
+  default_prompt: "Use $e2e-testing to design Playwright end-to-end test coverage."
 policy:
   allow_implicit_invocation: true

.agents/skills/eval-harness/SKILL.md

@@ -1,8 +1,7 @@
 ---
 name: eval-harness
 description: Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
-origin: ECC
-tools: Read, Write, Edit, Bash, Grep, Glob
+allowed-tools: Read, Write, Edit, Bash, Grep, Glob
 ---
 
 # Eval Harness Skill

.agents/skills/eval-harness/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Eval Harness"
-  short_description: "Eval-driven development with pass/fail criteria"
+  short_description: "Eval-driven development harnesses"
   brand_color: "#EC4899"
-  default_prompt: "Set up eval-driven development with pass/fail criteria"
+  default_prompt: "Use $eval-harness to define eval-driven development checks."
 policy:
   allow_implicit_invocation: true

.agents/skills/everything-claude-code/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: everything-claude-code-conventions
+name: everything-claude-code
 description: Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
 ---
 
@@ -304,24 +304,24 @@ Register the agent in AGENTS.md
 Optionally update README.md and docs/COMMAND-AGENT-MAP.md
 ```
 
-### Add New Command
+### Add New Workflow Surface
 
-Adds a new command to the system, often paired with a backing skill.
+Adds or updates a workflow entrypoint. Default to skills-first; only add a command shim when legacy slash compatibility is still required.
 
 **Frequency**: ~1 times per month
 
 **Steps**:
-1. Create a new markdown file under commands/{command-name}.md
-2. Optionally add or update a backing skill under skills/{skill-name}/SKILL.md
+1. Create or update the canonical workflow under skills/{skill-name}/SKILL.md
+2. Only if needed, add or update commands/{command-name}.md as a compatibility shim
 
 **Files typically involved**:
-- `commands/*.md`
 - `skills/*/SKILL.md`
+- `commands/*.md` (only when a legacy shim is intentionally retained)
 
 **Example commit sequence**:
 ```
-Create a new markdown file under commands/{command-name}.md
-Optionally add or update a backing skill under skills/{skill-name}/SKILL.md
+Create or update the canonical skill under skills/{skill-name}/SKILL.md
+Only if needed, add or update commands/{command-name}.md as a compatibility shim
 ```
 
 ### Sync Catalog Counts

.agents/skills/everything-claude-code/agents/openai.yaml

@@ -1,6 +1,7 @@
 interface:
   display_name: "Everything Claude Code"
-  short_description: "Repo-specific patterns and workflows for everything-claude-code"
-  default_prompt: "Use the everything-claude-code repo skill to follow existing architecture, testing, and workflow conventions."
+  short_description: "Repo workflows for everything-claude-code"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $everything-claude-code to follow this repository's conventions and workflows."
 policy:
-  allow_implicit_invocation: true
+  allow_implicit_invocation: true

.agents/skills/exa-search/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: exa-search
 description: Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
-origin: ECC
 ---
 
 # Exa Search

.agents/skills/exa-search/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Exa Search"
-  short_description: "Neural search via Exa MCP for web, code, and companies"
+  short_description: "Neural search via Exa MCP"
   brand_color: "#8B5CF6"
-  default_prompt: "Search using Exa MCP tools for web content, code, or company research"
+  default_prompt: "Use $exa-search to search web, code, or company data through Exa."
 policy:
   allow_implicit_invocation: true

.agents/skills/fal-ai-media/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: fal-ai-media
 description: Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
-origin: ECC
 ---
 
 # fal.ai Media Generation

.agents/skills/fal-ai-media/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "fal.ai Media"
-  short_description: "AI image, video, and audio generation via fal.ai"
+  short_description: "AI media generation via fal.ai"
   brand_color: "#F43F5E"
-  default_prompt: "Generate images, videos, or audio using fal.ai models"
+  default_prompt: "Use $fal-ai-media to generate image, video, or audio assets with fal.ai."
 policy:
   allow_implicit_invocation: true

.agents/skills/frontend-design/SKILL.md

@@ -0,0 +1,144 @@
+---
+name: frontend-design
+description: Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.
+---
+
+# Frontend Design
+
+Use this when the task is not just "make it work" but "make it look designed."
+
+This skill is for product pages, dashboards, app shells, components, or visual systems that need a clear point of view instead of generic AI-looking UI.
+
+## When To Use
+
+- building a landing page, dashboard, or app surface from scratch
+- upgrading a bland interface into something intentional and memorable
+- translating a product concept into a concrete visual direction
+- implementing a frontend where typography, composition, and motion matter
+
+## Core Principle
+
+Pick a direction and commit to it.
+
+Safe-average UI is usually worse than a strong, coherent aesthetic with a few bold choices.
+
+## Design Workflow
+
+### 1. Frame the interface first
+
+Before coding, settle:
+
+- purpose
+- audience
+- emotional tone
+- visual direction
+- one thing the user should remember
+
+Possible directions:
+
+- brutally minimal
+- editorial
+- industrial
+- luxury
+- playful
+- geometric
+- retro-futurist
+- soft and organic
+- maximalist
+
+Do not mix directions casually. Choose one and execute it cleanly.
+
+### 2. Build the visual system
+
+Define:
+
+- type hierarchy
+- color variables
+- spacing rhythm
+- layout logic
+- motion rules
+- surface / border / shadow treatment
+
+Use CSS variables or the project's token system so the interface stays coherent as it grows.
+
+### 3. Compose with intention
+
+Prefer:
+
+- asymmetry when it sharpens hierarchy
+- overlap when it creates depth
+- strong whitespace when it clarifies focus
+- dense layouts only when the product benefits from density
+
+Avoid defaulting to a symmetrical card grid unless it is clearly the right fit.
+
+### 4. Make motion meaningful
+
+Use animation to:
+
+- reveal hierarchy
+- stage information
+- reinforce user action
+- create one or two memorable moments
+
+Do not scatter generic micro-interactions everywhere. One well-directed load sequence is usually stronger than twenty random hover effects.
+
+## Strong Defaults
+
+### Typography
+
+- pick fonts with character
+- pair a distinctive display face with a readable body face when appropriate
+- avoid generic defaults when the page is design-led
+
+### Color
+
+- commit to a clear palette
+- one dominant field with selective accents usually works better than evenly weighted rainbow palettes
+- avoid cliché purple-gradient-on-white unless the product genuinely calls for it
+
+### Background
+
+Use atmosphere:
+
+- gradients
+- meshes
+- textures
+- subtle noise
+- patterns
+- layered transparency
+
+Flat empty backgrounds are rarely the best answer for a product-facing page.
+
+### Layout
+
+- break the grid when the composition benefits from it
+- use diagonals, offsets, and grouping intentionally
+- keep reading flow obvious even when the layout is unconventional
+
+## Anti-Patterns
+
+Never default to:
+
+- interchangeable SaaS hero sections
+- generic card piles with no hierarchy
+- random accent colors without a system
+- placeholder-feeling typography
+- motion that exists only because animation was easy to add
+
+## Execution Rules
+
+- preserve the established design system when working inside an existing product
+- match technical complexity to the visual idea
+- keep accessibility and responsiveness intact
+- frontends should feel deliberate on desktop and mobile
+
+## Quality Gate
+
+Before delivering:
+
+- the interface has a clear visual point of view
+- typography and spacing feel intentional
+- color and motion support the product instead of decorating it randomly
+- the result does not read like generic AI UI
+- the implementation is production-grade, not just visually interesting

.agents/skills/frontend-design/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Frontend Design"
+  short_description: "Production-grade frontend interface design"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $frontend-design to build a distinctive production-grade interface."
+policy:
+  allow_implicit_invocation: true

.agents/skills/frontend-patterns/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: frontend-patterns
 description: Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
-origin: ECC
 ---
 
 # Frontend Development Patterns

.agents/skills/frontend-patterns/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Frontend Patterns"
-  short_description: "React and Next.js patterns and best practices"
+  short_description: "React and Next.js frontend patterns"
   brand_color: "#8B5CF6"
-  default_prompt: "Apply React/Next.js patterns and best practices"
+  default_prompt: "Use $frontend-patterns to apply React and Next.js frontend patterns."
 policy:
   allow_implicit_invocation: true

.agents/skills/frontend-slides/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: frontend-slides
 description: Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
-origin: ECC
 ---
 
 # Frontend Slides

.agents/skills/frontend-slides/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Frontend Slides"
-  short_description: "Create distinctive HTML slide decks and convert PPTX to web"
+  short_description: "Animation-rich HTML presentation decks"
   brand_color: "#FF6B3D"
-  default_prompt: "Create a viewport-safe HTML presentation with strong visual direction"
+  default_prompt: "Use $frontend-slides to create an animation-rich HTML presentation deck."
 policy:
   allow_implicit_invocation: true

.agents/skills/investor-materials/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: investor-materials
 description: Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
-origin: ECC
 ---
 
 # Investor Materials

.agents/skills/investor-materials/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Investor Materials"
-  short_description: "Create decks, memos, and financial materials from one source of truth"
+  short_description: "Investor decks, memos, and financial materials"
   brand_color: "#7C3AED"
-  default_prompt: "Draft investor materials that stay numerically consistent across assets"
+  default_prompt: "Use $investor-materials to draft consistent investor-facing fundraising assets."
 policy:
   allow_implicit_invocation: true

.agents/skills/investor-outreach/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: investor-outreach
 description: Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
-origin: ECC
 ---
 
 # Investor Outreach
 
-Write investor communication that is short, personalized, and easy to act on.
+Write investor communication that is short, concrete, and easy to act on.
 
 ## When to Activate
 
@@ -20,17 +19,32 @@ Write investor communication that is short, personalized, and easy to act on.
 
 1. Personalize every outbound message.
 2. Keep the ask low-friction.
-3. Use proof, not adjectives.
+3. Use proof instead of adjectives.
 4. Stay concise.
-5. Never send generic copy that could go to any investor.
+5. Never send copy that could go to any investor.
+
+## Voice Handling
+
+If the user's voice matters, run `brand-voice` first and reuse its `VOICE PROFILE`.
+This skill should keep the investor-specific structure and ask discipline, not recreate its own parallel voice system.
+
+## Hard Bans
+
+Delete and rewrite any of these:
+- "I'd love to connect"
+- "excited to share"
+- generic thesis praise without a real tie-in
+- vague founder adjectives
+- begging language
+- soft closing questions when a direct ask is clearer
 
 ## Cold Email Structure
 
 1. subject line: short and specific
 2. opener: why this investor specifically
-3. pitch: what the company does, why now, what proof matters
+3. pitch: what the company does, why now, and what proof matters
 4. ask: one concrete next step
-5. sign-off: name, role, one credibility anchor if needed
+5. sign-off: name, role, and one credibility anchor if needed
 
 ## Personalization Sources
 
@@ -40,14 +54,14 @@ Reference one or more of:
 - a mutual connection
 - a clear market or product fit with the investor's focus
 
-If that context is missing, ask for it or state that the draft is a template awaiting personalization.
+If that context is missing, state that the draft still needs personalization instead of pretending it is finished.
 
 ## Follow-Up Cadence
 
 Default:
 - day 0: initial outbound
-- day 4-5: short follow-up with one new data point
-- day 10-12: final follow-up with a clean close
+- day 4 or 5: short follow-up with one new data point
+- day 10 to 12: final follow-up with a clean close
 
 Do not keep nudging after that unless the user wants a longer sequence.
 
@@ -69,8 +83,8 @@ Include:
 ## Quality Gate
 
 Before delivering:
-- message is personalized
+- the message is genuinely personalized
 - the ask is explicit
-- there is no fluff or begging language
 - the proof point is concrete
+- filler praise and softener language are gone
 - word count stays tight

.agents/skills/investor-outreach/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Investor Outreach"
-  short_description: "Write concise, personalized outreach and follow-ups for fundraising"
+  short_description: "Personalized investor outreach and follow-ups"
   brand_color: "#059669"
-  default_prompt: "Draft a personalized investor outreach email with a clear low-friction ask"
+  default_prompt: "Use $investor-outreach to write concise personalized investor outreach."
 policy:
   allow_implicit_invocation: true

.agents/skills/market-research/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: market-research
 description: Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
-origin: ECC
 ---
 
 # Market Research

.agents/skills/market-research/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Market Research"
-  short_description: "Source-attributed market, competitor, and investor research"
+  short_description: "Source-attributed market research"
   brand_color: "#2563EB"
-  default_prompt: "Research this market and summarize the decision-relevant findings"
+  default_prompt: "Use $market-research to research markets with source-attributed findings."
 policy:
   allow_implicit_invocation: true

.agents/skills/mcp-server-patterns/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: mcp-server-patterns
 description: Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
-origin: ECC
 ---
 
 # MCP Server Patterns

.agents/skills/mcp-server-patterns/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "MCP Server Patterns"
+  short_description: "MCP server tools, resources, and prompts"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $mcp-server-patterns to build MCP tools, resources, and prompts."
+policy:
+  allow_implicit_invocation: true

.agents/skills/nextjs-turbopack/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: nextjs-turbopack
 description: Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
-origin: ECC
 ---
 
 # Next.js and Turbopack

.agents/skills/nextjs-turbopack/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Next.js Turbopack"
-  short_description: "Next.js 16+ and Turbopack dev bundler"
+  short_description: "Next.js and Turbopack workflow guidance"
   brand_color: "#000000"
-  default_prompt: "Next.js dev, Turbopack, or bundle optimization"
+  default_prompt: "Use $nextjs-turbopack to work through Next.js and Turbopack decisions."
 policy:
   allow_implicit_invocation: true

.agents/skills/product-capability/SKILL.md

@@ -0,0 +1,140 @@
+---
+name: product-capability
+description: Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.
+---
+
+# Product Capability
+
+This skill turns product intent into explicit engineering constraints.
+
+Use it when the gap is not "what should we build?" but "what exactly must be true before implementation starts?"
+
+## When to Use
+
+- A PRD, roadmap item, discussion, or founder note exists, but the implementation constraints are still implicit
+- A feature crosses multiple services, repos, or teams and needs a capability contract before coding
+- Product intent is clear, but architecture, data, lifecycle, or policy implications are still fuzzy
+- Senior engineers keep restating the same hidden assumptions during review
+- You need a reusable artifact that can survive across harnesses and sessions
+
+## Canonical Artifact
+
+If the repo has a durable product-context file such as `PRODUCT.md`, `docs/product/`, or a program-spec directory, update it there.
+
+If no capability manifest exists yet, create one using the template at:
+
+- `docs/examples/product-capability-template.md`
+
+The goal is not to create another planning stack. The goal is to make hidden capability constraints durable and reusable.
+
+## Non-Negotiable Rules
+
+- Do not invent product truth. Mark unresolved questions explicitly.
+- Separate user-visible promises from implementation details.
+- Call out what is fixed policy, what is architecture preference, and what is still open.
+- If the request conflicts with existing repo constraints, say so clearly instead of smoothing it over.
+- Prefer one reusable capability artifact over scattered ad hoc notes.
+
+## Inputs
+
+Read only what is needed:
+
+1. Product intent
+   - issue, discussion, PRD, roadmap note, founder message
+2. Current architecture
+   - relevant repo docs, contracts, schemas, routes, existing workflows
+3. Existing capability context
+   - `PRODUCT.md`, design docs, RFCs, migration notes, operating-model docs
+4. Delivery constraints
+   - auth, billing, compliance, rollout, backwards compatibility, performance, review policy
+
+## Core Workflow
+
+### 1. Restate the capability
+
+Compress the ask into one precise statement:
+
+- who the user or operator is
+- what new capability exists after this ships
+- what outcome changes because of it
+
+If this statement is weak, the implementation will drift.
+
+### 2. Resolve capability constraints
+
+Extract the constraints that must hold before implementation:
+
+- business rules
+- scope boundaries
+- invariants
+- trust boundaries
+- data ownership
+- lifecycle transitions
+- rollout / migration requirements
+- failure and recovery expectations
+
+These are the things that often live only in senior-engineer memory.
+
+### 3. Define the implementation-facing contract
+
+Produce an SRS-style capability plan with:
+
+- capability summary
+- explicit non-goals
+- actors and surfaces
+- required states and transitions
+- interfaces / inputs / outputs
+- data model implications
+- security / billing / policy constraints
+- observability and operator requirements
+- open questions blocking implementation
+
+### 4. Translate into execution
+
+End with the exact handoff:
+
+- ready for direct implementation
+- needs architecture review first
+- needs product clarification first
+
+If useful, point to the next ECC-native lane:
+
+- `project-flow-ops`
+- `workspace-surface-audit`
+- `api-connector-builder`
+- `dashboard-builder`
+- `tdd-workflow`
+- `verification-loop`
+
+## Output Format
+
+Return the result in this order:
+
+```text
+CAPABILITY
+- one-paragraph restatement
+
+CONSTRAINTS
+- fixed rules, invariants, and boundaries
+
+IMPLEMENTATION CONTRACT
+- actors
+- surfaces
+- states and transitions
+- interface/data implications
+
+NON-GOALS
+- what this lane explicitly does not own
+
+OPEN QUESTIONS
+- blockers or product decisions still required
+
+HANDOFF
+- what should happen next and which ECC lane should take it
+```
+
+## Good Outcomes
+
+- Product intent is now concrete enough to implement without rediscovering hidden constraints mid-PR.
+- Engineering review has a durable artifact instead of relying on memory or Slack context.
+- The resulting plan is reusable across Claude Code, Codex, Cursor, OpenCode, and ECC 2.0 planning surfaces.

.agents/skills/product-capability/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Product Capability"
+  short_description: "Implementation-ready product capability plans"
+  brand_color: "#0EA5E9"
+  default_prompt: "Use $product-capability to turn product intent into an implementation plan."
+policy:
+  allow_implicit_invocation: true

.agents/skills/security-review/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: security-review
 description: Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
-origin: ECC
 ---
 
 # Security Review Skill

.agents/skills/security-review/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Security Review"
-  short_description: "Comprehensive security checklist and vulnerability detection"
+  short_description: "Security checklist and vulnerability review"
   brand_color: "#EF4444"
-  default_prompt: "Run security checklist: secrets, input validation, injection prevention"
+  default_prompt: "Use $security-review to review sensitive code with the security checklist."
 policy:
   allow_implicit_invocation: true

.agents/skills/strategic-compact/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: strategic-compact
 description: Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
-origin: ECC
 ---
 
 # Strategic Compact Skill

.agents/skills/strategic-compact/agents/openai.yaml

@@ -2,6 +2,6 @@ interface:
   display_name: "Strategic Compact"
   short_description: "Context management via strategic compaction"
   brand_color: "#14B8A6"
-  default_prompt: "Suggest task boundary compaction for context management"
+  default_prompt: "Use $strategic-compact to choose a useful context compaction boundary."
 policy:
   allow_implicit_invocation: true

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

@@ -1,7 +1,6 @@
 ---
 name: tdd-workflow
 description: Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
-origin: ECC
 ---
 
 # Test-Driven Development Workflow

.agents/skills/tdd-workflow/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "TDD Workflow"
-  short_description: "Test-driven development with 80%+ coverage"
+  short_description: "Test-driven development with coverage gates"
   brand_color: "#22C55E"
-  default_prompt: "Follow TDD: write tests first, implement, verify 80%+ coverage"
+  default_prompt: "Use $tdd-workflow to drive the change with tests before implementation."
 policy:
   allow_implicit_invocation: true

.agents/skills/verification-loop/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: verification-loop
 description: "A comprehensive verification system for Claude Code sessions."
-origin: ECC
 ---
 
 # Verification Loop Skill

.agents/skills/verification-loop/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Verification Loop"
-  short_description: "Build, test, lint, typecheck verification"
+  short_description: "Build, test, lint, and typecheck verification"
   brand_color: "#10B981"
-  default_prompt: "Run verification: build, test, lint, typecheck, security"
+  default_prompt: "Use $verification-loop to run build, test, lint, and typecheck verification."
 policy:
   allow_implicit_invocation: true

.agents/skills/video-editing/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: video-editing
 description: AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
-origin: ECC
 ---
 
 # Video Editing

.agents/skills/video-editing/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "Video Editing"
-  short_description: "AI-assisted video editing for real footage"
+  short_description: "AI-assisted editing for real footage"
   brand_color: "#EF4444"
-  default_prompt: "Edit video using AI-assisted pipeline: organize, cut, compose, generate assets, polish"
+  default_prompt: "Use $video-editing to plan an AI-assisted edit for real footage."
 policy:
   allow_implicit_invocation: true

.agents/skills/x-api/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: x-api
 description: X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
-origin: ECC
 ---
 
 # X API
@@ -19,7 +18,7 @@ Programmatic interaction with X (Twitter) for posting, reading, searching, and a
 
 ## Authentication
 
-### OAuth 2.0 (App-Only / User Context)
+### OAuth 2.0 Bearer Token (App-Only)
 
 Best for: read-heavy operations, search, public data.
 
@@ -46,25 +45,27 @@ tweets = resp.json()
 
 ### OAuth 1.0a (User Context)
 
-Required for: posting tweets, managing account, DMs.
+Required for: posting tweets, managing account, DMs, and any write flow.
 
 ```bash
 # Environment setup — source before use
-export X_API_KEY="your-api-key"
-export X_API_SECRET="your-api-secret"
+export X_CONSUMER_KEY="your-consumer-key"
+export X_CONSUMER_SECRET="your-consumer-secret"
 export X_ACCESS_TOKEN="your-access-token"
-export X_ACCESS_SECRET="your-access-secret"
+export X_ACCESS_TOKEN_SECRET="your-access-token-secret"
 ```
 
+Legacy aliases such as `X_API_KEY`, `X_API_SECRET`, and `X_ACCESS_SECRET` may exist in older setups. Prefer the `X_CONSUMER_*` and `X_ACCESS_TOKEN_SECRET` names when documenting or wiring new flows.
+
 ```python
 import os
 from requests_oauthlib import OAuth1Session
 
 oauth = OAuth1Session(
-    os.environ["X_API_KEY"],
-    client_secret=os.environ["X_API_SECRET"],
+    os.environ["X_CONSUMER_KEY"],
+    client_secret=os.environ["X_CONSUMER_SECRET"],
     resource_owner_key=os.environ["X_ACCESS_TOKEN"],
-    resource_owner_secret=os.environ["X_ACCESS_SECRET"],
+    resource_owner_secret=os.environ["X_ACCESS_TOKEN_SECRET"],
 )
 ```
 
@@ -92,7 +93,6 @@ def post_thread(oauth, tweets: list[str]) -> list[str]:
         if reply_to:
             payload["reply"] = {"in_reply_to_tweet_id": reply_to}
         resp = oauth.post("https://api.x.com/2/tweets", json=payload)
-        resp.raise_for_status()
         tweet_id = resp.json()["data"]["id"]
         ids.append(tweet_id)
         reply_to = tweet_id
@@ -126,6 +126,21 @@ resp = requests.get(
 )
 ```
 
+### Pull Recent Original Posts for Voice Modeling
+
+```python
+resp = requests.get(
+    "https://api.x.com/2/tweets/search/recent",
+    headers=headers,
+    params={
+        "query": "from:affaanmustafa -is:retweet -is:reply",
+        "max_results": 25,
+        "tweet.fields": "created_at,public_metrics",
+    }
+)
+voice_samples = resp.json()
+```
+
 ### Get User by Username
 
 ```python
@@ -155,17 +170,12 @@ resp = oauth.post(
 )
 ```
 
-## Rate Limits Reference
+## Rate Limits
 
-| Endpoint | Limit | Window |
-|----------|-------|--------|
-| POST /2/tweets | 200 | 15 min |
-| GET /2/tweets/search/recent | 450 | 15 min |
-| GET /2/users/:id/tweets | 1500 | 15 min |
-| GET /2/users/by/username | 300 | 15 min |
-| POST media/upload | 415 | 15 min |
-
-Always check `x-rate-limit-remaining` and `x-rate-limit-reset` headers.
+X API rate limits vary by endpoint, auth method, and account tier, and they change over time. Always:
+- Check the current X developer docs before hardcoding assumptions
+- Read `x-rate-limit-remaining` and `x-rate-limit-reset` headers at runtime
+- Back off automatically instead of relying on static tables in code
 
 ```python
 import time
@@ -202,13 +212,18 @@ else:
 
 ## Integration with Content Engine
 
-Use `content-engine` skill to generate platform-native content, then post via X API:
-1. Generate content with content-engine (X platform format)
-2. Validate length (280 chars for single tweet)
-3. Post via X API using patterns above
-4. Track engagement via public_metrics
+Use `brand-voice` plus `content-engine` to generate platform-native content, then post via X API:
+1. Pull recent original posts when voice matching matters
+2. Build or reuse a `VOICE PROFILE`
+3. Generate content with `content-engine` in X-native format
+4. Validate length and thread structure
+5. Return the draft for approval unless the user explicitly asked to post now
+6. Post via X API only after approval
+7. Track engagement via public_metrics
 
 ## Related Skills
 
+- `brand-voice` — Build a reusable voice profile from real X and site/source material
 - `content-engine` — Generate platform-native content for X
 - `crosspost` — Distribute content across X, LinkedIn, and other platforms
+- `connections-optimizer` — Reorganize the X graph before drafting network-driven outreach

.agents/skills/x-api/agents/openai.yaml

@@ -1,7 +1,7 @@
 interface:
   display_name: "X API"
-  short_description: "X/Twitter API integration for posting, threads, and analytics"
+  short_description: "X API posting, timelines, and analytics"
   brand_color: "#000000"
-  default_prompt: "Use X API to post tweets, threads, or retrieve timeline and search data"
+  default_prompt: "Use $x-api to build X API posting, timeline, or analytics workflows."
 policy:
   allow_implicit_invocation: true

.claude-plugin/PLUGIN_SCHEMA_NOTES.md

@@ -45,60 +45,37 @@ Example:
 
 The following fields **must always be arrays**:
 
-* `agents`
 * `commands`
 * `skills`
 * `hooks` (if present)
 
 Even if there is only one entry, **strings are not accepted**.
 
-### Invalid
-
-```json
-{
-  "agents": "./agents"
-}
-```
-
-### Valid
-
-```json
-{
-  "agents": ["./agents/planner.md"]
-}
-```
-
 This applies consistently across all component path fields.
 
 ---
 
-## Path Resolution Rules (Critical)
+## The `agents` Field: DO NOT ADD
 
-### Agents MUST use explicit file paths
+> WARNING: **CRITICAL:** Do NOT add an `"agents"` field to `plugin.json`. The Claude Code plugin validator rejects it entirely.
 
-The validator **does not accept directory paths for `agents`**.
+### Why This Matters
 
-Even the following will fail:
+The `agents` field is not part of the Claude Code plugin manifest schema. Any form of it -- string path, array of paths, or array of directories -- causes a validation error:
 
-```json
-{
-  "agents": ["./agents/"]
-}
+```
+agents: Invalid input
 ```
 
-Instead, you must enumerate agent files explicitly:
+Agent `.md` files under `agents/` are discovered automatically by convention (similar to hooks). They do not need to be declared in the manifest.
 
-```json
-{
-  "agents": [
-    "./agents/planner.md",
-    "./agents/architect.md",
-    "./agents/code-reviewer.md"
-  ]
-}
-```
+### History
 
-This is the most common source of validation errors.
+Previously this repo listed agents explicitly in `plugin.json` as an array of file paths. This passed the repo's own schema but failed Claude Code's actual validator, which does not recognize the field. Removed in #1459.
+
+---
+
+## Path Resolution Rules
 
 ### Commands and Skills
 
@@ -160,7 +137,7 @@ The test `plugin.json does NOT have explicit hooks declaration` in `tests/hooks/
 These look correct but are rejected:
 
 * String values instead of arrays
-* Arrays of directories for `agents`
+* **Adding `"agents"` in any form** - not a recognized manifest field, causes `Invalid input`
 * Missing `version`
 * Relying on inferred paths
 * Assuming marketplace behavior matches local validation
@@ -175,10 +152,6 @@ Avoid cleverness. Be explicit.
 ```json
 {
   "version": "1.1.0",
-  "agents": [
-    "./agents/planner.md",
-    "./agents/code-reviewer.md"
-  ],
   "commands": ["./commands/"],
   "skills": ["./skills/"]
 }
@@ -186,7 +159,7 @@ Avoid cleverness. Be explicit.
 
 This structure has been validated against the Claude plugin validator.
 
-**Important:** Notice there is NO `"hooks"` field. The `hooks/hooks.json` file is loaded automatically by convention. Adding it explicitly causes a duplicate error.
+**Important:** Notice there is NO `"hooks"` field and NO `"agents"` field. Both are loaded automatically by convention. Adding either explicitly causes errors.
 
 ---
 
@@ -194,9 +167,9 @@ This structure has been validated against the Claude plugin validator.
 
 Before submitting changes that touch `plugin.json`:
 
-1. Use explicit file paths for agents
-2. Ensure all component fields are arrays
-3. Include a `version`
+1. Ensure all component fields are arrays
+2. Include a `version`
+3. Do NOT add `agents` or `hooks` fields (both are auto-loaded by convention)
 4. Run:
 
 ```bash

.claude-plugin/README.md

@@ -1,12 +1,12 @@
 ### Plugin Manifest Gotchas
 
-If you plan to edit `.claude-plugin/plugin.json`, be aware that the Claude plugin validator enforces several **undocumented but strict constraints** that can cause installs to fail with vague errors (for example, `agents: Invalid input`). In particular, component fields must be arrays, `agents` must use explicit file paths rather than directories, and a `version` field is required for reliable validation and installation.
+If you plan to edit `.claude-plugin/plugin.json`, be aware that the Claude plugin validator enforces several **undocumented but strict constraints** that can cause installs to fail with vague errors (for example, `agents: Invalid input`). In particular, component fields must be arrays, `agents` is not a supported manifest field and must not be included in plugin.json, and a `version` field is required for reliable validation and installation.
 
 These constraints are not obvious from public examples and have caused repeated installation failures in the past. They are documented in detail in `.claude-plugin/PLUGIN_SCHEMA_NOTES.md`, which should be reviewed before making any changes to the plugin manifest.
 
 ### Custom Endpoints and Gateways
 
-ECC does not override Claude Code transport settings. If Claude Code is configured to run through an official LLM gateway or a compatible custom endpoint, the plugin continues to work because hooks, commands, and skills execute locally after the CLI starts successfully.
+ECC does not override Claude Code transport settings. If Claude Code is configured to run through an official LLM gateway or a compatible custom endpoint, the plugin continues to work because hooks, skills, and any retained legacy command shims execute locally after the CLI starts successfully.
 
 Use Claude Code's own environment/configuration for transport selection, for example:
 

.claude-plugin/marketplace.json

@@ -1,7 +1,5 @@
 {
-  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
   "name": "everything-claude-code",
-  "description": "Battle-tested Claude Code configurations from an Anthropic hackathon winner — agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use",
   "owner": {
     "name": "Affaan Mustafa",
     "email": "me@affaanmustafa.com"
@@ -13,13 +11,13 @@
     {
       "name": "everything-claude-code",
       "source": "./",
-      "description": "The most comprehensive Claude Code plugin — 14+ agents, 56+ skills, 33+ commands, and production-ready hooks for TDD, security scanning, code review, and continuous learning",
-      "version": "1.9.0",
+      "description": "The most comprehensive Claude Code plugin — 48 agents, 184 skills, 79 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",
         "email": "me@affaanmustafa.com"
       },
-      "homepage": "https://github.com/affaan-m/everything-claude-code",
+      "homepage": "https://ecc.tools",
       "repository": "https://github.com/affaan-m/everything-claude-code",
       "license": "MIT",
       "keywords": [

.claude-plugin/plugin.json

@@ -1,12 +1,12 @@
 {
   "name": "everything-claude-code",
-  "version": "1.9.0",
-  "description": "Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use",
+  "version": "2.0.0-rc.1",
+  "description": "Battle-tested Claude Code plugin for engineering teams — 48 agents, 184 skills, 79 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"
   },
-  "homepage": "https://github.com/affaan-m/everything-claude-code",
+  "homepage": "https://ecc.tools",
   "repository": "https://github.com/affaan-m/everything-claude-code",
   "license": "MIT",
   "keywords": [
@@ -22,36 +22,6 @@
     "automation",
     "best-practices"
   ],
-  "agents": [
-    "./agents/architect.md",
-    "./agents/build-error-resolver.md",
-    "./agents/chief-of-staff.md",
-    "./agents/code-reviewer.md",
-    "./agents/cpp-build-resolver.md",
-    "./agents/cpp-reviewer.md",
-    "./agents/database-reviewer.md",
-    "./agents/doc-updater.md",
-    "./agents/docs-lookup.md",
-    "./agents/e2e-runner.md",
-    "./agents/flutter-reviewer.md",
-    "./agents/go-build-resolver.md",
-    "./agents/go-reviewer.md",
-    "./agents/harness-optimizer.md",
-    "./agents/java-build-resolver.md",
-    "./agents/java-reviewer.md",
-    "./agents/kotlin-build-resolver.md",
-    "./agents/kotlin-reviewer.md",
-    "./agents/loop-operator.md",
-    "./agents/planner.md",
-    "./agents/python-reviewer.md",
-    "./agents/pytorch-build-resolver.md",
-    "./agents/refactor-cleaner.md",
-    "./agents/rust-build-resolver.md",
-    "./agents/rust-reviewer.md",
-    "./agents/security-reviewer.md",
-    "./agents/tdd-guide.md",
-    "./agents/typescript-reviewer.md"
-  ],
   "skills": ["./skills/"],
   "commands": ["./commands/"]
 }

.codebuddy/README.md

@@ -0,0 +1,98 @@
+# Everything Claude Code for CodeBuddy
+
+Bring Everything Claude Code (ECC) workflows to CodeBuddy IDE. This repository provides custom commands, agents, skills, and rules that can be installed into any CodeBuddy project using the unified Target Adapter architecture.
+
+## Quick Start (Recommended)
+
+Use the unified install system for full lifecycle management:
+
+```bash
+# Install with default profile
+node scripts/install-apply.js --target codebuddy --profile developer
+
+# Install with full profile (all modules)
+node scripts/install-apply.js --target codebuddy --profile full
+
+# Dry-run to preview changes
+node scripts/install-apply.js --target codebuddy --profile full --dry-run
+```
+
+## Management Commands
+
+```bash
+# Check installation health
+node scripts/doctor.js --target codebuddy
+
+# Repair installation
+node scripts/repair.js --target codebuddy
+
+# Uninstall cleanly (tracked via install-state)
+node scripts/uninstall.js --target codebuddy
+```
+
+## Shell Script (Legacy)
+
+The legacy shell scripts are still available for quick setup:
+
+```bash
+# Install to current project
+cd /path/to/your/project
+.codebuddy/install.sh
+
+# Install globally
+.codebuddy/install.sh ~
+```
+
+## What's Included
+
+### Commands
+
+Commands are on-demand workflows invocable via the `/` menu in CodeBuddy chat. All commands are reused directly from the project root's `commands/` folder.
+
+### Agents
+
+Agents are specialized AI assistants with specific tool configurations. All agents are reused directly from the project root's `agents/` folder.
+
+### Skills
+
+Skills are on-demand workflows invocable via the `/` menu in chat. All skills are reused directly from the project's `skills/` folder.
+
+### Rules
+
+Rules provide always-on rules and context that shape how the agent works with your code. Rules are flattened into namespaced files (e.g., `common-coding-style.md`) for CodeBuddy compatibility.
+
+## Project Structure
+
+```
+.codebuddy/
+├── commands/           # Command files (reused from project root)
+├── agents/             # Agent files (reused from project root)
+├── skills/             # Skill files (reused from skills/)
+├── rules/              # Rule files (flattened from rules/)
+├── ecc-install-state.json  # Install state tracking
+├── install.sh          # Legacy install script
+├── uninstall.sh        # Legacy uninstall script
+└── README.md           # This file
+```
+
+## Benefits of Target Adapter Install
+
+- **Install-state tracking**: Safe uninstall that only removes ECC-managed files
+- **Doctor checks**: Verify installation health and detect drift
+- **Repair**: Auto-fix broken installations
+- **Selective install**: Choose specific modules via profiles
+- **Cross-platform**: Node.js-based, works on Windows/macOS/Linux
+
+## Recommended Workflow
+
+1. **Start with planning**: Use `/plan` command to break down complex features
+2. **Write tests first**: Invoke `/tdd` command before implementing
+3. **Review your code**: Use `/code-review` after writing code
+4. **Check security**: Use `/code-review` again for auth, API endpoints, or sensitive data handling
+5. **Fix build errors**: Use `/build-fix` if there are build errors
+
+## Next Steps
+
+- Open your project in CodeBuddy
+- Type `/` to see available commands
+- Enjoy the ECC workflows!

.codebuddy/README.zh-CN.md

@@ -0,0 +1,98 @@
+# Everything Claude Code for CodeBuddy
+
+为 CodeBuddy IDE 带来 Everything Claude Code (ECC) 工作流。此仓库提供自定义命令、智能体、技能和规则，可以通过统一的 Target Adapter 架构安装到任何 CodeBuddy 项目中。
+
+## 快速开始（推荐）
+
+使用统一安装系统，获得完整的生命周期管理：
+
+```bash
+# 使用默认配置安装
+node scripts/install-apply.js --target codebuddy --profile developer
+
+# 使用完整配置安装（所有模块）
+node scripts/install-apply.js --target codebuddy --profile full
+
+# 预览模式查看变更
+node scripts/install-apply.js --target codebuddy --profile full --dry-run
+```
+
+## 管理命令
+
+```bash
+# 检查安装健康状态
+node scripts/doctor.js --target codebuddy
+
+# 修复安装
+node scripts/repair.js --target codebuddy
+
+# 清洁卸载（通过 install-state 跟踪）
+node scripts/uninstall.js --target codebuddy
+```
+
+## Shell 脚本（旧版）
+
+旧版 Shell 脚本仍然可用于快速设置：
+
+```bash
+# 安装到当前项目
+cd /path/to/your/project
+.codebuddy/install.sh
+
+# 全局安装
+.codebuddy/install.sh ~
+```
+
+## 包含的内容
+
+### 命令
+
+命令是通过 CodeBuddy 聊天中的 `/` 菜单调用的按需工作流。所有命令都直接复用自项目根目录的 `commands/` 文件夹。
+
+### 智能体
+
+智能体是具有特定工具配置的专门 AI 助手。所有智能体都直接复用自项目根目录的 `agents/` 文件夹。
+
+### 技能
+
+技能是通过聊天中的 `/` 菜单调用的按需工作流。所有技能都直接复用自项目的 `skills/` 文件夹。
+
+### 规则
+
+规则提供始终适用的规则和上下文，塑造智能体处理代码的方式。规则会被扁平化为命名空间文件（如 `common-coding-style.md`）以兼容 CodeBuddy。
+
+## 项目结构
+
+```
+.codebuddy/
+├── commands/           # 命令文件（复用自项目根目录）
+├── agents/             # 智能体文件（复用自项目根目录）
+├── skills/             # 技能文件（复用自 skills/）
+├── rules/              # 规则文件（从 rules/ 扁平化）
+├── ecc-install-state.json  # 安装状态跟踪
+├── install.sh          # 旧版安装脚本
+├── uninstall.sh        # 旧版卸载脚本
+└── README.zh-CN.md     # 此文件
+```
+
+## Target Adapter 安装的优势
+
+- **安装状态跟踪**：安全卸载，仅删除 ECC 管理的文件
+- **Doctor 检查**：验证安装健康状态并检测偏移
+- **修复**：自动修复损坏的安装
+- **选择性安装**：通过配置文件选择特定模块
+- **跨平台**：基于 Node.js，支持 Windows/macOS/Linux
+
+## 推荐的工作流
+
+1. **从计划开始**：使用 `/plan` 命令分解复杂功能
+2. **先写测试**：在实现之前调用 `/tdd` 命令
+3. **审查您的代码**：编写代码后使用 `/code-review`
+4. **检查安全性**：对于身份验证、API 端点或敏感数据处理，再次使用 `/code-review`
+5. **修复构建错误**：如果有构建错误，使用 `/build-fix`
+
+## 下一步
+
+- 在 CodeBuddy 中打开您的项目
+- 输入 `/` 以查看可用命令
+- 享受 ECC 工作流！

.codebuddy/install.js

@@ -0,0 +1,312 @@
+#!/usr/bin/env node
+/**
+ * ECC CodeBuddy Installer (Cross-platform Node.js version)
+ * Installs Everything Claude Code workflows into a CodeBuddy project.
+ *
+ * Usage:
+ *   node install.js              # Install to current directory
+ *   node install.js ~            # Install globally to ~/.codebuddy/
+ */
+
+const fs = require('fs');
+const path = require('path');
+const os = require('os');
+
+// Platform detection
+const isWindows = process.platform === 'win32';
+
+/**
+ * Get home directory cross-platform
+ */
+function getHomeDir() {
+  return process.env.USERPROFILE || process.env.HOME || os.homedir();
+}
+
+/**
+ * Ensure directory exists
+ */
+function ensureDir(dirPath) {
+  try {
+    if (!fs.existsSync(dirPath)) {
+      fs.mkdirSync(dirPath, { recursive: true });
+    }
+  } catch (err) {
+    if (err.code !== 'EEXIST') {
+      throw err;
+    }
+  }
+}
+
+/**
+ * Read lines from a file
+ */
+function readLines(filePath) {
+  try {
+    if (!fs.existsSync(filePath)) {
+      return [];
+    }
+    const content = fs.readFileSync(filePath, 'utf8');
+    return content.split('\n').filter(line => line.length > 0);
+  } catch {
+    return [];
+  }
+}
+
+/**
+ * Check if manifest contains an entry
+ */
+function manifestHasEntry(manifestPath, entry) {
+  const lines = readLines(manifestPath);
+  return lines.includes(entry);
+}
+
+/**
+ * Add entry to manifest
+ */
+function ensureManifestEntry(manifestPath, entry) {
+  try {
+    const lines = readLines(manifestPath);
+    if (!lines.includes(entry)) {
+      const content = lines.join('\n') + (lines.length > 0 ? '\n' : '') + entry + '\n';
+      fs.writeFileSync(manifestPath, content, 'utf8');
+    }
+  } catch (err) {
+    console.error(`Error updating manifest: ${err.message}`);
+  }
+}
+
+/**
+ * Copy a file and manage in manifest
+ */
+function copyManagedFile(sourcePath, targetPath, manifestPath, manifestEntry, makeExecutable = false) {
+  const alreadyManaged = manifestHasEntry(manifestPath, manifestEntry);
+
+  // If target file already exists
+  if (fs.existsSync(targetPath)) {
+    if (alreadyManaged) {
+      ensureManifestEntry(manifestPath, manifestEntry);
+    }
+    return false;
+  }
+
+  // Copy the file
+  try {
+    ensureDir(path.dirname(targetPath));
+    fs.copyFileSync(sourcePath, targetPath);
+
+    // Make executable on Unix systems
+    if (makeExecutable && !isWindows) {
+      fs.chmodSync(targetPath, 0o755);
+    }
+
+    ensureManifestEntry(manifestPath, manifestEntry);
+    return true;
+  } catch (err) {
+    console.error(`Error copying ${sourcePath}: ${err.message}`);
+    return false;
+  }
+}
+
+/**
+ * Recursively find files in a directory
+ */
+function findFiles(dir, extension = '') {
+  const results = [];
+  try {
+    if (!fs.existsSync(dir)) {
+      return results;
+    }
+
+    function walk(currentPath) {
+      try {
+        const entries = fs.readdirSync(currentPath, { withFileTypes: true });
+        for (const entry of entries) {
+          const fullPath = path.join(currentPath, entry.name);
+          if (entry.isDirectory()) {
+            walk(fullPath);
+          } else if (!extension || entry.name.endsWith(extension)) {
+            results.push(fullPath);
+          }
+        }
+      } catch {
+        // Ignore permission errors
+      }
+    }
+
+    walk(dir);
+  } catch {
+    // Ignore errors
+  }
+  return results.sort();
+}
+
+/**
+ * Main install function
+ */
+function doInstall() {
+  // Resolve script directory (where this file lives)
+  const scriptDir = path.dirname(path.resolve(__filename));
+  const repoRoot = path.dirname(scriptDir);
+  const codebuddyDirName = '.codebuddy';
+
+  // Parse arguments
+  let targetDir = process.cwd();
+  if (process.argv.length > 2) {
+    const arg = process.argv[2];
+    if (arg === '~' || arg === getHomeDir()) {
+      targetDir = getHomeDir();
+    } else {
+      targetDir = path.resolve(arg);
+    }
+  }
+
+  // Determine codebuddy full path
+  let codebuddyFullPath;
+  const baseName = path.basename(targetDir);
+
+  if (baseName === codebuddyDirName) {
+    codebuddyFullPath = targetDir;
+  } else {
+    codebuddyFullPath = path.join(targetDir, codebuddyDirName);
+  }
+
+  console.log('ECC CodeBuddy Installer');
+  console.log('=======================');
+  console.log('');
+  console.log(`Source:  ${repoRoot}`);
+  console.log(`Target:  ${codebuddyFullPath}/`);
+  console.log('');
+
+  // Create subdirectories
+  const subdirs = ['commands', 'agents', 'skills', 'rules'];
+  for (const dir of subdirs) {
+    ensureDir(path.join(codebuddyFullPath, dir));
+  }
+
+  // Manifest file
+  const manifest = path.join(codebuddyFullPath, '.ecc-manifest');
+  ensureDir(path.dirname(manifest));
+
+  // Counters
+  let commands = 0;
+  let agents = 0;
+  let skills = 0;
+  let rules = 0;
+
+  // Copy commands
+  const commandsDir = path.join(repoRoot, 'commands');
+  if (fs.existsSync(commandsDir)) {
+    const files = findFiles(commandsDir, '.md');
+    for (const file of files) {
+      if (path.basename(path.dirname(file)) === 'commands') {
+        const localName = path.basename(file);
+        const targetPath = path.join(codebuddyFullPath, 'commands', localName);
+        if (copyManagedFile(file, targetPath, manifest, `commands/${localName}`)) {
+          commands += 1;
+        }
+      }
+    }
+  }
+
+  // Copy agents
+  const agentsDir = path.join(repoRoot, 'agents');
+  if (fs.existsSync(agentsDir)) {
+    const files = findFiles(agentsDir, '.md');
+    for (const file of files) {
+      if (path.basename(path.dirname(file)) === 'agents') {
+        const localName = path.basename(file);
+        const targetPath = path.join(codebuddyFullPath, 'agents', localName);
+        if (copyManagedFile(file, targetPath, manifest, `agents/${localName}`)) {
+          agents += 1;
+        }
+      }
+    }
+  }
+
+  // Copy skills (with subdirectories)
+  const skillsDir = path.join(repoRoot, 'skills');
+  if (fs.existsSync(skillsDir)) {
+    const skillDirs = fs.readdirSync(skillsDir, { withFileTypes: true })
+      .filter(entry => entry.isDirectory())
+      .map(entry => entry.name);
+
+    for (const skillName of skillDirs) {
+      const sourceSkillDir = path.join(skillsDir, skillName);
+      const targetSkillDir = path.join(codebuddyFullPath, 'skills', skillName);
+      let skillCopied = false;
+
+      const skillFiles = findFiles(sourceSkillDir);
+      for (const sourceFile of skillFiles) {
+        const relativePath = path.relative(sourceSkillDir, sourceFile);
+        const targetPath = path.join(targetSkillDir, relativePath);
+        const manifestEntry = `skills/${skillName}/${relativePath.replace(/\\/g, '/')}`;
+
+        if (copyManagedFile(sourceFile, targetPath, manifest, manifestEntry)) {
+          skillCopied = true;
+        }
+      }
+
+      if (skillCopied) {
+        skills += 1;
+      }
+    }
+  }
+
+  // Copy rules (with subdirectories)
+  const rulesDir = path.join(repoRoot, 'rules');
+  if (fs.existsSync(rulesDir)) {
+    const ruleFiles = findFiles(rulesDir);
+    for (const ruleFile of ruleFiles) {
+      const relativePath = path.relative(rulesDir, ruleFile);
+      const targetPath = path.join(codebuddyFullPath, 'rules', relativePath);
+      const manifestEntry = `rules/${relativePath.replace(/\\/g, '/')}`;
+
+      if (copyManagedFile(ruleFile, targetPath, manifest, manifestEntry)) {
+        rules += 1;
+      }
+    }
+  }
+
+  // Copy README files (skip install/uninstall scripts to avoid broken
+  // path references when the copied script runs from the target directory)
+  const readmeFiles = ['README.md', 'README.zh-CN.md'];
+  for (const readmeFile of readmeFiles) {
+    const sourcePath = path.join(scriptDir, readmeFile);
+    if (fs.existsSync(sourcePath)) {
+      const targetPath = path.join(codebuddyFullPath, readmeFile);
+      copyManagedFile(sourcePath, targetPath, manifest, readmeFile);
+    }
+  }
+
+  // Add manifest itself
+  ensureManifestEntry(manifest, '.ecc-manifest');
+
+  // Print summary
+  console.log('Installation complete!');
+  console.log('');
+  console.log('Components installed:');
+  console.log(`  Commands:  ${commands}`);
+  console.log(`  Agents:    ${agents}`);
+  console.log(`  Skills:    ${skills}`);
+  console.log(`  Rules:     ${rules}`);
+  console.log('');
+  console.log(`Directory:   ${path.basename(codebuddyFullPath)}`);
+  console.log('');
+  console.log('Next steps:');
+  console.log('  1. Open your project in CodeBuddy');
+  console.log('  2. Type / to see available commands');
+  console.log('  3. Enjoy the ECC workflows!');
+  console.log('');
+  console.log('To uninstall later:');
+  console.log(`  cd ${codebuddyFullPath}`);
+  console.log('  node uninstall.js');
+  console.log('');
+}
+
+// Run installer
+try {
+  doInstall();
+} catch (error) {
+  console.error(`Error: ${error.message}`);
+  process.exit(1);
+}

.codebuddy/install.sh

@@ -0,0 +1,231 @@
+#!/bin/bash
+#
+# ECC CodeBuddy Installer
+# Installs Everything Claude Code workflows into a CodeBuddy project.
+#
+# Usage:
+#   ./install.sh              # Install to current directory
+#   ./install.sh ~            # Install globally to ~/.codebuddy/
+#
+
+set -euo pipefail
+
+# When globs match nothing, expand to empty list instead of the literal pattern
+shopt -s nullglob
+
+# Resolve the directory where this script lives
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# Locate the ECC repo root by walking up from SCRIPT_DIR to find the marker
+# file (VERSION). This keeps the script working even when it has been copied
+# into a target project's .codebuddy/ directory.
+find_repo_root() {
+    local dir="$(dirname "$SCRIPT_DIR")"
+    # First try the parent of SCRIPT_DIR (original layout: .codebuddy/ lives in repo root)
+    if [ -f "$dir/VERSION" ] && [ -d "$dir/commands" ] && [ -d "$dir/agents" ]; then
+        echo "$dir"
+        return 0
+    fi
+    echo ""
+    return 1
+}
+
+REPO_ROOT="$(find_repo_root)"
+if [ -z "$REPO_ROOT" ]; then
+    echo "Error: Cannot locate the ECC repository root."
+    echo "This script must be run from within the ECC repository's .codebuddy/ directory."
+    exit 1
+fi
+
+# CodeBuddy directory name
+CODEBUDDY_DIR=".codebuddy"
+
+ensure_manifest_entry() {
+    local manifest="$1"
+    local entry="$2"
+
+    touch "$manifest"
+    if ! grep -Fqx "$entry" "$manifest"; then
+        echo "$entry" >> "$manifest"
+    fi
+}
+
+manifest_has_entry() {
+    local manifest="$1"
+    local entry="$2"
+
+    [ -f "$manifest" ] && grep -Fqx "$entry" "$manifest"
+}
+
+copy_managed_file() {
+    local source_path="$1"
+    local target_path="$2"
+    local manifest="$3"
+    local manifest_entry="$4"
+    local make_executable="${5:-0}"
+
+    local already_managed=0
+    if manifest_has_entry "$manifest" "$manifest_entry"; then
+        already_managed=1
+    fi
+
+    if [ -f "$target_path" ]; then
+        if [ "$already_managed" -eq 1 ]; then
+            ensure_manifest_entry "$manifest" "$manifest_entry"
+        fi
+        return 1
+    fi
+
+    cp "$source_path" "$target_path"
+    if [ "$make_executable" -eq 1 ]; then
+        chmod +x "$target_path"
+    fi
+    ensure_manifest_entry "$manifest" "$manifest_entry"
+    return 0
+}
+
+# Install function
+do_install() {
+    local target_dir="$PWD"
+
+    # Check if ~ was specified (or expanded to $HOME)
+    if [ "$#" -ge 1 ]; then
+        if [ "$1" = "~" ] || [ "$1" = "$HOME" ]; then
+            target_dir="$HOME"
+        fi
+    fi
+
+    # Check if we're already inside a .codebuddy directory
+    local current_dir_name="$(basename "$target_dir")"
+    local codebuddy_full_path
+
+    if [ "$current_dir_name" = ".codebuddy" ]; then
+        # Already inside the codebuddy directory, use it directly
+        codebuddy_full_path="$target_dir"
+    else
+        # Normal case: append CODEBUDDY_DIR to target_dir
+        codebuddy_full_path="$target_dir/$CODEBUDDY_DIR"
+    fi
+
+    echo "ECC CodeBuddy Installer"
+    echo "======================="
+    echo ""
+    echo "Source:  $REPO_ROOT"
+    echo "Target:  $codebuddy_full_path/"
+    echo ""
+
+    # Subdirectories to create
+    SUBDIRS="commands agents skills rules"
+
+    # Create all required codebuddy subdirectories
+    for dir in $SUBDIRS; do
+        mkdir -p "$codebuddy_full_path/$dir"
+    done
+
+    # Manifest file to track installed files
+    MANIFEST="$codebuddy_full_path/.ecc-manifest"
+    touch "$MANIFEST"
+
+    # Counters for summary
+    commands=0
+    agents=0
+    skills=0
+    rules=0
+
+    # Copy commands from repo root
+    if [ -d "$REPO_ROOT/commands" ]; then
+        for f in "$REPO_ROOT/commands"/*.md; do
+            [ -f "$f" ] || continue
+            local_name=$(basename "$f")
+            target_path="$codebuddy_full_path/commands/$local_name"
+            if copy_managed_file "$f" "$target_path" "$MANIFEST" "commands/$local_name"; then
+                commands=$((commands + 1))
+            fi
+        done
+    fi
+
+    # Copy agents from repo root
+    if [ -d "$REPO_ROOT/agents" ]; then
+        for f in "$REPO_ROOT/agents"/*.md; do
+            [ -f "$f" ] || continue
+            local_name=$(basename "$f")
+            target_path="$codebuddy_full_path/agents/$local_name"
+            if copy_managed_file "$f" "$target_path" "$MANIFEST" "agents/$local_name"; then
+                agents=$((agents + 1))
+            fi
+        done
+    fi
+
+    # Copy skills from repo root (if available)
+    if [ -d "$REPO_ROOT/skills" ]; then
+        for d in "$REPO_ROOT/skills"/*/; do
+            [ -d "$d" ] || continue
+            skill_name="$(basename "$d")"
+            target_skill_dir="$codebuddy_full_path/skills/$skill_name"
+            skill_copied=0
+
+            while IFS= read -r source_file; do
+                relative_path="${source_file#$d}"
+                target_path="$target_skill_dir/$relative_path"
+
+                mkdir -p "$(dirname "$target_path")"
+                if copy_managed_file "$source_file" "$target_path" "$MANIFEST" "skills/$skill_name/$relative_path"; then
+                    skill_copied=1
+                fi
+            done < <(find "$d" -type f | sort)
+
+            if [ "$skill_copied" -eq 1 ]; then
+                skills=$((skills + 1))
+            fi
+        done
+    fi
+
+    # Copy rules from repo root
+    if [ -d "$REPO_ROOT/rules" ]; then
+        while IFS= read -r rule_file; do
+            relative_path="${rule_file#$REPO_ROOT/rules/}"
+            target_path="$codebuddy_full_path/rules/$relative_path"
+
+            mkdir -p "$(dirname "$target_path")"
+            if copy_managed_file "$rule_file" "$target_path" "$MANIFEST" "rules/$relative_path"; then
+                rules=$((rules + 1))
+            fi
+        done < <(find "$REPO_ROOT/rules" -type f | sort)
+    fi
+
+    # Copy README files (skip install/uninstall scripts to avoid broken
+    # path references when the copied script runs from the target directory)
+    for readme_file in "$SCRIPT_DIR/README.md" "$SCRIPT_DIR/README.zh-CN.md"; do
+        if [ -f "$readme_file" ]; then
+            local_name=$(basename "$readme_file")
+            target_path="$codebuddy_full_path/$local_name"
+            copy_managed_file "$readme_file" "$target_path" "$MANIFEST" "$local_name" || true
+        fi
+    done
+
+    # Add manifest file itself to manifest
+    ensure_manifest_entry "$MANIFEST" ".ecc-manifest"
+
+    # Installation summary
+    echo "Installation complete!"
+    echo ""
+    echo "Components installed:"
+    echo "  Commands:  $commands"
+    echo "  Agents:    $agents"
+    echo "  Skills:    $skills"
+    echo "  Rules:     $rules"
+    echo ""
+    echo "Directory:   $(basename "$codebuddy_full_path")"
+    echo ""
+    echo "Next steps:"
+    echo "  1. Open your project in CodeBuddy"
+    echo "  2. Type / to see available commands"
+    echo "  3. Enjoy the ECC workflows!"
+    echo ""
+    echo "To uninstall later:"
+    echo "  cd $codebuddy_full_path"
+    echo "  ./uninstall.sh"
+}
+
+# Main logic
+do_install "$@"

.codebuddy/uninstall.js

@@ -0,0 +1,291 @@
+#!/usr/bin/env node
+/**
+ * ECC CodeBuddy Uninstaller (Cross-platform Node.js version)
+ * Uninstalls Everything Claude Code workflows from a CodeBuddy project.
+ *
+ * Usage:
+ *   node uninstall.js              # Uninstall from current directory
+ *   node uninstall.js ~            # Uninstall globally from ~/.codebuddy/
+ */
+
+const fs = require('fs');
+const path = require('path');
+const os = require('os');
+const readline = require('readline');
+
+/**
+ * Get home directory cross-platform
+ */
+function getHomeDir() {
+  return process.env.USERPROFILE || process.env.HOME || os.homedir();
+}
+
+/**
+ * Resolve a path to its canonical form
+ */
+function resolvePath(filePath) {
+  try {
+    return fs.realpathSync(filePath);
+  } catch {
+    // If realpath fails, return the path as-is
+    return path.resolve(filePath);
+  }
+}
+
+/**
+ * Check if a manifest entry is valid (security check)
+ */
+function isValidManifestEntry(entry) {
+  // Reject empty, absolute paths, parent directory references
+  if (!entry || entry.length === 0) return false;
+  if (entry.startsWith('/')) return false;
+  if (entry.startsWith('~')) return false;
+  if (entry.includes('/../') || entry.includes('/..')) return false;
+  if (entry.startsWith('../') || entry.startsWith('..\\')) return false;
+  if (entry === '..' || entry === '...' || entry.includes('\\..\\')||entry.includes('/..')) return false;
+
+  return true;
+}
+
+/**
+ * Read lines from manifest file
+ */
+function readManifest(manifestPath) {
+  try {
+    if (!fs.existsSync(manifestPath)) {
+      return [];
+    }
+    const content = fs.readFileSync(manifestPath, 'utf8');
+    return content.split('\n').filter(line => line.length > 0);
+  } catch {
+    return [];
+  }
+}
+
+/**
+ * Recursively find empty directories
+ */
+function findEmptyDirs(dirPath) {
+  const emptyDirs = [];
+
+  function walkDirs(currentPath) {
+    try {
+      const entries = fs.readdirSync(currentPath, { withFileTypes: true });
+      const subdirs = entries.filter(e => e.isDirectory());
+
+      for (const subdir of subdirs) {
+        const subdirPath = path.join(currentPath, subdir.name);
+        walkDirs(subdirPath);
+      }
+
+      // Check if directory is now empty
+      try {
+        const remaining = fs.readdirSync(currentPath);
+        if (remaining.length === 0 && currentPath !== dirPath) {
+          emptyDirs.push(currentPath);
+        }
+      } catch {
+        // Directory might have been deleted
+      }
+    } catch {
+      // Ignore errors
+    }
+  }
+
+  walkDirs(dirPath);
+  return emptyDirs.sort().reverse(); // Sort in reverse for removal
+}
+
+/**
+ * Prompt user for confirmation
+ */
+async function promptConfirm(question) {
+  return new Promise((resolve) => {
+    const rl = readline.createInterface({
+      input: process.stdin,
+      output: process.stdout,
+    });
+
+    rl.question(question, (answer) => {
+      rl.close();
+      resolve(/^[yY]$/.test(answer));
+    });
+  });
+}
+
+/**
+ * Main uninstall function
+ */
+async function doUninstall() {
+  const codebuddyDirName = '.codebuddy';
+
+  // Parse arguments
+  let targetDir = process.cwd();
+  if (process.argv.length > 2) {
+    const arg = process.argv[2];
+    if (arg === '~' || arg === getHomeDir()) {
+      targetDir = getHomeDir();
+    } else {
+      targetDir = path.resolve(arg);
+    }
+  }
+
+  // Determine codebuddy full path
+  let codebuddyFullPath;
+  const baseName = path.basename(targetDir);
+
+  if (baseName === codebuddyDirName) {
+    codebuddyFullPath = targetDir;
+  } else {
+    codebuddyFullPath = path.join(targetDir, codebuddyDirName);
+  }
+
+  console.log('ECC CodeBuddy Uninstaller');
+  console.log('==========================');
+  console.log('');
+  console.log(`Target:  ${codebuddyFullPath}/`);
+  console.log('');
+
+  // Check if codebuddy directory exists
+  if (!fs.existsSync(codebuddyFullPath)) {
+    console.error(`Error: ${codebuddyDirName} directory not found at ${targetDir}`);
+    process.exit(1);
+  }
+
+  const codebuddyRootResolved = resolvePath(codebuddyFullPath);
+  const manifest = path.join(codebuddyFullPath, '.ecc-manifest');
+
+  // Handle missing manifest
+  if (!fs.existsSync(manifest)) {
+    console.log('Warning: No manifest file found (.ecc-manifest)');
+    console.log('');
+    console.log('This could mean:');
+    console.log('  1. ECC was installed with an older version without manifest support');
+    console.log('  2. The manifest file was manually deleted');
+    console.log('');
+
+    const confirmed = await promptConfirm(`Do you want to remove the entire ${codebuddyDirName} directory? (y/N) `);
+    if (!confirmed) {
+      console.log('Uninstall cancelled.');
+      process.exit(0);
+    }
+
+    try {
+      fs.rmSync(codebuddyFullPath, { recursive: true, force: true });
+      console.log('Uninstall complete!');
+      console.log('');
+      console.log(`Removed: ${codebuddyFullPath}/`);
+    } catch (err) {
+      console.error(`Error removing directory: ${err.message}`);
+      process.exit(1);
+    }
+    return;
+  }
+
+  console.log('Found manifest file - will only remove files installed by ECC');
+  console.log('');
+
+  const confirmed = await promptConfirm(`Are you sure you want to uninstall ECC from ${codebuddyDirName}? (y/N) `);
+  if (!confirmed) {
+    console.log('Uninstall cancelled.');
+    process.exit(0);
+  }
+
+  // Read manifest and remove files
+  const manifestLines = readManifest(manifest);
+  let removed = 0;
+  let skipped = 0;
+
+  for (const filePath of manifestLines) {
+    if (!filePath || filePath.length === 0) continue;
+
+    if (!isValidManifestEntry(filePath)) {
+      console.log(`Skipped: ${filePath} (invalid manifest entry)`);
+      skipped += 1;
+      continue;
+    }
+
+    const fullPath = path.join(codebuddyFullPath, filePath);
+
+    // Security check: use path.relative() to ensure the manifest entry
+    // resolves inside the codebuddy directory. This is stricter than
+    // startsWith and correctly handles edge-cases with symlinks.
+    const relative = path.relative(codebuddyRootResolved, path.resolve(fullPath));
+    if (relative.startsWith('..') || path.isAbsolute(relative)) {
+      console.log(`Skipped: ${filePath} (outside target directory)`);
+      skipped += 1;
+      continue;
+    }
+
+    try {
+      const stats = fs.lstatSync(fullPath);
+
+      if (stats.isFile() || stats.isSymbolicLink()) {
+        fs.unlinkSync(fullPath);
+        console.log(`Removed: ${filePath}`);
+        removed += 1;
+      } else if (stats.isDirectory()) {
+        try {
+          const files = fs.readdirSync(fullPath);
+          if (files.length === 0) {
+            fs.rmdirSync(fullPath);
+            console.log(`Removed: ${filePath}/`);
+            removed += 1;
+          } else {
+            console.log(`Skipped: ${filePath}/ (not empty - contains user files)`);
+            skipped += 1;
+          }
+        } catch {
+          console.log(`Skipped: ${filePath}/ (not empty - contains user files)`);
+          skipped += 1;
+        }
+      }
+    } catch {
+      skipped += 1;
+    }
+  }
+
+  // Remove empty directories
+  const emptyDirs = findEmptyDirs(codebuddyFullPath);
+  for (const emptyDir of emptyDirs) {
+    try {
+      fs.rmdirSync(emptyDir);
+      const relativePath = path.relative(codebuddyFullPath, emptyDir);
+      console.log(`Removed: ${relativePath}/`);
+      removed += 1;
+    } catch {
+      // Directory might not be empty anymore
+    }
+  }
+
+  // Try to remove main codebuddy directory if empty
+  try {
+    const files = fs.readdirSync(codebuddyFullPath);
+    if (files.length === 0) {
+      fs.rmdirSync(codebuddyFullPath);
+      console.log(`Removed: ${codebuddyDirName}/`);
+      removed += 1;
+    }
+  } catch {
+    // Directory not empty
+  }
+
+  // Print summary
+  console.log('');
+  console.log('Uninstall complete!');
+  console.log('');
+  console.log('Summary:');
+  console.log(`  Removed: ${removed} items`);
+  console.log(`  Skipped: ${skipped} items (not found or user-modified)`);
+  console.log('');
+
+  if (fs.existsSync(codebuddyFullPath)) {
+    console.log(`Note: ${codebuddyDirName} directory still exists (contains user-added files)`);
+  }
+}
+
+// Run uninstaller
+doUninstall().catch((error) => {
+  console.error(`Error: ${error.message}`);
+  process.exit(1);
+});

.codebuddy/uninstall.sh

@@ -0,0 +1,184 @@
+#!/bin/bash
+#
+# ECC CodeBuddy Uninstaller
+# Uninstalls Everything Claude Code workflows from a CodeBuddy project.
+#
+# Usage:
+#   ./uninstall.sh              # Uninstall from current directory
+#   ./uninstall.sh ~            # Uninstall globally from ~/.codebuddy/
+#
+
+set -euo pipefail
+
+# Resolve the directory where this script lives
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# CodeBuddy directory name
+CODEBUDDY_DIR=".codebuddy"
+
+resolve_path() {
+    python3 -c 'import os, sys; print(os.path.realpath(sys.argv[1]))' "$1"
+}
+
+is_valid_manifest_entry() {
+    local file_path="$1"
+
+    case "$file_path" in
+        ""|/*|~*|*/../*|../*|*/..|..)
+            return 1
+            ;;
+    esac
+
+    return 0
+}
+
+# Main uninstall function
+do_uninstall() {
+    local target_dir="$PWD"
+
+    # Check if ~ was specified (or expanded to $HOME)
+    if [ "$#" -ge 1 ]; then
+        if [ "$1" = "~" ] || [ "$1" = "$HOME" ]; then
+            target_dir="$HOME"
+        fi
+    fi
+
+    # Check if we're already inside a .codebuddy directory
+    local current_dir_name="$(basename "$target_dir")"
+    local codebuddy_full_path
+
+    if [ "$current_dir_name" = ".codebuddy" ]; then
+        # Already inside the codebuddy directory, use it directly
+        codebuddy_full_path="$target_dir"
+    else
+        # Normal case: append CODEBUDDY_DIR to target_dir
+        codebuddy_full_path="$target_dir/$CODEBUDDY_DIR"
+    fi
+
+    echo "ECC CodeBuddy Uninstaller"
+    echo "=========================="
+    echo ""
+    echo "Target:  $codebuddy_full_path/"
+    echo ""
+
+    if [ ! -d "$codebuddy_full_path" ]; then
+        echo "Error: $CODEBUDDY_DIR directory not found at $target_dir"
+        exit 1
+    fi
+
+    codebuddy_root_resolved="$(resolve_path "$codebuddy_full_path")"
+
+    # Manifest file path
+    MANIFEST="$codebuddy_full_path/.ecc-manifest"
+
+    if [ ! -f "$MANIFEST" ]; then
+        echo "Warning: No manifest file found (.ecc-manifest)"
+        echo ""
+        echo "This could mean:"
+        echo "  1. ECC was installed with an older version without manifest support"
+        echo "  2. The manifest file was manually deleted"
+        echo ""
+        read -p "Do you want to remove the entire $CODEBUDDY_DIR directory? (y/N) " -n 1 -r
+        echo
+        if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+            echo "Uninstall cancelled."
+            exit 0
+        fi
+        rm -rf "$codebuddy_full_path"
+        echo "Uninstall complete!"
+        echo ""
+        echo "Removed: $codebuddy_full_path/"
+        exit 0
+    fi
+
+    echo "Found manifest file - will only remove files installed by ECC"
+    echo ""
+    read -p "Are you sure you want to uninstall ECC from $CODEBUDDY_DIR? (y/N) " -n 1 -r
+    echo
+    if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+        echo "Uninstall cancelled."
+        exit 0
+    fi
+
+    # Counters
+    removed=0
+    skipped=0
+
+    # Read manifest and remove files
+    while IFS= read -r file_path; do
+        [ -z "$file_path" ] && continue
+
+        if ! is_valid_manifest_entry "$file_path"; then
+            echo "Skipped: $file_path (invalid manifest entry)"
+            skipped=$((skipped + 1))
+            continue
+        fi
+
+        full_path="$codebuddy_full_path/$file_path"
+
+        # Security check: ensure the path resolves inside the target directory.
+        # Use Python to compute a reliable relative path so symlinks cannot
+        # escape the boundary.
+        relative="$(python3 -c 'import os,sys; print(os.path.relpath(os.path.abspath(sys.argv[1]), sys.argv[2]))' "$full_path" "$codebuddy_root_resolved")"
+        case "$relative" in
+            ../*|..)
+                echo "Skipped: $file_path (outside target directory)"
+                skipped=$((skipped + 1))
+                continue
+                ;;
+        esac
+
+        if [ -L "$full_path" ] || [ -f "$full_path" ]; then
+            rm -f "$full_path"
+            echo "Removed: $file_path"
+            removed=$((removed + 1))
+        elif [ -d "$full_path" ]; then
+            # Only remove directory if it's empty
+            if [ -z "$(ls -A "$full_path" 2>/dev/null)" ]; then
+                rmdir "$full_path" 2>/dev/null || true
+                if [ ! -d "$full_path" ]; then
+                    echo "Removed: $file_path/"
+                    removed=$((removed + 1))
+                fi
+            else
+                echo "Skipped: $file_path/ (not empty - contains user files)"
+                skipped=$((skipped + 1))
+            fi
+        else
+            skipped=$((skipped + 1))
+        fi
+    done < "$MANIFEST"
+
+    while IFS= read -r empty_dir; do
+        [ "$empty_dir" = "$codebuddy_full_path" ] && continue
+        relative_dir="${empty_dir#$codebuddy_full_path/}"
+        rmdir "$empty_dir" 2>/dev/null || true
+        if [ ! -d "$empty_dir" ]; then
+            echo "Removed: $relative_dir/"
+            removed=$((removed + 1))
+        fi
+    done < <(find "$codebuddy_full_path" -depth -type d -empty 2>/dev/null | sort -r)
+
+    # Try to remove the main codebuddy directory if it's empty
+    if [ -d "$codebuddy_full_path" ] && [ -z "$(ls -A "$codebuddy_full_path" 2>/dev/null)" ]; then
+        rmdir "$codebuddy_full_path" 2>/dev/null || true
+        if [ ! -d "$codebuddy_full_path" ]; then
+            echo "Removed: $CODEBUDDY_DIR/"
+            removed=$((removed + 1))
+        fi
+    fi
+
+    echo ""
+    echo "Uninstall complete!"
+    echo ""
+    echo "Summary:"
+    echo "  Removed: $removed items"
+    echo "  Skipped: $skipped items (not found or user-modified)"
+    echo ""
+    if [ -d "$codebuddy_full_path" ]; then
+        echo "Note: $CODEBUDDY_DIR directory still exists (contains user-added files)"
+    fi
+}
+
+# Execute uninstall
+do_uninstall "$@"

.codex-plugin/README.md

@@ -12,7 +12,7 @@ This directory contains the **Codex plugin manifest** for Everything Claude Code
 
 ## What This Provides
 
-- **125 skills** from `./skills/` — reusable Codex workflows for TDD, security,
+- **156 skills** from `./skills/` — reusable Codex workflows for TDD, security,
   code review, architecture, and more
 - **6 MCP servers** — GitHub, Context7, Exa, Memory, Playwright, Sequential Thinking
 
@@ -30,6 +30,9 @@ codex plugin install ./
 Run this from the repository root so `./` points to the repo root and `.mcp.json` resolves correctly.
 ```
 
+The installed plugin registers under the short slug `ecc` so tool and command names
+stay below provider length limits.
+
 ## MCP Servers Included
 
 | Server | Purpose |
@@ -45,5 +48,7 @@ Run this from the repository root so `./` points to the repo root and `.mcp.json
 
 - The `skills/` directory at the repo root is shared between Claude Code (`.claude-plugin/`)
   and Codex (`.codex-plugin/`) — same source of truth, no duplication
+- ECC is moving to a skills-first workflow surface. Legacy `commands/` remain for
+  compatibility on harnesses that still expect slash-entry shims.
 - MCP server credentials are inherited from the launching environment (env vars)
 - This manifest does **not** override `~/.codex/config.toml` settings

.codex-plugin/plugin.json

@@ -1,13 +1,13 @@
 {
-  "name": "everything-claude-code",
-  "version": "1.9.0",
-  "description": "Battle-tested Codex workflows — 125 skills, production-ready MCP configs, and agent definitions for TDD, security scanning, code review, and autonomous development.",
+  "name": "ecc",
+  "version": "2.0.0-rc.1",
+  "description": "Battle-tested Codex workflows — 156 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",
     "url": "https://x.com/affaanmustafa"
   },
-  "homepage": "https://github.com/affaan-m/everything-claude-code",
+  "homepage": "https://ecc.tools",
   "repository": "https://github.com/affaan-m/everything-claude-code",
   "license": "MIT",
   "keywords": ["codex", "agents", "skills", "tdd", "code-review", "security", "workflow", "automation"],
@@ -15,16 +15,16 @@
   "mcpServers": "./.mcp.json",
   "interface": {
     "displayName": "Everything Claude Code",
-    "shortDescription": "125 battle-tested skills for TDD, security, code review, and autonomous development.",
-    "longDescription": "Everything Claude Code (ECC) is a community-maintained collection of Codex skills and MCP configs evolved over 10+ months of intensive daily use. It covers TDD workflows, security scanning, code review, architecture decisions, and more — all in one installable plugin.",
+    "shortDescription": "156 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",
     "capabilities": ["Read", "Write"],
-    "websiteURL": "https://github.com/affaan-m/everything-claude-code",
+    "websiteURL": "https://ecc.tools",
     "defaultPrompt": [
       "Use the tdd-workflow skill to write tests before implementation.",
       "Use the security-review skill to scan for OWASP Top 10 vulnerabilities.",
-      "Use the code-review skill to review this PR for correctness and security."
+      "Use the verification-loop skill to verify correctness before shipping changes."
     ]
   }
 }

.codex/config.toml

@@ -101,7 +101,6 @@ approval_policy = "never"
 sandbox_mode = "workspace-write"
 web_search = "live"
 
-[agents]
 [agents]
 # Multi-agent role limits and local role definitions.
 # These map to `.codex/agents/*.toml` and mirror the repo's explorer/reviewer/docs workflow.

.cursor/hooks.json

@@ -1,4 +1,5 @@
 {
+  "version": 1,
   "hooks": {
     "sessionStart": [
       {
@@ -37,7 +38,7 @@
       {
         "command": "node .cursor/hooks/after-file-edit.js",
         "event": "afterFileEdit",
-        "description": "Auto-format, TypeScript check, console.log warning"
+        "description": "Auto-format, TypeScript check, console.log warning, and frontend design-quality reminder"
       }
     ],
     "beforeMCPExecution": [

.cursor/hooks/after-file-edit.js

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-const { readStdin, runExistingHook, transformToClaude } = require('./adapter');
+const { hookEnabled, readStdin, runExistingHook, transformToClaude } = require('./adapter');
 readStdin().then(raw => {
   try {
     const input = JSON.parse(raw);
@@ -8,10 +8,12 @@ readStdin().then(raw => {
     });
     const claudeStr = JSON.stringify(claudeInput);
 
-    // Run format, typecheck, and console.log warning sequentially
-    runExistingHook('post-edit-format.js', claudeStr);
-    runExistingHook('post-edit-typecheck.js', claudeStr);
+    // Accumulate edited paths for batch format+typecheck at stop time
+    runExistingHook('post-edit-accumulator.js', claudeStr);
     runExistingHook('post-edit-console-warn.js', claudeStr);
+    if (hookEnabled('post:edit:design-quality-check', ['standard', 'strict'])) {
+      runExistingHook('design-quality-check.js', claudeStr);
+    }
   } catch {}
   process.stdout.write(raw);
 }).catch(() => process.exit(0));

.gemini/GEMINI.md

@@ -0,0 +1,48 @@
+# ECC for Gemini CLI
+
+This file provides Gemini CLI with the baseline ECC workflow, review standards, and security checks for repositories that install the Gemini target.
+
+## Overview
+
+Everything Claude Code (ECC) is a cross-harness coding system with 36 specialized agents, 142 skills, and 68 commands.
+
+Gemini support is currently focused on a strong project-local instruction layer via `.gemini/GEMINI.md`, plus the shared MCP catalog and package-manager setup assets shipped by the installer.
+
+## Core Workflow
+
+1. Plan before editing large features.
+2. Prefer test-first changes for bug fixes and new functionality.
+3. Review for security before shipping.
+4. Keep changes self-contained, readable, and easy to revert.
+
+## Coding Standards
+
+- Prefer immutable updates over in-place mutation.
+- Keep functions small and files focused.
+- Validate user input at boundaries.
+- Never hardcode secrets.
+- Fail loudly with clear error messages instead of silently swallowing problems.
+
+## Security Checklist
+
+Before any commit:
+
+- No hardcoded API keys, passwords, or tokens
+- All external input validated
+- Parameterized queries for database writes
+- Sanitized HTML output where applicable
+- Authz/authn checked for sensitive paths
+- Error messages scrubbed of sensitive internals
+
+## Delivery Standards
+
+- Use conventional commits: `feat`, `fix`, `refactor`, `docs`, `test`, `chore`, `perf`, `ci`
+- Run targeted verification for touched areas before shipping
+- Prefer contained local implementations over adding new third-party runtime dependencies
+
+## ECC Areas To Reuse
+
+- `AGENTS.md` for repo-wide operating rules
+- `skills/` for deep workflow guidance
+- `commands/` for slash-command patterns worth adapting into prompts/macros
+- `mcp-configs/` for shared connector baselines

.github/dependabot.yml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+  - package-ecosystem: "npm"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 10
+    labels:
+      - "dependencies"
+    groups:
+      minor-and-patch:
+        update-types:
+          - "minor"
+          - "patch"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels:
+      - "dependencies"
+      - "ci"

.github/workflows/ci.yml

@@ -2,7 +2,8 @@ name: CI
 
 on:
   push:
-    branches: [main]
+    branches: [main, 'release/**']
+    tags: ['v*']
   pull_request:
     branches: [main]
 
@@ -34,19 +35,27 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Node.js ${{ matrix.node }}
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: ${{ matrix.node }}
 
       # Package manager setup
       - name: Setup pnpm
-        if: matrix.pm == 'pnpm'
-        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v4
+        if: matrix.pm == 'pnpm' && matrix.node != '18.x'
+        uses: pnpm/action-setup@08c4be7e2e672a47d11bd04269e27e5f3e8529cb # v6.0.0
         with:
-          version: latest
+          # Keep an explicit pnpm major because this repo's packageManager is Yarn.
+          version: 10
+
+      - name: Setup pnpm (via Corepack)
+        if: matrix.pm == 'pnpm' && matrix.node == '18.x'
+        shell: bash
+        run: |
+          corepack enable
+          corepack prepare pnpm@9 --activate
 
       - name: Setup Yarn (via Corepack)
         if: matrix.pm == 'yarn'
@@ -68,7 +77,7 @@ jobs:
 
       - name: Cache npm
         if: matrix.pm == 'npm'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ${{ steps.npm-cache-dir.outputs.dir }}
           key: ${{ runner.os }}-node-${{ matrix.node }}-npm-${{ hashFiles('**/package-lock.json') }}
@@ -79,11 +88,13 @@ jobs:
         if: matrix.pm == 'pnpm'
         id: pnpm-cache-dir
         shell: bash
+        env:
+          COREPACK_ENABLE_STRICT: '0'
         run: echo "dir=$(pnpm store path)" >> $GITHUB_OUTPUT
 
       - name: Cache pnpm
         if: matrix.pm == 'pnpm'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ${{ steps.pnpm-cache-dir.outputs.dir }}
           key: ${{ runner.os }}-node-${{ matrix.node }}-pnpm-${{ hashFiles('**/pnpm-lock.yaml') }}
@@ -104,7 +115,7 @@ jobs:
 
       - name: Cache yarn
         if: matrix.pm == 'yarn'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ${{ steps.yarn-cache-dir.outputs.dir }}
           key: ${{ runner.os }}-node-${{ matrix.node }}-yarn-${{ hashFiles('**/yarn.lock') }}
@@ -113,7 +124,7 @@ jobs:
 
       - name: Cache bun
         if: matrix.pm == 'bun'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ~/.bun/install/cache
           key: ${{ runner.os }}-bun-${{ hashFiles('**/bun.lockb') }}
@@ -130,7 +141,10 @@ jobs:
         run: |
           case "${{ matrix.pm }}" in
             npm) npm ci ;;
-            pnpm) pnpm install --no-frozen-lockfile ;;
+            # pnpm v10 can fail CI on ignored native build scripts
+            # (for example msgpackr-extract) even though this repo is Yarn-native
+            # and pnpm is only exercised here as a compatibility lane.
+            pnpm) pnpm install --config.strict-dep-builds=false --no-frozen-lockfile ;;
             # Yarn Berry (v4+) removed --ignore-engines; engine checking is no longer a core feature
             yarn) yarn install ;;
             bun) bun install ;;
@@ -146,7 +160,7 @@ jobs:
       # Upload test artifacts on failure
       - name: Upload test artifacts
         if: failure()
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: test-results-${{ matrix.os }}-node${{ matrix.node }}-${{ matrix.pm }}
           path: |
@@ -160,10 +174,10 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: '20.x'
 
@@ -190,6 +204,10 @@ jobs:
         run: node scripts/ci/validate-install-manifests.js
         continue-on-error: false
 
+      - name: Validate workflow security
+        run: node scripts/ci/validate-workflow-security.js
+        continue-on-error: false
+
       - name: Validate rules
         run: node scripts/ci/validate-rules.js
         continue-on-error: false
@@ -209,10 +227,10 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: '20.x'
 
@@ -227,10 +245,10 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: '20.x'
 

.github/workflows/maintenance.yml

@@ -15,8 +15,8 @@ jobs:
     name: Check Dependencies
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: '20.x'
       - name: Check for outdated packages
@@ -26,8 +26,8 @@ jobs:
     name: Security Audit
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: '20.x'
       - name: Run security audit
@@ -43,7 +43,7 @@ jobs:
     name: Stale Issues/PRs
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9
+      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f # v10.2.0
         with:
           stale-issue-message: 'This issue is stale due to inactivity.'
           stale-pr-message: 'This PR is stale due to inactivity.'

.github/workflows/monthly-metrics.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Update monthly metrics issue
-        uses: actions/github-script@v7
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const owner = context.repo.owner;
@@ -30,6 +30,10 @@ jobs:
               return match ? Number(match[1]) : null;
             }
 
+            function escapeRegex(value) {
+              return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+            }
+
             function fmt(value) {
               if (value === null || value === undefined) return "n/a";
               return Number(value).toLocaleString("en-US");
@@ -167,14 +171,17 @@ jobs:
             }
 
             const currentBody = issue.body || "";
-            if (currentBody.includes(`| ${monthKey} |`)) {
-              console.log(`Issue #${issue.number} already has snapshot row for ${monthKey}`);
-              return;
-            }
+            const rowPattern = new RegExp(`^\\| ${escapeRegex(monthKey)} \\|.*$`, "m");
 
-            const body = currentBody.includes("| Month (UTC) |")
-              ? `${currentBody.trimEnd()}\n${row}\n`
-              : `${intro}\n${row}\n`;
+            let body;
+            if (rowPattern.test(currentBody)) {
+              body = currentBody.replace(rowPattern, row);
+              console.log(`Refreshed issue #${issue.number} snapshot row for ${monthKey}`);
+            } else {
+              body = currentBody.includes("| Month (UTC) |")
+                ? `${currentBody.trimEnd()}\n${row}\n`
+                : `${intro}\n${row}\n`;
+            }
 
             await github.rest.issues.update({
               owner,

.github/workflows/release.yml

@@ -6,6 +6,7 @@ on:
 
 permissions:
   contents: write
+  id-token: write
 
 jobs:
   release:
@@ -14,31 +15,59 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
 
+      - name: Setup Node.js
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: '20.x'
+          registry-url: 'https://registry.npmjs.org'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Verify OpenCode package payload
+        run: node tests/scripts/build-opencode.test.js
+
       - name: Validate version tag
         run: |
-          if ! [[ "${REF_NAME}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-            echo "Invalid version tag format. Expected vX.Y.Z"
+          if ! [[ "${REF_NAME}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z.-]+)?$ ]]; then
+            echo "Invalid version tag format. Expected vX.Y.Z or vX.Y.Z-prerelease"
             exit 1
           fi
 
         env:
           REF_NAME: ${{ github.ref_name }}
-      - name: Verify plugin.json version matches tag
+      - name: Verify package version matches tag
         env:
           TAG_NAME: ${{ github.ref_name }}
         run: |
           TAG_VERSION="${TAG_NAME#v}"
-          PLUGIN_VERSION=$(grep -oE '"version": *"[^"]*"' .claude-plugin/plugin.json | grep -oE '[0-9]+\.[0-9]+\.[0-9]+')
-          if [ "$TAG_VERSION" != "$PLUGIN_VERSION" ]; then
-            echo "::error::Tag version ($TAG_VERSION) does not match plugin.json version ($PLUGIN_VERSION)"
+          PACKAGE_VERSION=$(node -p "require('./package.json').version")
+          if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
+            echo "::error::Tag version ($TAG_VERSION) does not match package.json version ($PACKAGE_VERSION)"
             echo "Run: ./scripts/release.sh $TAG_VERSION"
             exit 1
           fi
 
+      - name: Verify release metadata stays in sync
+        run: node tests/plugin-manifest.test.js
+
+      - name: Check npm publish state
+        id: npm_publish_state
+        run: |
+          PACKAGE_NAME=$(node -p "require('./package.json').name")
+          PACKAGE_VERSION=$(node -p "require('./package.json').version")
+          NPM_DIST_TAG=$(node -p "require('./package.json').version.includes('-') ? 'next' : 'latest'")
+          if npm view "${PACKAGE_NAME}@${PACKAGE_VERSION}" version >/dev/null 2>&1; then
+            echo "already_published=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "already_published=false" >> "$GITHUB_OUTPUT"
+          fi
+          echo "dist_tag=${NPM_DIST_TAG}" >> "$GITHUB_OUTPUT"
+
       - name: Generate release highlights
         id: highlights
         env:
@@ -59,11 +88,21 @@ jobs:
           - Improved release-note generation and changelog hygiene
 
           ### Notes
+          - npm package: \`ecc-universal\`
+          - Claude marketplace/plugin identifier: \`everything-claude-code@everything-claude-code\`
           - For migration tips and compatibility notes, see README and CHANGELOG.
           EOF
 
       - name: Create GitHub Release
-        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # v2
+        uses: softprops/action-gh-release@b4309332981a82ec1c5618f44dd2e27cc8bfbfda # v3.0.0
         with:
           body_path: release_body.md
           generate_release_notes: true
+          prerelease: ${{ contains(github.ref_name, '-') }}
+          make_latest: ${{ contains(github.ref_name, '-') && 'false' || 'true' }}
+
+      - name: Publish npm package
+        if: steps.npm_publish_state.outputs.already_published != 'true'
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: npm publish --access public --provenance --tag "${{ steps.npm_publish_state.outputs.dist_tag }}"

.github/workflows/reusable-release.yml

@@ -12,9 +12,24 @@ on:
         required: false
         type: boolean
         default: true
+    secrets:
+      NPM_TOKEN:
+        required: false
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Version tag to release or republish (e.g., v2.0.0-rc.1)'
+        required: true
+        type: string
+      generate-notes:
+        description: 'Auto-generate release notes'
+        required: false
+        type: boolean
+        default: true
 
 permissions:
   contents: write
+  id-token: write
 
 jobs:
   release:
@@ -23,17 +38,60 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0
+          ref: ${{ inputs.tag }}
+
+      - name: Setup Node.js
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        with:
+          node-version: '20.x'
+          registry-url: 'https://registry.npmjs.org'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Verify OpenCode package payload
+        run: node tests/scripts/build-opencode.test.js
 
       - name: Validate version tag
+        env:
+          INPUT_TAG: ${{ inputs.tag }}
         run: |
-          if ! [[ "${{ inputs.tag }}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-            echo "Invalid version tag format. Expected vX.Y.Z"
+          if ! [[ "$INPUT_TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z.-]+)?$ ]]; then
+            echo "Invalid version tag format. Expected vX.Y.Z or vX.Y.Z-prerelease"
             exit 1
           fi
 
+      - name: Verify package version matches tag
+        env:
+          INPUT_TAG: ${{ inputs.tag }}
+        run: |
+          TAG_VERSION="${INPUT_TAG#v}"
+          PACKAGE_VERSION=$(node -p "require('./package.json').version")
+          if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
+            echo "::error::Tag version ($TAG_VERSION) does not match package.json version ($PACKAGE_VERSION)"
+            echo "Run: ./scripts/release.sh $TAG_VERSION"
+            exit 1
+          fi
+
+      - name: Verify release metadata stays in sync
+        run: node tests/plugin-manifest.test.js
+
+      - name: Check npm publish state
+        id: npm_publish_state
+        run: |
+          PACKAGE_NAME=$(node -p "require('./package.json').name")
+          PACKAGE_VERSION=$(node -p "require('./package.json').version")
+          NPM_DIST_TAG=$(node -p "require('./package.json').version.includes('-') ? 'next' : 'latest'")
+          if npm view "${PACKAGE_NAME}@${PACKAGE_VERSION}" version >/dev/null 2>&1; then
+            echo "already_published=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "already_published=false" >> "$GITHUB_OUTPUT"
+          fi
+          echo "dist_tag=${NPM_DIST_TAG}" >> "$GITHUB_OUTPUT"
+
       - name: Generate release highlights
         env:
           TAG_NAME: ${{ inputs.tag }}
@@ -46,11 +104,23 @@ jobs:
           - Harness reliability and cross-platform compatibility
           - Eval-driven quality improvements
           - Better workflow and operator ergonomics
+
+          ### Package Notes
+          - npm package: \`ecc-universal\`
+          - Claude marketplace/plugin identifier: \`everything-claude-code@everything-claude-code\`
           EOF
 
       - name: Create GitHub Release
-        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # v2
+        uses: softprops/action-gh-release@b4309332981a82ec1c5618f44dd2e27cc8bfbfda # v3.0.0
         with:
           tag_name: ${{ inputs.tag }}
           body_path: release_body.md
           generate_release_notes: ${{ inputs.generate-notes }}
+          prerelease: ${{ contains(inputs.tag, '-') }}
+          make_latest: ${{ contains(inputs.tag, '-') && 'false' || 'true' }}
+
+      - name: Publish npm package
+        if: steps.npm_publish_state.outputs.already_published != 'true'
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: npm publish --access public --provenance --tag "${{ steps.npm_publish_state.outputs.dist_tag }}"

.github/workflows/reusable-test.yml

@@ -27,18 +27,26 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: ${{ inputs.node-version }}
 
       - name: Setup pnpm
-        if: inputs.package-manager == 'pnpm'
-        uses: pnpm/action-setup@fc06bc1257f339d1d5d8b3a19a8cae5388b55320 # v4
+        if: inputs.package-manager == 'pnpm' && inputs.node-version != '18.x'
+        uses: pnpm/action-setup@08c4be7e2e672a47d11bd04269e27e5f3e8529cb # v6.0.0
         with:
-          version: latest
+          # Keep an explicit pnpm major because this repo's packageManager is Yarn.
+          version: 10
+
+      - name: Setup pnpm (via Corepack)
+        if: inputs.package-manager == 'pnpm' && inputs.node-version == '18.x'
+        shell: bash
+        run: |
+          corepack enable
+          corepack prepare pnpm@9 --activate
 
       - name: Setup Yarn (via Corepack)
         if: inputs.package-manager == 'yarn'
@@ -59,7 +67,7 @@ jobs:
 
       - name: Cache npm
         if: inputs.package-manager == 'npm'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ${{ steps.npm-cache-dir.outputs.dir }}
           key: ${{ runner.os }}-node-${{ inputs.node-version }}-npm-${{ hashFiles('**/package-lock.json') }}
@@ -70,11 +78,13 @@ jobs:
         if: inputs.package-manager == 'pnpm'
         id: pnpm-cache-dir
         shell: bash
+        env:
+          COREPACK_ENABLE_STRICT: '0'
         run: echo "dir=$(pnpm store path)" >> $GITHUB_OUTPUT
 
       - name: Cache pnpm
         if: inputs.package-manager == 'pnpm'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ${{ steps.pnpm-cache-dir.outputs.dir }}
           key: ${{ runner.os }}-node-${{ inputs.node-version }}-pnpm-${{ hashFiles('**/pnpm-lock.yaml') }}
@@ -95,7 +105,7 @@ jobs:
 
       - name: Cache yarn
         if: inputs.package-manager == 'yarn'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ${{ steps.yarn-cache-dir.outputs.dir }}
           key: ${{ runner.os }}-node-${{ inputs.node-version }}-yarn-${{ hashFiles('**/yarn.lock') }}
@@ -104,7 +114,7 @@ jobs:
 
       - name: Cache bun
         if: inputs.package-manager == 'bun'
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4
+        uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
         with:
           path: ~/.bun/install/cache
           key: ${{ runner.os }}-bun-${{ hashFiles('**/bun.lockb') }}
@@ -120,7 +130,10 @@ jobs:
         run: |
           case "${{ inputs.package-manager }}" in
             npm) npm ci ;;
-            pnpm) pnpm install --no-frozen-lockfile ;;
+            # pnpm v10 can fail CI on ignored native build scripts
+            # (for example msgpackr-extract) even though this repo is Yarn-native
+            # and pnpm is only exercised here as a compatibility lane.
+            pnpm) pnpm install --config.strict-dep-builds=false --no-frozen-lockfile ;;
             # Yarn Berry (v4+) removed --ignore-engines; engine checking is no longer a core feature
             yarn) yarn install ;;
             bun) bun install ;;
@@ -134,7 +147,7 @@ jobs:
 
       - name: Upload test artifacts
         if: failure()
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: test-results-${{ inputs.os }}-node${{ inputs.node-version }}-${{ inputs.package-manager }}
           path: |

.github/workflows/reusable-validate.yml

@@ -17,10 +17,10 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
         with:
           node-version: ${{ inputs.node-version }}
 
@@ -42,6 +42,9 @@ jobs:
       - name: Validate install manifests
         run: node scripts/ci/validate-install-manifests.js
 
+      - name: Validate workflow security
+        run: node scripts/ci/validate-workflow-security.js
+
       - name: Validate rules
         run: node scripts/ci/validate-rules.js
 

.gitignore

@@ -75,6 +75,9 @@ examples/sessions/*.tmp
 # Local drafts
 marketing/
 .dmux/
+.dmux-hooks/
+.claude/worktrees/
+.claude/scheduled_tasks.lock
 
 # Temporary files
 tmp/

.kiro/install.sh

@@ -1,139 +1,143 @@
-#!/bin/bash
-#
-# ECC Kiro Installer
-# Installs Everything Claude Code workflows into a Kiro project.
-#
-# Usage:
-#   ./install.sh              # Install to current directory
-#   ./install.sh /path/to/dir # Install to specific directory
-#   ./install.sh ~            # Install globally to ~/.kiro/
-#
-
-set -euo pipefail
-
-# When globs match nothing, expand to empty list instead of the literal pattern
-shopt -s nullglob
-
-# Resolve the directory where this script lives (the repo root)
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-SOURCE_KIRO="$SCRIPT_DIR/.kiro"
-
-# Target directory: argument or current working directory
-TARGET="${1:-.}"
-
-# Expand ~ to $HOME
-if [ "$TARGET" = "~" ] || [[ "$TARGET" == "~/"* ]]; then
-  TARGET="${TARGET/#\~/$HOME}"
-fi
-
-# Resolve to absolute path
-TARGET="$(cd "$TARGET" 2>/dev/null && pwd || echo "$TARGET")"
-
-echo "ECC Kiro Installer"
-echo "=================="
-echo ""
-echo "Source:  $SOURCE_KIRO"
-echo "Target:  $TARGET/.kiro/"
-echo ""
-
-# Subdirectories to create and populate
-SUBDIRS="agents skills steering hooks scripts settings"
-
-# Create all required .kiro/ subdirectories
-for dir in $SUBDIRS; do
-  mkdir -p "$TARGET/.kiro/$dir"
-done
-
-# Counters for summary
-agents=0; skills=0; steering=0; hooks=0; scripts=0; settings=0
-
-# Copy agents (JSON for CLI, Markdown for IDE)
-if [ -d "$SOURCE_KIRO/agents" ]; then
-  for f in "$SOURCE_KIRO/agents"/*.json "$SOURCE_KIRO/agents"/*.md; do
-    [ -f "$f" ] || continue
-    local_name=$(basename "$f")
-    if [ ! -f "$TARGET/.kiro/agents/$local_name" ]; then
-      cp "$f" "$TARGET/.kiro/agents/" 2>/dev/null || true
-      agents=$((agents + 1))
-    fi
-  done
-fi
-
-# Copy skills (directories with SKILL.md)
-if [ -d "$SOURCE_KIRO/skills" ]; then
-  for d in "$SOURCE_KIRO/skills"/*/; do
-    [ -d "$d" ] || continue
-    skill_name="$(basename "$d")"
-    if [ ! -d "$TARGET/.kiro/skills/$skill_name" ]; then
-      mkdir -p "$TARGET/.kiro/skills/$skill_name"
-      cp "$d"* "$TARGET/.kiro/skills/$skill_name/" 2>/dev/null || true
-      skills=$((skills + 1))
-    fi
-  done
-fi
-
-# Copy steering files (markdown)
-if [ -d "$SOURCE_KIRO/steering" ]; then
-  for f in "$SOURCE_KIRO/steering"/*.md; do
-    local_name=$(basename "$f")
-    if [ ! -f "$TARGET/.kiro/steering/$local_name" ]; then
-      cp "$f" "$TARGET/.kiro/steering/" 2>/dev/null || true
-      steering=$((steering + 1))
-    fi
-  done
-fi
-
-# Copy hooks (.kiro.hook files and README)
-if [ -d "$SOURCE_KIRO/hooks" ]; then
-  for f in "$SOURCE_KIRO/hooks"/*.kiro.hook "$SOURCE_KIRO/hooks"/*.md; do
-    [ -f "$f" ] || continue
-    local_name=$(basename "$f")
-    if [ ! -f "$TARGET/.kiro/hooks/$local_name" ]; then
-      cp "$f" "$TARGET/.kiro/hooks/" 2>/dev/null || true
-      hooks=$((hooks + 1))
-    fi
-  done
-fi
-
-# Copy scripts (shell scripts) and make executable
-if [ -d "$SOURCE_KIRO/scripts" ]; then
-  for f in "$SOURCE_KIRO/scripts"/*.sh; do
-    local_name=$(basename "$f")
-    if [ ! -f "$TARGET/.kiro/scripts/$local_name" ]; then
-      cp "$f" "$TARGET/.kiro/scripts/" 2>/dev/null || true
-      chmod +x "$TARGET/.kiro/scripts/$local_name" 2>/dev/null || true
-      scripts=$((scripts + 1))
-    fi
-  done
-fi
-
-# Copy settings (example files)
-if [ -d "$SOURCE_KIRO/settings" ]; then
-  for f in "$SOURCE_KIRO/settings"/*; do
-    [ -f "$f" ] || continue
-    local_name=$(basename "$f")
-    if [ ! -f "$TARGET/.kiro/settings/$local_name" ]; then
-      cp "$f" "$TARGET/.kiro/settings/" 2>/dev/null || true
-      settings=$((settings + 1))
-    fi
-  done
-fi
-
-# Installation summary
-echo "Installation complete!"
-echo ""
-echo "Components installed:"
-echo "  Agents:    $agents"
-echo "  Skills:    $skills"
-echo "  Steering:  $steering"
-echo "  Hooks:     $hooks"
-echo "  Scripts:   $scripts"
-echo "  Settings:  $settings"
-echo ""
-echo "Next steps:"
-echo "  1. Open your project in Kiro"
-echo "  2. Agents: Automatic in IDE, /agent swap in CLI"
-echo "  3. Skills: Available via / menu in chat"
-echo "  4. Steering files with 'auto' inclusion load automatically"
-echo "  5. Toggle hooks in the Agent Hooks panel"
-echo "  6. Copy desired MCP servers from .kiro/settings/mcp.json.example to .kiro/settings/mcp.json"
+#!/bin/bash
+#
+# ECC Kiro Installer
+# Installs Everything Claude Code workflows into a Kiro project.
+#
+# Usage:
+#   ./install.sh              # Install to current directory
+#   ./install.sh /path/to/dir # Install to specific directory
+#   ./install.sh ~            # Install globally to ~/.kiro/
+#
+
+set -euo pipefail
+
+# When globs match nothing, expand to empty list instead of the literal pattern
+shopt -s nullglob
+
+# Resolve the directory where this script lives
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# The script lives inside .kiro/, so SCRIPT_DIR *is* the source.
+# If invoked from the repo root (e.g., .kiro/install.sh), SCRIPT_DIR already
+# points to the .kiro directory — no need to append /.kiro again.
+SOURCE_KIRO="$SCRIPT_DIR"
+
+# Target directory: argument or current working directory
+TARGET="${1:-.}"
+
+# Expand ~ to $HOME
+if [ "$TARGET" = "~" ] || [[ "$TARGET" == "~/"* ]]; then
+  TARGET="${TARGET/#\~/$HOME}"
+fi
+
+# Resolve to absolute path
+TARGET="$(cd "$TARGET" 2>/dev/null && pwd || echo "$TARGET")"
+
+echo "ECC Kiro Installer"
+echo "=================="
+echo ""
+echo "Source:  $SOURCE_KIRO"
+echo "Target:  $TARGET/.kiro/"
+echo ""
+
+# Subdirectories to create and populate
+SUBDIRS="agents skills steering hooks scripts settings"
+
+# Create all required .kiro/ subdirectories
+for dir in $SUBDIRS; do
+  mkdir -p "$TARGET/.kiro/$dir"
+done
+
+# Counters for summary
+agents=0; skills=0; steering=0; hooks=0; scripts=0; settings=0
+
+# Copy agents (JSON for CLI, Markdown for IDE)
+if [ -d "$SOURCE_KIRO/agents" ]; then
+  for f in "$SOURCE_KIRO/agents"/*.json "$SOURCE_KIRO/agents"/*.md; do
+    [ -f "$f" ] || continue
+    local_name=$(basename "$f")
+    if [ ! -f "$TARGET/.kiro/agents/$local_name" ]; then
+      cp "$f" "$TARGET/.kiro/agents/" 2>/dev/null || true
+      agents=$((agents + 1))
+    fi
+  done
+fi
+
+# Copy skills (directories with SKILL.md)
+if [ -d "$SOURCE_KIRO/skills" ]; then
+  for d in "$SOURCE_KIRO/skills"/*/; do
+    [ -d "$d" ] || continue
+    skill_name="$(basename "$d")"
+    if [ ! -d "$TARGET/.kiro/skills/$skill_name" ]; then
+      mkdir -p "$TARGET/.kiro/skills/$skill_name"
+      cp "$d"* "$TARGET/.kiro/skills/$skill_name/" 2>/dev/null || true
+      skills=$((skills + 1))
+    fi
+  done
+fi
+
+# Copy steering files (markdown)
+if [ -d "$SOURCE_KIRO/steering" ]; then
+  for f in "$SOURCE_KIRO/steering"/*.md; do
+    local_name=$(basename "$f")
+    if [ ! -f "$TARGET/.kiro/steering/$local_name" ]; then
+      cp "$f" "$TARGET/.kiro/steering/" 2>/dev/null || true
+      steering=$((steering + 1))
+    fi
+  done
+fi
+
+# Copy hooks (.kiro.hook files and README)
+if [ -d "$SOURCE_KIRO/hooks" ]; then
+  for f in "$SOURCE_KIRO/hooks"/*.kiro.hook "$SOURCE_KIRO/hooks"/*.md; do
+    [ -f "$f" ] || continue
+    local_name=$(basename "$f")
+    if [ ! -f "$TARGET/.kiro/hooks/$local_name" ]; then
+      cp "$f" "$TARGET/.kiro/hooks/" 2>/dev/null || true
+      hooks=$((hooks + 1))
+    fi
+  done
+fi
+
+# Copy scripts (shell scripts) and make executable
+if [ -d "$SOURCE_KIRO/scripts" ]; then
+  for f in "$SOURCE_KIRO/scripts"/*.sh; do
+    local_name=$(basename "$f")
+    if [ ! -f "$TARGET/.kiro/scripts/$local_name" ]; then
+      cp "$f" "$TARGET/.kiro/scripts/" 2>/dev/null || true
+      chmod +x "$TARGET/.kiro/scripts/$local_name" 2>/dev/null || true
+      scripts=$((scripts + 1))
+    fi
+  done
+fi
+
+# Copy settings (example files)
+if [ -d "$SOURCE_KIRO/settings" ]; then
+  for f in "$SOURCE_KIRO/settings"/*; do
+    [ -f "$f" ] || continue
+    local_name=$(basename "$f")
+    if [ ! -f "$TARGET/.kiro/settings/$local_name" ]; then
+      cp "$f" "$TARGET/.kiro/settings/" 2>/dev/null || true
+      settings=$((settings + 1))
+    fi
+  done
+fi
+
+# Installation summary
+echo "Installation complete!"
+echo ""
+echo "Components installed:"
+echo "  Agents:    $agents"
+echo "  Skills:    $skills"
+echo "  Steering:  $steering"
+echo "  Hooks:     $hooks"
+echo "  Scripts:   $scripts"
+echo "  Settings:  $settings"
+echo ""
+echo "Next steps:"
+echo "  1. Open your project in Kiro"
+echo "  2. Agents: Automatic in IDE, /agent swap in CLI"
+echo "  3. Skills: Available via / menu in chat"
+echo "  4. Steering files with 'auto' inclusion load automatically"
+echo "  5. Toggle hooks in the Agent Hooks panel"
+echo "  6. Copy desired MCP servers from .kiro/settings/mcp.json.example to .kiro/settings/mcp.json"

.mcp.json

@@ -2,7 +2,7 @@
   "mcpServers": {
     "github": {
       "command": "npx",
-      "args": ["-y", "@modelcontextprotocol/server-github"]
+      "args": ["-y", "@modelcontextprotocol/server-github@2025.4.8"]
     },
     "context7": {
       "command": "npx",
@@ -14,15 +14,15 @@
     },
     "memory": {
       "command": "npx",
-      "args": ["-y", "@modelcontextprotocol/server-memory"]
+      "args": ["-y", "@modelcontextprotocol/server-memory@2026.1.26"]
     },
     "playwright": {
       "command": "npx",
-      "args": ["-y", "@playwright/mcp@0.0.68", "--extension"]
+      "args": ["-y", "@playwright/mcp@0.0.69", "--extension"]
     },
     "sequential-thinking": {
       "command": "npx",
-      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
+      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking@2025.12.18"]
     }
   }
 }

.opencode/.npmignore

@@ -0,0 +1,2 @@
+node_modules
+bun.lock

.opencode/MIGRATION.md

@@ -184,7 +184,7 @@ Create a detailed implementation plan for: {input}
 ```markdown
 ---
 description: Create implementation plan
-agent: planner
+agent: everything-claude-code:planner
 ---
 
 Create a detailed implementation plan for: $ARGUMENTS

.opencode/commands/build-fix.md

@@ -1,6 +1,6 @@
 ---
 description: Fix build and TypeScript errors with minimal changes
-agent: build-error-resolver
+agent: everything-claude-code:build-error-resolver
 subtask: true
 ---