fix: retire legacy command shims from default surface

.claude-plugin/marketplace.json

@@ -11,7 +11,7 @@
     {
       "name": "everything-claude-code",
       "source": "./",
-      "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",
+      "description": "The most comprehensive Claude Code plugin — 48 agents, 184 skills, 68 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning",
       "version": "2.0.0-rc.1",
       "author": {
         "name": "Affaan Mustafa",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "everything-claude-code",
   "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",
+  "description": "Battle-tested Claude Code plugin for engineering teams — 48 agents, 184 skills, 68 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"

AGENTS.md

@@ -1,6 +1,6 @@
 # Everything Claude Code (ECC) — Agent Instructions
 
-This is a **production-ready AI coding plugin** providing 48 specialized agents, 184 skills, 80 commands, and automated hook workflows for software development.
+This is a **production-ready AI coding plugin** providing 48 specialized agents, 184 skills, 68 commands, and automated hook workflows for software development.
 
 **Version:** 2.0.0-rc.1
 
@@ -147,7 +147,7 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
 ```
 agents/          — 48 specialized subagents
 skills/          — 184 workflow skills and domain knowledge
-commands/        — 80 slash commands
+commands/        — 68 slash commands
 hooks/           — Trigger-based automations
 rules/           — Always-follow guidelines (common + per-language)
 scripts/         — Cross-platform Node.js utilities

README.md

@@ -89,7 +89,7 @@ This repo is the raw code only. The guides explain everything.
 ### v2.0.0-rc.1 — Surface Refresh, Operator Workflows, and ECC 2.0 Alpha (Apr 2026)
 
 - **Dashboard GUI** — New Tkinter-based desktop application (`ecc_dashboard.py` or `npm run dashboard`) with dark/light theme toggle, font customization, and project logo in header and taskbar.
-- **Public surface synced to the live repo** — metadata, catalog counts, plugin manifests, and install-facing docs now match the actual OSS surface: 38 agents, 156 skills, and 72 legacy command shims.
+- **Public surface synced to the live repo** — metadata, catalog counts, plugin manifests, and install-facing docs now match the actual OSS surface: 48 agents, 184 skills, and 68 legacy command shims.
 - **Operator and outbound workflow expansion** — `brand-voice`, `social-graph-ranker`, `connections-optimizer`, `customer-billing-ops`, `ecc-tools-cost-audit`, `google-workspace-ops`, `project-flow-ops`, and `workspace-surface-audit` round out the operator lane.
 - **Media and launch tooling** — `manim-video`, `remotion-video-creation`, and upgraded social publishing surfaces make technical explainers and launch content part of the same system.
 - **Framework and product surface growth** — `nestjs-patterns`, richer Codex/OpenCode install surfaces, and expanded cross-harness packaging keep the repo usable beyond Claude Code alone.
@@ -312,7 +312,7 @@ If you stacked methods, clean up in this order:
 /plugin list everything-claude-code@everything-claude-code
 ```
 
-**That's it!** You now have access to 48 agents, 184 skills, and 80 legacy command shims.
+**That's it!** You now have access to 48 agents, 184 skills, and 68 legacy command shims.
 
 ### Dashboard GUI
 
@@ -499,17 +499,15 @@ everything-claude-code/
 |   |-- autonomous-loops/           # Autonomous loop patterns: sequential pipelines, PR loops, DAG orchestration (NEW)
 |   |-- plankton-code-quality/      # Write-time code quality enforcement with Plankton hooks (NEW)
 |
-|-- commands/         # Legacy slash-entry shims; prefer skills/
+|-- commands/         # Maintained slash-entry compatibility; prefer skills/
-|   |-- tdd.md              # /tdd - Test-driven development
 |   |-- plan.md             # /plan - Implementation planning
-|   |-- e2e.md              # /e2e - E2E test generation
 |   |-- code-review.md      # /code-review - Quality review
 |   |-- build-fix.md        # /build-fix - Fix build errors
 |   |-- refactor-clean.md   # /refactor-clean - Dead code removal
+|   |-- quality-gate.md     # /quality-gate - Verification gate
 |   |-- learn.md            # /learn - Extract patterns mid-session (Longform Guide)
 |   |-- learn-eval.md       # /learn-eval - Extract, evaluate, and save patterns (NEW)
 |   |-- checkpoint.md       # /checkpoint - Save verification state (Longform Guide)
-|   |-- verify.md           # /verify - Run verification loop (Longform Guide)
 |   |-- setup-pm.md         # /setup-pm - Configure package manager
 |   |-- go-review.md        # /go-review - Go code review (NEW)
 |   |-- go-test.md          # /go-test - Go TDD workflow (NEW)
@@ -526,13 +524,17 @@ everything-claude-code/
 |   |-- multi-backend.md    # /multi-backend - Backend multi-service orchestration (NEW)
 |   |-- multi-frontend.md   # /multi-frontend - Frontend multi-service orchestration (NEW)
 |   |-- multi-workflow.md   # /multi-workflow - General multi-service workflows (NEW)
-|   |-- orchestrate.md      # /orchestrate - Multi-agent coordination
 |   |-- sessions.md         # /sessions - Session history management
-|   |-- eval.md             # /eval - Evaluate against criteria
 |   |-- test-coverage.md    # /test-coverage - Test coverage analysis
 |   |-- update-docs.md      # /update-docs - Update documentation
 |   |-- update-codemaps.md  # /update-codemaps - Update codemaps
 |   |-- python-review.md    # /python-review - Python code review (NEW)
+|-- legacy-command-shims/   # Opt-in archive for retired shims such as /tdd and /eval
+|   |-- tdd.md              # /tdd - Prefer the tdd-workflow skill
+|   |-- e2e.md              # /e2e - Prefer the e2e-testing skill
+|   |-- eval.md             # /eval - Prefer the eval-harness skill
+|   |-- verify.md           # /verify - Prefer the verification-loop skill
+|   |-- orchestrate.md      # /orchestrate - Prefer dmux-workflows or multi-workflow
 |
 |-- rules/            # Always-follow guidelines (copy to ~/.claude/rules/)
 |   |-- README.md            # Structure overview and installation guide
@@ -795,9 +797,12 @@ cp -r everything-claude-code/skills/search-first ~/.claude/skills/
 # cp -r everything-claude-code/skills/$s ~/.claude/skills/
 # done
 
-# Optional: keep legacy slash-command compatibility during migration
+# Optional: keep maintained slash-command compatibility during migration
 mkdir -p ~/.claude/commands
 cp everything-claude-code/commands/*.md ~/.claude/commands/
+
+# Retired shims live in legacy-command-shims/commands/.
+# Copy individual files from there only if you still need old names such as /tdd.
 ```
 
 #### Install hooks
@@ -857,7 +862,7 @@ You are a senior code reviewer...
 
 ### Skills
 
-Skills are the primary workflow surface. They can be invoked directly, suggested automatically, and reused by agents. ECC still ships `commands/` during migration, but new workflow development should land in `skills/` first.
+Skills are the primary workflow surface. They can be invoked directly, suggested automatically, and reused by agents. ECC still ships maintained `commands/` during migration, while retired short-name shims live under `legacy-command-shims/` for explicit opt-in only. New workflow development should land in `skills/` first.
 
 ```markdown
 # TDD Workflow
@@ -903,16 +908,16 @@ See [`rules/README.md`](rules/README.md) for installation and structure details.
 
 ## Which Agent Should I Use?
 
-Not sure where to start? Use this quick reference. Skills are the canonical workflow surface; slash entries below are the compatibility form most users already know.
+Not sure where to start? Use this quick reference. Skills are the canonical workflow surface; maintained slash entries stay available for command-first workflows.
 
-| I want to... | Use this command | Agent used |
+| I want to... | Use this surface | Agent used |
 |--------------|-----------------|------------|
 | Plan a new feature | `/ecc:plan "Add auth"` | planner |
 | Design system architecture | `/ecc:plan` + architect agent | architect |
-| Write code with tests first | `/tdd` | tdd-guide |
+| Write code with tests first | `tdd-workflow` skill | tdd-guide |
 | Review code I just wrote | `/code-review` | code-reviewer |
 | Fix a failing build | `/build-fix` | build-error-resolver |
-| Run end-to-end tests | `/e2e` | e2e-runner |
+| Run end-to-end tests | `e2e-testing` skill | e2e-runner |
 | Find security vulnerabilities | `/security-scan` | security-reviewer |
 | Remove dead code | `/refactor-clean` | refactor-cleaner |
 | Update documentation | `/update-docs` | doc-updater |
@@ -923,19 +928,19 @@ Not sure where to start? Use this quick reference. Skills are the canonical work
 
 ### Common Workflows
 
-Slash forms below are shown because they are still the fastest familiar entrypoint. Under the hood, ECC is shifting these workflows toward skills-first definitions.
+Slash forms below are shown where they remain part of the maintained command surface. Retired short-name shims such as `/tdd` and `/eval` live in `legacy-command-shims/` for explicit opt-in only.
 
 **Starting a new feature:**
 ```
 /ecc:plan "Add user authentication with OAuth"
                                               → planner creates implementation blueprint
-/tdd                                          → tdd-guide enforces write-tests-first
+tdd-workflow skill                            → tdd-guide enforces write-tests-first
 /code-review                                  → code-reviewer checks your work
 ```
 
 **Fixing a bug:**
 ```
-/tdd                                          → tdd-guide: write a failing test that reproduces it
+tdd-workflow skill                            → tdd-guide: write a failing test that reproduces it
                                               → implement the fix, verify test passes
 /code-review                                  → code-reviewer: catch regressions
 ```
@@ -943,7 +948,7 @@ Slash forms below are shown because they are still the fastest familiar entrypoi
 **Preparing for production:**
 ```
 /security-scan                                → security-reviewer: OWASP Top 10 audit
-/e2e                                          → e2e-runner: critical user flow tests
+e2e-testing skill                             → e2e-runner: critical user flow tests
 /test-coverage                                → verify 80%+ coverage
 ```
 
@@ -1279,7 +1284,7 @@ The configuration is automatically detected from `.opencode/opencode.json`.
 | Feature | Claude Code | OpenCode | Status |
 |---------|-------------|----------|--------|
 | Agents | PASS: 48 agents | PASS: 12 agents | **Claude Code leads** |
-| Commands | PASS: 80 commands | PASS: 31 commands | **Claude Code leads** |
+| Commands | PASS: 68 commands | PASS: 31 commands | **Claude Code leads** |
 | Skills | PASS: 184 skills | PASS: 37 skills | **Claude Code leads** |
 | Hooks | PASS: 8 event types | PASS: 11 events | **OpenCode has more!** |
 | Rules | PASS: 29 rules | PASS: 13 instructions | **Claude Code leads** |
@@ -1300,21 +1305,17 @@ OpenCode's plugin system is MORE sophisticated than Claude Code with 20+ event t
 
 **Additional OpenCode events**: `file.edited`, `file.watcher.updated`, `message.updated`, `lsp.client.diagnostics`, `tui.toast.show`, and more.
 
-### Available Slash Entry Shims (31+)
+### Maintained Slash Entries
 
 | Command | Description |
 |---------|-------------|
 | `/plan` | Create implementation plan |
-| `/tdd` | Enforce TDD workflow |
 | `/code-review` | Review code changes |
 | `/build-fix` | Fix build errors |
-| `/e2e` | Generate E2E tests |
 | `/refactor-clean` | Remove dead code |
-| `/orchestrate` | Multi-agent workflow |
 | `/learn` | Extract patterns from session |
 | `/checkpoint` | Save verification state |
-| `/verify` | Run verification loop |
+| `/quality-gate` | Run the maintained verification gate |
-| `/eval` | Evaluate against criteria |
 | `/update-docs` | Update documentation |
 | `/update-codemaps` | Update codemaps |
 | `/test-coverage` | Analyze coverage |
@@ -1388,7 +1389,7 @@ ECC is the **first plugin to maximize every major AI coding tool**. Here's how e
 | Feature | Claude Code | Cursor IDE | Codex CLI | OpenCode |
 |---------|------------|------------|-----------|----------|
 | **Agents** | 48 | Shared (AGENTS.md) | Shared (AGENTS.md) | 12 |
-| **Commands** | 80 | Shared | Instruction-based | 31 |
+| **Commands** | 68 | Shared | Instruction-based | 31 |
 | **Skills** | 184 | Shared | 10 (native format) | 37 |
 | **Hook Events** | 8 types | 15 types | None yet | 11 types |
 | **Hook Scripts** | 20+ scripts | 16 scripts (DRY adapter) | N/A | Plugin hooks |

README.zh-CN.md

@@ -160,7 +160,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
 /plugin list everything-claude-code@everything-claude-code
 ```
 
-**完成！** 你现在可以使用 48 个代理、184 个技能和 80 个命令。
+**完成！** 你现在可以使用 48 个代理、184 个技能和 68 个命令。
 
 ### multi-* 命令需要额外配置
 
@@ -330,17 +330,15 @@ everything-claude-code/
 |   |-- autonomous-loops/           # 自主循环模式：顺序流水线、PR 循环、DAG 编排（新增）
 |   |-- plankton-code-quality/      # 基于 Plankton 钩子的实时代码质量管控（新增）
 |
-|-- commands/         # 传统斜杠命令兼容层；优先使用 skills/
+|-- commands/         # 维护中的斜杠命令兼容层；优先使用 skills/
-|   |-- tdd.md              # /tdd - 测试驱动开发
 |   |-- plan.md             # /plan - 实现规划
-|   |-- e2e.md              # /e2e - 生成端到端测试
 |   |-- code-review.md      # /code-review - 代码质量审查
 |   |-- build-fix.md        # /build-fix - 修复构建错误
+|   |-- quality-gate.md     # /quality-gate - 验证门禁
 |   |-- refactor-clean.md   # /refactor-clean - 清理无效代码
 |   |-- learn.md            # /learn - 会话中提取模式（长文本指南）
 |   |-- learn-eval.md       # /learn-eval - 提取、评估并保存模式（新增）
 |   |-- checkpoint.md       # /checkpoint - 保存验证状态（长文本指南）
-|   |-- verify.md           # /verify - 运行验证循环（长文本指南）
 |   |-- setup-pm.md         # /setup-pm - 配置包管理器
 |   |-- go-review.md        # /go-review - Go 代码审查（新增）
 |   |-- go-test.md          # /go-test - Go TDD 工作流（新增）
@@ -357,13 +355,17 @@ everything-claude-code/
 |   |-- multi-backend.md    # /multi-backend - 后端多服务编排（新增）
 |   |-- multi-frontend.md   # /multi-frontend - 前端多服务编排（新增）
 |   |-- multi-workflow.md   # /multi-workflow - 通用多服务工作流（新增）
-|   |-- orchestrate.md      # /orchestrate - 多智能体协同调度
 |   |-- sessions.md         # /sessions - 会话历史管理
-|   |-- eval.md             # /eval - 按标准评估
 |   |-- test-coverage.md    # /test-coverage - 测试覆盖率分析
 |   |-- update-docs.md      # /update-docs - 更新文档
 |   |-- update-codemaps.md  # /update-codemaps - 更新代码映射
 |   |-- python-review.md    # /python-review - Python 代码审查（新增）
+|-- legacy-command-shims/   # 已退役短命令的按需归档，例如 /tdd 和 /eval
+|   |-- tdd.md              # /tdd - 优先使用 tdd-workflow 技能
+|   |-- e2e.md              # /e2e - 优先使用 e2e-testing 技能
+|   |-- eval.md             # /eval - 优先使用 eval-harness 技能
+|   |-- verify.md           # /verify - 优先使用 verification-loop 技能
+|   |-- orchestrate.md      # /orchestrate - 优先使用 dmux-workflows 或 multi-workflow
 |
 |-- rules/            # 必须遵守的规范（复制到 ~/.claude/rules/）
 |   |-- README.md            # 结构概览与安装指南
@@ -618,9 +620,12 @@ cp -r everything-claude-code/skills/search-first ~/.claude/skills/
 # cp -r everything-claude-code/skills/$s ~/.claude/skills/
 # done
 
-# 可选：迁移期间保留传统斜杠命令兼容
+# 可选：迁移期间保留维护中的斜杠命令兼容
 mkdir -p ~/.claude/commands
 cp everything-claude-code/commands/*.md ~/.claude/commands/
+
+# 已退役短命令位于 legacy-command-shims/commands/。
+# 仅在仍需要 /tdd 等旧名称时，单独复制对应文件。
 ```
 
 #### 将钩子配置添加到 settings.json

agent.yaml

@@ -144,21 +144,14 @@ skills:
   - visa-doc-translate
   - x-api
 commands:
-  - agent-sort
   - aside
   - auto-update
   - build-fix
   - checkpoint
-  - claw
   - code-review
-  - context-budget
   - cpp-build
   - cpp-review
   - cpp-test
-  - devfleet
-  - docs
-  - e2e
-  - eval
   - evolve
   - feature-dev
   - flutter-build
@@ -192,12 +185,10 @@ commands:
   - multi-frontend
   - multi-plan
   - multi-workflow
-  - orchestrate
   - plan
   - pm2
   - projects
   - promote
-  - prompt-optimize
   - prp-commit
   - prp-implement
   - prp-plan
@@ -209,7 +200,6 @@ commands:
   - refactor-clean
   - resume-session
   - review-pr
-  - rules-distill
   - rust-build
   - rust-review
   - rust-test
@@ -219,11 +209,9 @@ commands:
   - setup-pm
   - skill-create
   - skill-health
-  - tdd
   - test-coverage
   - update-codemaps
   - update-docs
-  - verify
 tags:
   - agent-harness
   - developer-tools

commands/cpp-build.md

@@ -165,7 +165,7 @@ The agent will stop and report if:
 
 - `/cpp-test` - Run tests after build succeeds
 - `/cpp-review` - Review code quality
-- `/verify` - Full verification loop
+- `verification-loop` skill - Full verification loop
 
 ## Related
 

commands/cpp-test.md

@@ -243,7 +243,7 @@ genhtml coverage.info --output-directory coverage_html
 
 - `/cpp-build` - Fix build errors
 - `/cpp-review` - Review code after implementation
-- `/verify` - Run full verification loop
+- `verification-loop` skill - Run full verification loop
 
 ## Related
 

commands/flutter-build.md

@@ -156,7 +156,7 @@ The agent will stop and report if:
 
 - `/flutter-test` — Run tests after build succeeds
 - `/flutter-review` — Review code quality
-- `/verify` — Full verification loop
+- `verification-loop` skill — Full verification loop
 
 ## Related
 

commands/flutter-test.md

@@ -134,7 +134,7 @@ Test Status: PASS ✓
 
 - `/flutter-build` — Fix build errors before running tests
 - `/flutter-review` — Review code after tests pass
-- `/tdd` — Test-driven development workflow
+- `tdd-workflow` skill — Test-driven development workflow
 
 ## Related
 

commands/go-build.md

@@ -175,7 +175,7 @@ The agent will stop and report if:
 
 - `/go-test` - Run tests after build succeeds
 - `/go-review` - Review code quality
-- `/verify` - Full verification loop
+- `verification-loop` skill - Full verification loop
 
 ## Related
 

commands/go-test.md

@@ -260,7 +260,7 @@ go test -race -cover ./...
 
 - `/go-build` - Fix build errors
 - `/go-review` - Review code after implementation
-- `/verify` - Run full verification loop
+- `verification-loop` skill - Run full verification loop
 
 ## Related
 

commands/jira.md

@@ -55,7 +55,7 @@ Dependencies:
 
 Recommended Next Steps:
 - /plan to create implementation plan
-- /tdd to implement with tests first
+- `tdd-workflow` skill to implement with tests first
 ```
 
 ### `/jira comment <TICKET-KEY>`
@@ -95,7 +95,7 @@ If credentials are missing, stop and direct the user to set them up.
 
 After analyzing a ticket:
 - Use `/plan` to create an implementation plan from the requirements
-- Use `/tdd` to implement with test-driven development
+- Use the `tdd-workflow` skill to implement with test-driven development
 - Use `/code-review` after implementation
 - Use `/jira comment` to post progress back to the ticket
 - Use `/jira transition` to move the ticket when work is complete

commands/kotlin-build.md

@@ -166,7 +166,7 @@ The agent will stop and report if:
 
 - `/kotlin-test` - Run tests after build succeeds
 - `/kotlin-review` - Review code quality
-- `/verify` - Full verification loop
+- `verification-loop` skill - Full verification loop
 
 ## Related
 

commands/kotlin-test.md

@@ -304,7 +304,7 @@ open build/reports/kover/html/index.html
 
 - `/kotlin-build` - Fix build errors
 - `/kotlin-review` - Review code after implementation
-- `/verify` - Run full verification loop
+- `verification-loop` skill - Run full verification loop
 
 ## Related
 

commands/plan.md

@@ -105,7 +105,7 @@ If you want changes, respond with:
 ## Integration with Other Commands
 
 After planning:
-- Use `/tdd` to implement with test-driven development
+- Use the `tdd-workflow` skill to implement with test-driven development
 - Use `/build-fix` if build errors occur
 - Use `/code-review` to review completed implementation
 

commands/python-review.md

@@ -171,7 +171,7 @@ Run: `black app/routes/user.py app/services/auth.py`
 
 ## Integration with Other Commands
 
-- Use `/tdd` first to ensure tests pass
+- Use the `tdd-workflow` skill first to ensure tests pass
 - Use `/code-review` for non-Python specific concerns
 - Use `/python-review` before committing
 - Use `/build-fix` if static analysis tools fail

commands/rust-build.md

@@ -179,7 +179,7 @@ The agent will stop and report if:
 
 - `/rust-test` - Run tests after build succeeds
 - `/rust-review` - Review code quality
-- `/verify` - Full verification loop
+- `verification-loop` skill - Full verification loop
 
 ## Related
 

commands/rust-test.md

@@ -300,7 +300,7 @@ cargo test --no-fail-fast
 
 - `/rust-build` - Fix build errors
 - `/rust-review` - Review code after implementation
-- `/verify` - Run full verification loop
+- `verification-loop` skill - Run full verification loop
 
 ## Related
 

docs/zh-CN/AGENTS.md

@@ -1,6 +1,6 @@
 # Everything Claude Code (ECC) — 智能体指令
 
-这是一个**生产就绪的 AI 编码插件**，提供 48 个专业代理、184 项技能、80 条命令以及自动化钩子工作流，用于软件开发。
+这是一个**生产就绪的 AI 编码插件**，提供 48 个专业代理、184 项技能、68 条命令以及自动化钩子工作流，用于软件开发。
 
 **版本:** 2.0.0-rc.1
 
@@ -148,7 +148,7 @@
 ```
 agents/          — 48 个专业子代理
 skills/          — 184 个工作流技能和领域知识
-commands/        — 80 个斜杠命令
+commands/        — 68 个斜杠命令
 hooks/           — 基于触发的自动化
 rules/           — 始终遵循的指导方针（通用 + 每种语言）
 scripts/         — 跨平台 Node.js 实用工具

docs/zh-CN/README.md

@@ -215,7 +215,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
 /plugin list everything-claude-code@everything-claude-code
 ```
 
-**搞定！** 你现在可以使用 48 个智能体、184 项技能和 80 个命令了。
+**搞定！** 你现在可以使用 48 个智能体、184 项技能和 68 个命令了。
 
 ***
 
@@ -371,17 +371,15 @@ everything-claude-code/
 |   |-- autonomous-loops/           # 自主循环模式：顺序流水线、PR 循环与 DAG 编排（新增）
 |   |-- plankton-code-quality/      # 使用 Plankton hooks 的编写期代码质量控制（新增）
 |
-|-- commands/         # 快速执行的斜杠命令
+|-- commands/         # 维护中的斜杠命令兼容层；优先使用 skills/
-|   |-- tdd.md              # /tdd - 测试驱动开发
 |   |-- plan.md             # /plan - 实现规划
-|   |-- e2e.md              # /e2e - 端到端测试生成
 |   |-- code-review.md      # /code-review - 质量审查
 |   |-- build-fix.md        # /build-fix - 修复构建错误
 |   |-- refactor-clean.md   # /refactor-clean - 无用代码清理
+|   |-- quality-gate.md     # /quality-gate - 验证门禁
 |   |-- learn.md            # /learn - 会话中提取模式（长文指南）
 |   |-- learn-eval.md       # /learn-eval - 提取、评估并保存模式（新增）
 |   |-- checkpoint.md       # /checkpoint - 保存验证状态（长文指南）
-|   |-- verify.md           # /verify - 运行验证循环（长文指南）
 |   |-- setup-pm.md         # /setup-pm - 配置包管理器
 |   |-- go-review.md        # /go-review - Go 代码审查（新增）
 |   |-- go-test.md          # /go-test - Go TDD 工作流（新增）
@@ -397,13 +395,17 @@ everything-claude-code/
 |   |-- multi-backend.md    # /multi-backend - 后端多服务编排（新增）
 |   |-- multi-frontend.md   # /multi-frontend - 前端多服务编排（新增）
 |   |-- multi-workflow.md   # /multi-workflow - 通用多服务工作流（新增）
-|   |-- orchestrate.md      # /orchestrate - 多代理协调
 |   |-- sessions.md         # /sessions - 会话历史管理
-|   |-- eval.md             # /eval - 按标准评估
 |   |-- test-coverage.md    # /test-coverage - 测试覆盖率分析
 |   |-- update-docs.md      # /update-docs - 更新文档
 |   |-- update-codemaps.md  # /update-codemaps - 更新代码映射
 |   |-- python-review.md    # /python-review - Python 代码审查（新增）
+|-- legacy-command-shims/   # 已退役短命令的按需归档，例如 /tdd 和 /eval
+|   |-- tdd.md              # /tdd - 优先使用 tdd-workflow 技能
+|   |-- e2e.md              # /e2e - 优先使用 e2e-testing 技能
+|   |-- eval.md             # /eval - 优先使用 eval-harness 技能
+|   |-- verify.md           # /verify - 优先使用 verification-loop 技能
+|   |-- orchestrate.md      # /orchestrate - 优先使用 dmux-workflows 或 multi-workflow
 |
 |-- rules/            # 必须遵循的规则（复制到 ~/.claude/rules/）
 |   |-- README.md            # 结构说明与安装指南
@@ -654,9 +656,12 @@ cp -r everything-claude-code/rules/python/* ~/.claude/rules/
 cp -r everything-claude-code/rules/golang/* ~/.claude/rules/
 cp -r everything-claude-code/rules/php/* ~/.claude/rules/
 
-# Copy commands
+# Copy maintained commands
 cp everything-claude-code/commands/*.md ~/.claude/commands/
 
+# Retired shims live in legacy-command-shims/commands/.
+# Copy individual files from there only if you still need old names such as /tdd.
+
 # Copy skills (core vs niche)
 # Recommended (new users): core/general skills only
 cp -r everything-claude-code/.agents/skills/* ~/.claude/skills/
@@ -746,16 +751,16 @@ rules/
 
 ## 我应该使用哪个代理？
 
-不确定从哪里开始？使用这个快速参考：
+不确定从哪里开始？使用这个快速参考。技能是规范工作流表面，维护中的斜杠命令保留给偏命令式工作流。
 
-| 我想要... | 使用此命令 | 使用的智能体 |
+| 我想要... | 使用此表面 | 使用的智能体 |
 |--------------|-----------------|------------|
 | 规划新功能 | `/ecc:plan "Add auth"` | planner |
 | 设计系统架构 | `/ecc:plan` + architect agent | architect |
-| 先写测试再写代码 | `/tdd` | tdd-guide |
+| 先写测试再写代码 | `tdd-workflow` 技能 | tdd-guide |
 | 评审我刚写的代码 | `/code-review` | code-reviewer |
 | 修复失败的构建 | `/build-fix` | build-error-resolver |
-| 运行端到端测试 | `/e2e` | e2e-runner |
+| 运行端到端测试 | `e2e-testing` 技能 | e2e-runner |
 | 查找安全漏洞 | `/security-scan` | security-reviewer |
 | 移除死代码 | `/refactor-clean` | refactor-cleaner |
 | 更新文档 | `/update-docs` | doc-updater |
@@ -771,14 +776,14 @@ rules/
 ```
 /ecc:plan "使用 OAuth 添加用户身份验证"
                                               → 规划器创建实现蓝图
-/tdd                                          → tdd-guide 强制执行先写测试
+tdd-workflow 技能                             → tdd-guide 强制执行先写测试
 /code-review                                  → 代码审查员检查你的工作
 ```
 
 **修复错误：**
 
 ```
-/tdd                                          → tdd-guide：编写一个能复现问题的失败测试
+tdd-workflow 技能                             → tdd-guide：编写一个能复现问题的失败测试
                                               → 实现修复，验证测试通过
 /code-review                                  → code-reviewer：捕捉回归问题
 ```
@@ -787,7 +792,7 @@ rules/
 
 ```
 /security-scan                                → security-reviewer: OWASP Top 10 审计
-/e2e                                          → e2e-runner: 关键用户流程测试
+e2e-testing 技能                              → e2e-runner: 关键用户流程测试
 /test-coverage                                → verify 80%+ 覆盖率
 ```
 
@@ -1101,7 +1106,7 @@ opencode
 | 功能特性 | Claude Code | OpenCode | 状态 |
 |---------|-------------|----------|--------|
 | 智能体 | PASS: 48 个 | PASS: 12 个 | **Claude Code 领先** |
-| 命令 | PASS: 80 个 | PASS: 31 个 | **Claude Code 领先** |
+| 命令 | PASS: 68 个 | PASS: 31 个 | **Claude Code 领先** |
 | 技能 | PASS: 184 项 | PASS: 37 项 | **Claude Code 领先** |
 | 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多！** |
 | 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
@@ -1122,21 +1127,17 @@ OpenCode 的插件系统比 Claude Code 更复杂，有 20 多种事件类型：
 
 **额外的 OpenCode 事件**：`file.edited`、`file.watcher.updated`、`message.updated`、`lsp.client.diagnostics`、`tui.toast.show` 等等。
 
-### 可用命令（31+）
+### 维护中的斜杠命令
 
 | 命令 | 描述 |
 |---------|-------------|
 | `/plan` | 创建实施计划 |
-| `/tdd` | 强制执行 TDD 工作流 |
 | `/code-review` | 审查代码变更 |
 | `/build-fix` | 修复构建错误 |
-| `/e2e` | 生成端到端测试 |
 | `/refactor-clean` | 移除死代码 |
-| `/orchestrate` | 多智能体工作流 |
 | `/learn` | 从会话中提取模式 |
 | `/checkpoint` | 保存验证状态 |
-| `/verify` | 运行验证循环 |
+| `/quality-gate` | 运行维护中的验证门禁 |
-| `/eval` | 根据标准进行评估 |
 | `/update-docs` | 更新文档 |
 | `/update-codemaps` | 更新代码地图 |
 | `/test-coverage` | 分析覆盖率 |
@@ -1213,7 +1214,7 @@ ECC 是**第一个最大化利用每个主要 AI 编码工具的插件**。以
 | 功能特性 | Claude Code | Cursor IDE | Codex CLI | OpenCode |
 |---------|------------|------------|-----------|----------|
 | **智能体** | 48 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
-| **命令** | 80 | 共享 | 基于指令 | 31 |
+| **命令** | 68 | 共享 | 基于指令 | 31 |
 | **技能** | 184 | 共享 | 10 (原生格式) | 37 |
 | **钩子事件** | 8 种类型 | 15 种类型 | 暂无 | 11 种类型 |
 | **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | N/A | 插件钩子 |

legacy-command-shims/README.md

@@ -0,0 +1,7 @@
+# Legacy Command Shims
+
+These slash-entry shims are no longer loaded by the default plugin command surface.
+
+They remain here for users who still need short-term migration compatibility with old muscle-memory commands such as `/tdd`, `/eval`, or `/verify`.
+
+Prefer the canonical skills or maintained commands referenced inside each shim. If you need one of these shims locally, copy the individual Markdown file into your project-level or user-level Claude commands directory instead of enabling the full archive by default.

manifests/install-modules.json

@@ -417,7 +417,6 @@
       "description": "Worktree/tmux orchestration runtime and workflow docs.",
       "paths": [
         "commands/multi-workflow.md",
-        "commands/orchestrate.md",
         "commands/sessions.md",
         "scripts/lib/orchestration-session.js",
         "scripts/lib/tmux-worktree-orchestrator.js",

scripts/harness-audit.js

@@ -392,11 +392,11 @@ function getRepoChecks(rootDir) {
       id: 'eval-commands',
       category: 'Eval Coverage',
       points: 4,
-      scopes: ['repo', 'commands'],
+      scopes: ['repo', 'commands', 'skills'],
-      path: 'commands/eval.md',
+      path: 'commands/checkpoint.md',
-      description: 'Eval and verification commands exist',
+      description: 'Checkpoint command and eval/verification skills exist',
-      pass: fileExists(rootDir, 'commands/eval.md') && fileExists(rootDir, 'commands/verify.md') && fileExists(rootDir, 'commands/checkpoint.md'),
+      pass: fileExists(rootDir, 'commands/checkpoint.md') && fileExists(rootDir, 'skills/eval-harness/SKILL.md') && fileExists(rootDir, 'skills/verification-loop/SKILL.md'),
-      fix: 'Add eval/checkpoint/verify commands to standardize verification loops.',
+      fix: 'Add checkpoint command plus eval-harness and verification-loop skills to standardize verification loops.',
     },
     {
       id: 'eval-tests-presence',

tests/ci/agent-yaml-surface.test.js

@@ -10,6 +10,22 @@ const path = require('path');
 const REPO_ROOT = path.join(__dirname, '..', '..');
 const AGENT_YAML_PATH = path.join(REPO_ROOT, 'agent.yaml');
 const COMMANDS_DIR = path.join(REPO_ROOT, 'commands');
+const LEGACY_COMMANDS_DIR = path.join(REPO_ROOT, 'legacy-command-shims', 'commands');
+
+const RETIRED_LEGACY_SHIMS = [
+  'agent-sort',
+  'claw',
+  'context-budget',
+  'devfleet',
+  'docs',
+  'e2e',
+  'eval',
+  'orchestrate',
+  'prompt-optimize',
+  'rules-distill',
+  'tdd',
+  'verify',
+];
 
 function extractTopLevelList(yamlSource, key) {
   const lines = yamlSource.replace(/^\uFEFF/, '').split(/\r?\n/);
@@ -70,6 +86,22 @@ function run() {
     assert.deepStrictEqual(declaredCommands, actualCommands);
   })) passed++; else failed++;
 
+  if (test('retired legacy slash-entry shims are not in the default commands export', () => {
+    const defaultShimCommands = RETIRED_LEGACY_SHIMS
+      .filter(command => actualCommands.includes(command));
+
+    assert.deepStrictEqual(defaultShimCommands, []);
+  })) passed++; else failed++;
+
+  if (test('retired legacy slash-entry shims remain available from the opt-in archive', () => {
+    const archivedCommands = fs.readdirSync(LEGACY_COMMANDS_DIR)
+      .filter(file => file.endsWith('.md'))
+      .map(file => path.basename(file, '.md'))
+      .sort();
+
+    assert.deepStrictEqual(archivedCommands, RETIRED_LEGACY_SHIMS);
+  })) passed++; else failed++;
+
   console.log(`\nPassed: ${passed}`);
   console.log(`Failed: ${failed}`);
 

tests/lib/orchestration-session.test.js

@@ -59,7 +59,7 @@ test('parseWorkerTask extracts objective and seeded overlays', () => {
     '',
     '## Seeded Local Overlays',
     '- `scripts/orchestrate-worktrees.js`',
-    '- `commands/orchestrate.md`',
+    '- `commands/multi-workflow.md`',
     '',
     '## Objective',
     'Verify seeded files and summarize status.'
@@ -67,7 +67,7 @@ test('parseWorkerTask extracts objective and seeded overlays', () => {
 
   assert.deepStrictEqual(task.seedPaths, [
     'scripts/orchestrate-worktrees.js',
-    'commands/orchestrate.md'
+    'commands/multi-workflow.md'
   ]);
   assert.strictEqual(task.objective, 'Verify seeded files and summarize status.');
 });

tests/lib/tmux-worktree-orchestrator.test.js

@@ -299,7 +299,7 @@ test('executePlan rolls back partial setup when orchestration fails mid-run', ()
         workerName: 'Docs',
         workerSlug: 'docs',
         worktreePath: '/tmp/ecc-rollback-docs',
-        seedPaths: ['commands/orchestrate.md'],
+        seedPaths: ['commands/multi-workflow.md'],
         gitArgs: ['worktree', 'add', '-b', 'orchestrator-rollback-test-docs', '/tmp/ecc-rollback-docs', 'HEAD'],
         launchCommand: 'echo run'
       }

tests/scripts/trae-install.test.js

@@ -84,14 +84,14 @@ function runTests() {
     const projectRoot = createTempDir('trae-project-');
 
     try {
-      const preexistingCommandPath = path.join(projectRoot, '.trae', 'commands', 'e2e.md');
+      const preexistingCommandPath = path.join(projectRoot, '.trae', 'commands', 'quality-gate.md');
       fs.mkdirSync(path.dirname(preexistingCommandPath), { recursive: true });
       fs.writeFileSync(preexistingCommandPath, 'user owned command\n');
 
       runInstall({ cwd: projectRoot, homeDir });
 
       const manifestLines = readManifestLines(projectRoot);
-      assert.ok(!manifestLines.includes('commands/e2e.md'), 'Preexisting file should not be recorded in manifest');
+      assert.ok(!manifestLines.includes('commands/quality-gate.md'), 'Preexisting file should not be recorded in manifest');
 
       runUninstall({ cwd: projectRoot, homeDir });
 
@@ -131,13 +131,13 @@ function runTests() {
     try {
       runInstall({ cwd: projectRoot, homeDir });
 
-      const managedCommandPath = path.join(projectRoot, '.trae', 'commands', 'e2e.md');
+      const managedCommandPath = path.join(projectRoot, '.trae', 'commands', 'quality-gate.md');
       fs.rmSync(managedCommandPath);
 
       runInstall({ cwd: projectRoot, homeDir });
 
       const manifestLines = readManifestLines(projectRoot);
-      const entryCount = manifestLines.filter((line) => line === 'commands/e2e.md').length;
+      const entryCount = manifestLines.filter((line) => line === 'commands/quality-gate.md').length;
 
       assert.strictEqual(entryCount, 1, 'Managed file should appear once in manifest after reinstall');
       assert.ok(fs.existsSync(managedCommandPath), 'Managed file should be recreated on reinstall');