v7.3.2 — Launcher UX & Unified Manifest

v7.3.2 — Launcher UX & Unified Manifest

中文版

v7.2.29 → v7.3.2 共 14 个提交，涵盖 Launcher 工作流管理、Hook 系统、Manifest 统一读取、CCW Coordinator Tracker、Memory Capture 技能等多项改进。

---

✨ 新功能

• Launcher 工作流管理 (81702c96)

  • 新增交互式生态系统选择（claude / codex / all）
  • 安装时自动全局安装 claude.ccw.md
  • 升级命令支持旧版 CLAUDE.md 迁移到新格式的交互提示
  • 改进全局文件和用户设置的安装/卸载处理逻辑
  • 新增 file-reader.ts 工具模块

• 统一 Manifest 读取与 BOM 兼容 (5cab701b)

  • 跨 ~/.claude-manifests/ 和 ~/.maestro/manifests/ 目录的统一清单读取
  • 修复 UTF-8 BOM 编码导致 JSON 解析失败的问题
  • 重构 ccw-coordinator.md 和 ccw.md 命令文件，增强 Launcher 状态仪表板逻辑

• Hook 安装系统 (87b6279f, 21a152c6)

  • Manifest 结构扩展，新增 hooks 字段和相关操作
  • 安装时提供四种 Hook 选择模式：推荐 / 全部 / 自定义 / 跳过
  • 卸载时自动清理已注册的 hooks（uninstall.ts）
  • hook-templates.ts 新增从 settings 中卸载指定 hook 的功能
  • Launcher 增加 npm 包检查和安装提示

• CCW Coordinator Tracker (d4fe81c9)

  • 新增 ccwCoordinatorTrackerAction 处理 /ccw 和 /ccw-coordinator 进度追踪
  • 引入 hooks 机制用于工具执行期间的追踪和提示注入
  • 新增 ccw-coordinator-tracker.ts 模块，读取会话状态并管理 bridge 数据
  • 新增 ccw-coordinator-tracker hook 模板
  • brainstorm-with-file.md 初始化增加 Artifact Index

• 统一 Memory Capture 技能 (4403088e)

  • 新增 memory-capture 技能编排器
  • Phase 1: Compact — 结构化会话记忆压缩导出，捕获关键信息用于恢复
  • Phase 2: Tips — 快捷笔记，支持可选标签和上下文关联
  • 清理旧版 workflow-skill.md、collaborative-plan-with-file.md、unified-execute-with-file.md 等遗留文件（净减 570 行）

• 链式工作流技能 (dc390cc7)

  • 新增 workflow-plan 技能：6 阶段规划工作流，含模式路由和冲突检测
  • 新增 workflow-tdd-plan 技能：7 阶段 TDD 规划，含 Red-Green-Refactor 任务生成
  • 新增 workflow-test-fix 技能：5 阶段测试生成与迭代执行管道
  • 新增链拓扑 ASCII 可视化工具

• CLI 入口与会话管理 (87aac2ca)

  • 新增 bin/ccw.js 和 bin/ccw-mcp.js 入口文件
  • CLI session manager 增加可选依赖的优雅处理
  • 新增 cli-executor-utils-codex-review.test.js 和 package-entrypoints.test.js 测试

• Claude 指令与 CLI 端点配置 (bbfc294c)

  • CLAUDE.md 重命名为 claude.ccw.md
  • 移除过时的 .gemini/GEMINI.md 和 .qwen/QWEN.md 协议文件

---

🐛 修复

• checklistChoices 类型与分隔符 (b3155956) — 修复 installCommand 中 checklistChoices 的类型定义，改进分隔符处理逻辑
• CCW Coordinator Tracker 触发器 (1efef96f) — 改为 Stop 触发器，优化 next-step 提示注入；安装提示增加详细 CCW hook 描述；workflow-tune.md 补充沙箱创建绝对路径要求
• CLAUDE.CCW.md 引用路径 (877ef962) — 全面更新 install.ts、uninstall.ts、upgrade.ts 和安装文档中的文件引用路径，从 claude.ccw.md 统一为 CLAUDE.CCW.md

---

♻️ 重构

• json-builder 解耦 (ad5f5713) — 从 schema-registry 解耦，精简为 6 个纯 JSON 命令（create/set/get/merge/delete/validate）；更新 5 个 agent 文件：schema→template 术语，cat→Read 加载，增加 json_builder set 增量更新指导
• Codex 技能 API 标准化 (e598c54d) — 94 个技能文件中 request_user_input() → functions.request_user_input()；3 个 team-config.json 中 AskUserQuestion → request_user_input；9 个多阶段技能增加 functions.update_plan 进度追踪
• Codex 技能 v4 API 迁移 (fd3a005b) — 9 个技能从 v3 close_agent({id:}) 迁移至 v4 close_agent({target:})；修复 wait_agent({ids:}) → wait_agent({targets:})（共 36 处）
• ccw-chain 精简与命令重构 (f93d6461) — 删除 60+ 重复 phase 文件；chain JSON content_ref 改为指向 @commands/ 或 @skills/ 源；新增 @commands/ 前缀解析支持；新增 ccw chain-loader CLI 命令；新增 /workflow-skill 命令；链式工作流技能迁移至 .claude/workflow-skills/

---

English

v7.2.29 → v7.3.2: 14 commits covering Launcher workflow management, Hook system, unified Manifest reading, CCW Coordinator Tracker, Memory Capture skill, and more.

---

✨ Features

• Launcher workflow management (81702c96)

  • Interactive target ecosystem selection during install (claude / codex / all)
  • Always install claude.ccw.md globally
  • Upgrade command prompts for old CLAUDE.md → new format migration
  • Improved global file and user settings handling during install/uninstall
  • New file-reader.ts utility module

• Unified manifest reading with BOM compatibility (5cab701b)

  • Cross-directory manifest reader for ~/.claude-manifests/ and ~/.maestro/manifests/
  • Fix UTF-8 BOM encoding causing JSON parse failures
  • Refactored ccw-coordinator.md and ccw.md command files; enhanced Launcher dashboard logic

• Hook installation system (87b6279f, 21a152c6)

  • Extended manifest structure with hooks field and related operations
  • Four hook selection modes during install: Recommended / All / Custom / Skip
  • Auto-cleanup of registered hooks during uninstall (uninstall.ts)
  • hook-templates.ts: new function to uninstall specific hooks from settings
  • Launcher adds npm package checks and install prompts

• CCW Coordinator Tracker (d4fe81c9)

  • New ccwCoordinatorTrackerAction for /ccw and /ccw-coordinator progress tracking
  • Hooks for tracking and hint injection during tool execution
  • New ccw-coordinator-tracker.ts module: reads session state, manages bridge data
  • New ccw-coordinator-tracker hook template
  • brainstorm-with-file.md init now includes Artifact Index

• Unified memory capture skill (4403088e)

  • New memory-capture skill orchestrator
  • Phase 1: Compact — structured session memory export for critical info recovery
  • Phase 2: Tips — quick note-taking with optional tags and context linking
  • Cleaned up legacy workflow-skill.md, collaborative-plan-with-file.md, unified-execute-with-file.md (net -570 lines)

• Chain-loaded workflow skills (dc390cc7)

  • workflow-plan: 6-phase planning workflow with mode routing and conflict detection
  • workflow-tdd-plan: 7-phase TDD planning with Red-Green-Refactor task generation
  • workflow-test-fix: 5-phase test generation and iterative execution pipeline
  • Chain topology ASCII visualizer

• CLI entrypoints and session management (87aac2ca)

  • New bin/ccw.js and bin/ccw-mcp.js entrypoints
  • CLI session manager with graceful optional dependency handling
  • New tests: cli-executor-utils-codex-review.test.js, package-entrypoints.test.js

• Claude instructions and CLI endpoint config (bbfc294c)

  • Renamed CLAUDE.md → claude.ccw.md
  • Removed outdated .gemini/GEMINI.md and .qwen/QWEN.md protocol files

---

🐛 Fixes

• checklistChoices type and separator handling (b3155956) — Fix type definition for checklistChoices in installCommand, improve separator handling logic
• CCW Coordinator Tracker trigger (1efef96f) — Switch to Stop trigger, improve next-step hint injection; add detailed CCW hook descriptions to install prompt; clarify absolute path requirement for sandbox creation in workflow-tune.md
• CLAUDE.CCW.md reference paths (877ef962) — Update file references from claude.ccw.md to CLAUDE.CCW.md across install.ts, uninstall.ts, upgrade.ts, and installation docs

---

♻️ Refactoring

• json-builder decoupling (ad5f5713) — Decouple from schema-registry, simplify to 6 pure JSON commands (create/set/get/merge/delete/validate); update 5 agent files: schema→template terminology, cat→Read for template loading, add json_builder set guidance for incremental updates
• Codex skill API standardization (e598c54d) — request_user_input() → functions.request_user_input() across 94 skill files; AskUserQuestion → request_user_input in 3 team-config.json tool arrays; add functions.update_plan progress tracking to 9 multi-phase skills
• Codex skill v4 API migration (fd3a005b) — Migrate 9 skills from v3 close_agent({id:}) to v4 close_agent({target:}); fix wait_agent({ids:}) → wait_agent({targets:}) (36 occurrences)
• ccw-chain cleanup and command refactoring (f93d6461) — Delete 60+ duplicate phase files; chain JSON content_ref now points to @commands/ or @skills/ sources; add @commands/ prefix resolver; new ccw chain-loader CLI command; new /workflow-skill command; move chain-based workflow skills to .claude/workflow-skills/

---

Full Changelog: v7.2.29...v7.3.2

v7.2.29

What's Changed

Codex v4 Agent API Unification

• refactor: Unified all .codex/skills agent calling patterns to Codex v4 API across 31 files in 10 skills
  • wait() → wait_agent() with targets parameter
  • send_input() → assign_task() with structured items array
  • ids → targets parameter naming
  • Skills affected: spec-generator, brainstorm, clean, issue-discover, parallel-dev-cycle, review-cycle, roadmap-with-file, workflow-plan, workflow-tdd-plan, workflow-test-fix-cycle, spec-setup

Features

• feat: Add 4 new UI team skills (interactive-craft, motion-design, ui-polish, visual-a11y) with Impeccable design standards
• feat: Port 4 new UI team skills to Codex v4 format
• feat: Add investigate, security-audit, ship skills (Claude + Codex)
• feat: Enhance skill templates, hooks, CLI routes, and settings UI
• feat: Refactor API calls to use fetchApi for CSRF token handling in Unsplash and Settings pages

Docs

• Add Impeccable acknowledgment to README

v7.2.26 — json_builder Tool & Schema-Aware Validation

What's New

json_builder Tool (Core Feature)

New schema-aware JSON construction and validation tool that replaces manual cat schema + hand-written validation across the entire workflow system.

5 Commands:

• init — Create schema-compliant JSON skeleton from any of 24 registered schemas
• set — Incremental field setting with instant per-field validation (supports path syntax: field.sub, arr[+], arr[0], arr[?key=val])
• validate — Full structural (JSON Schema draft-07 subset) + semantic quality validation
• merge — Merge multiple same-schema JSONs with dedup_by_path strategy (keeps highest relevance)
• info — Compact schema summary replacing raw schema file reads (~100-500 lines → ~20 lines)

Validation Layers:

• Layer 1: Structural — required/type/enum/const/pattern/minLength/minItems/minimum/maximum
• Layer 2: Semantic — generic rationale detection, key_code/topic_relation quality checks, circular dependency detection
• Layer 3: Completeness — all required fields filled with non-empty values

24 Registered Schemas: explore, diagnosis, finding, plan, plan-fix, plan-legacy, fix-legacy, tech, guidelines, issue, queue, review-dim, review-deep, debug-log, discussion, task, solution, verify, discovery-state, conflict, registry, team-tasks, plan-verify

Agent & Skill Updates

All agents and skills updated to use json_builder instead of raw schema file reads:

• Agents: cli-explore-agent, cli-lite-planning-agent, action-planning-agent, issue-plan-agent
• Skills: workflow-plan, workflow-tdd-plan, workflow-test-fix, review-cycle (module + session), workflow-multi-cli-plan
• Commands: workflow/spec/setup

Other Changes

• Workflow session awareness spec added to CLAUDE.md and AGENTS.md
• Removed deprecated prep-cycle.md and prep-plan.md docs

Full Changelog: v7.2.25...v7.2.26

v7.2.13

Changes

• Add workflow-research-agent for targeted external research
• Split review responsibilities — code review in lite-execute, convergence review in lite-test-review
• Remove IDAW run and status commands (functionality consolidated into wf-composer)
• Optimize analyze-with-file explore agent triggering for efficiency
• Implement workflow tuning command

v7.2.11

Changes

• Add workflow-tune skill for multi-step workflow pipeline optimization
• Enhance workflow-tune with reference document extraction and intent matching
• Enhance spec loading capabilities and add new categories
• Resolve all 92 frontend test failures across 13 test files
• Fix team worker task discovery failures and clean up legacy role-specs

v7.2.10

Changes

• Update SKILL.md for analyze-with-file and roadmap-with-file
• Remove analyze-with-file EXECUTE.md
• Remove obsolete tool execution section from documentation

v7.2.9

Changes

• Fix: update CodexLens MCP template with AST support defaults

v7.2.8

Changes

• Enhance search functionality with quality tiers and scoped indexing
• Enhance CodexLens with quick install feature and embed mode toggle
• Add technical solution recording to analyze-with-file workflow
• Fix dependency graph key, CodexLens env defaults, hook path fixes
• Remove ccw-litellm UI components (dead code)
• Remove codex-lens-v2 from outer git tracking

v7.2.1

What's New

New Skill: team-arch-opt (Architecture Optimization)

• New team skill focused on structural architecture improvements: dependency cycles, coupling/cohesion, layering violations, God Classes, dead code
• Isomorphic to team-perf-opt with pipeline: ANALYZE → DESIGN → REFACTOR → VALIDATE + REVIEW
• 6 roles: coordinator, analyzer, designer, refactorer, validator, reviewer
• Supports single/fan-out/independent/auto parallel modes
• 2 subagents: explore (dependency graphs & module boundaries) + discuss (multi-perspective trade-off analysis)

Fixes & Improvements

• fix(analyze-with-file): add session termination boundary and optimize Phase 4 UX
• fix(planning-agent): clarify CLI output as markdown text, relax constraint wording
• fix(planning-agent): relax task parser regex and inject Prior Analysis into CLI context
• fix(planning-agent): remove skip-CLI logic, keep Prior Analysis as context
• fix(planning-agent): enforce blocking CLI calls overriding global default
• fix(planning-agent): add Prior Analysis fast path to skip CLI execution
• refactor(workflow-lite-planex): standardize phase naming and improve documentation

Full Changelog: https://github.com/anthropics/claude-code-workflow/compare/v7.2.0...v7.2.1

v7.0.8 - Structured Task Descriptions

🎯 Structured Task Descriptions for Team Workflows

This release introduces a comprehensive structured task description format across all v5 team workflows, providing workers with clearer context and actionable guidance.

✨ Features

team-coordinate-v2: Enhanced Task Analysis & Dispatch

• Structured Task Schema: Tasks now include goal, steps[], key_files[], upstream_artifacts[], success_criteria, and constraints
• Key File Inference: New Step 2.5 in analyze-task.md automatically infers relevant files based on capability type and task keywords
• Structured Dispatch Template: dispatch.md now uses PURPOSE/TASK/CONTEXT/EXPECTED/CONSTRAINTS format

team-lifecycle-v5: Structured Task Descriptions

• Updated Task Templates: All task creation (standard, revision, improvement) now uses structured format
• Clear Worker Context: Workers receive explicit goals, actionable steps, file references, and success criteria
• Improved Traceability: Upstream artifacts and key files are explicitly listed in CONTEXT section

team-skill-designer-v4: Enforced Quality Standards

• Template Specification: Phase 3 now includes detailed task description template for dispatch.md generation
• Quality Verification: Updated quality standards and integration verification to check structured format
• Consistent Generation: All generated v5 skills will use structured task descriptions

📋 Task Description Format

PURPOSE: <what this task achieves> | Success: <measurable completion criteria>
TASK:
  - <step 1: specific action>
  - <step 2: specific action>
  - <step 3: specific action>
CONTEXT:
  - Session: <session-folder>
  - Scope: <scope>
  - Upstream artifacts: <artifact-1.md>, <artifact-2.md>
  - Key files: <file1>, <file2>
  - Shared memory: <session>/shared-memory.json
EXPECTED: <deliverable path> + <quality criteria>
CONSTRAINTS: <scope limits, focus areas>

🔄 Backward Compatibility

• Fully compatible with existing team-worker Phase 1 (reads descriptions as freeform text)
• No schema changes to team-session.json or role-spec templates
• Existing workflows continue to function without modification

📦 Files Changed

• .claude/skills/team-coordinate-v2/roles/coordinator/commands/analyze-task.md
• .claude/skills/team-coordinate-v2/roles/coordinator/commands/dispatch.md
• .claude/skills/team-lifecycle-v5/roles/coordinator/commands/dispatch.md
• .claude/skills_lib/team-skill-designer-v4/phases/03-skill-generation.md
• .claude/skills_lib/team-skill-designer-v4/phases/04-integration-verification.md
• .claude/skills_lib/team-skill-designer-v4/specs/quality-standards.md

🎁 Benefits

• Clearer Worker Context: Workers understand exactly what to do, why, and how to verify success
• Better File Discovery: Key files are inferred and provided upfront, reducing exploration time
• Improved Success Rates: Explicit success criteria and constraints reduce ambiguity
• Consistent Format: All v5 team workflows use the same structured approach