Add Chinese documentation for CLI commands and workflows

2026-02-13 02:41:50 +08:00 · 2026-02-05 23:30:06 +08:00
parent 05ad8110f4
commit f9188eb0b6
23 changed files with 8877 additions and 26 deletions
--- a/.claude/skills/_shared/COMMAND-TO-SKILL-CONVERSION.md
+++ b/.claude/skills/_shared/COMMAND-TO-SKILL-CONVERSION.md
@@ -291,6 +291,27 @@ allowed-tools: Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob,
 ## Architecture Overview
 {ASCII 架构图}

+## Key Design Principles
+{设计原则列表}
+
+## Auto Mode
+{自动模式说明}
+
+## Usage
+
+```
+Skill(skill="{skill-name}", args="<task description>")
+Skill(skill="{skill-name}", args="[FLAGS] \"<task description>\"")
+
+# Flags
+{flag 说明，每个 flag 一行}
+
+# Examples
+Skill(skill="{skill-name}", args="\"Implement JWT authentication\"")                   # 说明
+Skill(skill="{skill-name}", args="--mode xxx \"Refactor payment module\"")             # 说明
+Skill(skill="{skill-name}", args="-y \"Add user profile page\"")                        # 说明
+```
+
 ## Execution Flow
 {流程图 + Phase 引用表}

@@ -313,6 +334,16 @@ allowed-tools: Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob,
 {错误处理策略}
 ```

+**Usage 格式要求**：
+
+- **必须使用代码块** 包裹 Usage 内容
+- 使用 `Skill()` 调用格式，不使用 `/skill-name` 命令行格式
+- 包含两种调用格式：基本调用 + 带 Flags 的完整调用
+- Flags 说明每行一个 flag，格式：`flag-name    说明`
+- Examples 必须展示所有 flag 组合的典型调用场景
+- 字符串参数中的引号使用转义 `\"`
+- Examples 行尾可添加 `# 说明` 注释
+
 ### 5.3 执行流程示例

 ```markdown
@@ -641,12 +672,34 @@ skills/workflow-plan/
 | 原 plan.md 内容 | SKILL.md 对应位置 |
 |----------------|-------------------|
 | Frontmatter | Frontmatter (扩展) |
+| argument-hint | Usage (转换为 Skill 调用格式) |
 | 执行流程描述 | Execution Flow (可视化) |
 | 子命令调用 | Phase Reference Table |
 | 数据传递 | Data Flow (显式定义) |
+| (无) | Usage (新增 - Skill 调用格式) |
 | (无) | TodoWrite Pattern (新增) |
 | (无) | Error Handling (新增) |

+**Usage 转换示例**：
+
+原命令 `argument-hint`:
+```yaml
+argument-hint: "[-y|--yes] \"text description\"|file.md"
+```
+
+转换为 SKILL.md Usage:
+```
+Skill(skill="workflow-plan", args="<task description>")
+Skill(skill="workflow-plan", args="[-y|--yes] \"<task description>\"")
+
+# Flags
+-y, --yes    Skip all confirmations (auto mode)
+
+# Examples
+Skill(skill="workflow-plan", args="\"Implement authentication\"")     # Interactive mode
+Skill(skill="workflow-plan", args="-y \"Implement authentication\"")  # Auto mode
+```
+
 ### 9.3 Phase 文件与原子命令对比

 | 原子命令内容 | Phase 文件对应 |
@@ -685,3 +738,4 @@ wc -l skills/{skill-name}/SKILL.md skills/{skill-name}/phases/*.md
 | v1.0 | 2025-02-05 | 基于 workflow-plan 转换实践创建 |
 | v1.1 | 2025-02-05 | 强化内容一致性要求；添加第7章一致性验证；添加应移除的命令特有内容说明 |
 | v2.0 | 2026-02-05 | 命令调用引用统一转换为文件路径引用；移除 `/workflow:XX` 命令语法；引用转换规则重构 |
+| v2.1 | 2026-02-05 | 添加 Usage 部分格式规范（Skill 调用格式）；更新 5.2 必需章节；添加 Usage 转换示例到 9.2 节 |
--- a/.claude/skills/workflow-lite-plan/SKILL.md
+++ b/.claude/skills/workflow-lite-plan/SKILL.md
@@ -0,0 +1,217 @@
+---
+name: workflow-lite-plan
+description: Unified lightweight planning skill with mode selection (Lite Plan, Multi-CLI Plan, Lite Fix). Supports exploration, diagnosis, multi-CLI collaboration, and shared execution via lite-execute.
+allowed-tools: Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, Grep, Skill, mcp__ace-tool__search_context
+---
+
+# Planning Workflow
+
+Unified lightweight planning skill that consolidates multiple planning approaches into a single entry point with mode selection. Default mode: **Lite Plan**. All planning modes share a common execution phase (lite-execute).
+
+## Architecture Overview
+
+```
+┌──────────────────────────────────────────────────────────┐
+│  Planning Workflow Orchestrator (SKILL.md)                │
+│  → Parse args → Mode selection → Load phase → Execute    │
+└────────────┬─────────────────────────────────────────────┘
+             │ Mode Selection (default: Lite Plan)
+    ┌────────┼────────┬──────────┐
+    ↓        ↓        ↓          ↓ (shared)
+┌────────┐ ┌────────┐ ┌────────┐ ┌────────────┐
+│Phase 1 │ │Phase 2 │ │Phase 3 │ │  Phase 4   │
+│  Lite  │ │Multi-  │ │  Lite  │ │   Lite     │
+│  Plan  │ │CLI Plan│ │  Fix   │ │  Execute   │
+└────────┘ └────────┘ └────────┘ └────────────┘
+     │          │          │           ↑
+     └──────────┴──────────┴───────────┘
+            (all hand off to Phase 4)
+```
+
+## Key Design Principles
+
+1. **Mode Selection First**: User chooses planning approach before any work begins
+2. **Shared Execution**: All planning modes produce `executionContext` consumed by Phase 4 (lite-execute)
+3. **Progressive Phase Loading**: Only load the selected planning phase + execution phase
+4. **Auto-Continue**: Planning phase completes → automatically loads execution phase
+5. **Default Lite Plan**: When no mode specified, use Lite Plan (most common)
+
+## Auto Mode
+
+When `--yes` or `-y`: Skip mode selection (use default or flag-specified mode), auto-approve plan, skip clarifications.
+
+## Usage
+
+```
+Skill(skill="workflow-lite-plan", args="<task description>")
+Skill(skill="workflow-lite-plan", args="[FLAGS] \"<task description>\"")
+
+# Flags
+--mode lite-plan|multi-cli|lite-fix    Planning mode selection (default: lite-plan)
+-y, --yes                              Skip all confirmations (auto mode)
+-e, --explore                          Force exploration (lite-plan only)
+--hotfix                               Fast hotfix mode (lite-fix only)
+
+# Examples
+Skill(skill="workflow-lite-plan", args="\"Implement JWT authentication\"")                              # Default: lite-plan
+Skill(skill="workflow-lite-plan", args="--mode multi-cli \"Refactor payment module\"")                  # Multi-CLI planning
+Skill(skill="workflow-lite-plan", args="--mode lite-fix \"Login fails with 500 error\"")                # Bug fix mode
+Skill(skill="workflow-lite-plan", args="-y \"Add user profile page\"")                                  # Auto mode
+Skill(skill="workflow-lite-plan", args="--mode lite-fix --hotfix \"Production DB timeout\"")            # Hotfix mode
+```
+
+## Execution Flow
+
+```
+Input Parsing:
+   ├─ Extract flags: --mode, --yes, --explore, --hotfix
+   └─ Extract task description (string or file path)
+
+Mode Selection:
+   └─ Decision:
+      ├─ --mode lite-plan (or no --mode flag) → Read phases/01-lite-plan.md
+      ├─ --mode multi-cli → Read phases/02-multi-cli-plan.md
+      ├─ --mode lite-fix → Read phases/03-lite-fix.md
+      └─ No flag + not --yes → AskUserQuestion (default: Lite Plan)
+
+Planning Phase (one of):
+   ├─ Phase 1: Lite Plan
+   │   └─ Ref: phases/01-lite-plan.md
+   │      └─ Output: executionContext (plan.json + explorations + selections)
+   │
+   ├─ Phase 2: Multi-CLI Plan
+   │   └─ Ref: phases/02-multi-cli-plan.md
+   │      └─ Output: executionContext (plan.json + synthesis rounds + selections)
+   │
+   └─ Phase 3: Lite Fix
+       └─ Ref: phases/03-lite-fix.md
+          └─ Output: executionContext (fix-plan.json + diagnoses + selections)
+
+Execution Phase (always):
+   └─ Phase 4: Lite Execute
+       └─ Ref: phases/04-lite-execute.md
+          └─ Input: executionContext from planning phase
+          └─ Output: Executed tasks + optional code review
+```
+
+**Phase Reference Documents** (read on-demand when phase executes):
+
+| Phase | Document | Purpose |
+|-------|----------|---------|
+| 1 | [phases/01-lite-plan.md](phases/01-lite-plan.md) | Lightweight planning with exploration, clarification, and plan generation |
+| 2 | [phases/02-multi-cli-plan.md](phases/02-multi-cli-plan.md) | Multi-CLI collaborative planning with ACE context and cross-verification |
+| 3 | [phases/03-lite-fix.md](phases/03-lite-fix.md) | Bug diagnosis and fix planning with severity-based workflow |
+| 4 | [phases/04-lite-execute.md](phases/04-lite-execute.md) | Shared execution engine: task grouping, batch execution, code review |
+
+## Mode Selection Logic
+
+```javascript
+// Flag parsing
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+const modeFlag = extractFlag($ARGUMENTS, '--mode')  // 'lite-plan' | 'multi-cli' | 'lite-fix' | null
+
+// Mode determination
+let selectedMode
+
+if (modeFlag) {
+  // Explicit mode flag
+  selectedMode = modeFlag
+} else if (autoYes) {
+  // Auto mode: default to lite-plan
+  selectedMode = 'lite-plan'
+} else {
+  // Interactive: ask user
+  const selection = AskUserQuestion({
+    questions: [{
+      question: "Select planning approach:",
+      header: "Mode",
+      multiSelect: false,
+      options: [
+        { label: "Lite Plan (Recommended)", description: "Lightweight planning with exploration and clarification" },
+        { label: "Multi-CLI Plan", description: "Multi-model collaborative planning (Gemini + Codex + Claude)" },
+        { label: "Lite Fix", description: "Bug diagnosis and fix planning with severity assessment" }
+      ]
+    }]
+  })
+  selectedMode = parseSelection(selection)  // Map to 'lite-plan' | 'multi-cli' | 'lite-fix'
+}
+
+// Load phase document
+const phaseDoc = {
+  'lite-plan': 'phases/01-lite-plan.md',
+  'multi-cli': 'phases/02-multi-cli-plan.md',
+  'lite-fix': 'phases/03-lite-fix.md'
+}[selectedMode]
+
+Read(phaseDoc)  // Load selected planning phase
+// Execute planning phase...
+// After planning completes:
+Read('phases/04-lite-execute.md')  // Load execution phase
+```
+
+## Data Flow
+
+```
+Planning Phase (01/02/03)
+   │
+   ├─ Produces: executionContext = {
+   │     planObject: plan.json or fix-plan.json,
+   │     explorationsContext / diagnosisContext / synthesis rounds,
+   │     clarificationContext,
+   │     executionMethod: "Agent" | "Codex" | "Auto",
+   │     codeReviewTool: "Skip" | "Gemini Review" | ...,
+   │     originalUserInput: string,
+   │     session: { id, folder, artifacts }
+   │   }
+   │
+   ↓
+Execution Phase (04)
+   │
+   ├─ Consumes: executionContext
+   ├─ Task grouping → Batch creation → Parallel/sequential execution
+   ├─ Optional code review
+   └─ Development index update
+```
+
+## TodoWrite Pattern
+
+**Initialization** (after mode selection):
+```json
+[
+  {"content": "Mode: {selectedMode} - Planning", "status": "in_progress", "activeForm": "Planning ({selectedMode})"},
+  {"content": "Execution (Phase 4)", "status": "pending", "activeForm": "Executing tasks"}
+]
+```
+
+**After planning completes**:
+```json
+[
+  {"content": "Mode: {selectedMode} - Planning", "status": "completed", "activeForm": "Planning ({selectedMode})"},
+  {"content": "Execution (Phase 4)", "status": "in_progress", "activeForm": "Executing tasks"}
+]
+```
+
+Phase-internal sub-tasks are managed by each phase document (attach/collapse pattern).
+
+## Core Rules
+
+1. **Planning phases NEVER execute code** - all execution delegated to Phase 4
+2. **Only ONE planning phase runs** per invocation (Phase 1, 2, or 3)
+3. **Phase 4 ALWAYS runs** after planning completes
+4. **executionContext is the contract** between planning and execution phases
+5. **Progressive loading**: Read phase doc ONLY when about to execute
+6. **No cross-phase loading**: Don't load Phase 2 if user selected Phase 1
+
+## Error Handling
+
+| Error | Resolution |
+|-------|------------|
+| Unknown --mode value | Default to lite-plan with warning |
+| Planning phase failure | Display error, offer retry or mode switch |
+| executionContext missing | Error: planning phase did not produce context |
+| Phase file not found | Error with file path for debugging |
+
+## Related Skills
+
+- Full planning workflow: [workflow-plan/SKILL.md](../workflow-plan/SKILL.md)
+- Brainstorming: [workflow-brainstorm-auto-parallel/SKILL.md](../workflow-brainstorm-auto-parallel/SKILL.md)
--- a/.claude/skills/workflow-lite-plan/phases/01-lite-plan.md
+++ b/.claude/skills/workflow-lite-plan/phases/01-lite-plan.md
@@ -0,0 +1,691 @@
+# Phase 1: Lite Plan
+
+## Overview
+
+Intelligent lightweight planning command with dynamic workflow adaptation based on task complexity. Focuses on planning phases (exploration, clarification, planning, confirmation) and delegates execution to Phase 4: Lite Execute (phases/04-lite-execute.md).
+
+**Core capabilities:**
+- Intelligent task analysis with automatic exploration detection
+- Dynamic code exploration (cli-explore-agent) when codebase understanding needed
+- Interactive clarification after exploration to gather missing information
+- Adaptive planning: Low complexity → Direct Claude; Medium/High → cli-lite-planning-agent
+- Two-step confirmation: plan display → multi-dimensional input collection
+- Execution execute with complete context handoff to lite-execute
+
+## Parameters
+
+| Parameter | Description |
+|-----------|-------------|
+| `-y`, `--yes` | Skip all confirmations (auto mode) |
+| `-e`, `--explore` | Force code exploration phase (overrides auto-detection) |
+| `<task-description>` | Task description or path to .md file (required) |
+
+## Output Artifacts
+
+| Artifact | Description |
+|----------|-------------|
+| `exploration-{angle}.json` | Per-angle exploration results (1-4 files based on complexity) |
+| `explorations-manifest.json` | Index of all exploration files |
+| `planning-context.md` | Evidence paths + synthesized understanding |
+| `plan.json` | Structured implementation plan (plan-json-schema.json) |
+
+**Output Directory**: `.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/`
+
+**Agent Usage**:
+- Low complexity → Direct Claude planning (no agent)
+- Medium/High complexity → `cli-lite-planning-agent` generates `plan.json`
+
+**Schema Reference**: `~/.claude/workflows/cli-templates/schemas/plan-json-schema.json`
+
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Clarification Questions**: Skipped (no clarification phase)
+- **Plan Confirmation**: Auto-selected "Allow"
+- **Execution Method**: Auto-selected "Auto"
+- **Code Review**: Auto-selected "Skip"
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+const forceExplore = $ARGUMENTS.includes('--explore') || $ARGUMENTS.includes('-e')
+```
+
+## Execution Process
+
+```
+Phase 1: Task Analysis & Exploration
+   ├─ Parse input (description or .md file)
+   ├─ intelligent complexity assessment (Low/Medium/High)
+   ├─ Exploration decision (auto-detect or --explore flag)
+   ├─ Context protection: If file reading ≥50k chars → force cli-explore-agent
+   └─ Decision:
+      ├─ needsExploration=true → Launch parallel cli-explore-agents (1-4 based on complexity)
+      └─ needsExploration=false → Skip to Phase 2/3
+
+Phase 2: Clarification (optional, multi-round)
+   ├─ Aggregate clarification_needs from all exploration angles
+   ├─ Deduplicate similar questions
+   └─ Decision:
+      ├─ Has clarifications → AskUserQuestion (max 4 questions per round, multiple rounds allowed)
+      └─ No clarifications → Skip to Phase 3
+
+Phase 3: Planning (NO CODE EXECUTION - planning only)
+   └─ Decision (based on Phase 1 complexity):
+      ├─ Low → Load schema: cat ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json → Direct Claude planning (following schema) → plan.json
+      └─ Medium/High → cli-lite-planning-agent → plan.json (agent internally executes quality check)
+
+Phase 4: Confirmation & Selection
+   ├─ Display plan summary (tasks, complexity, estimated time)
+   └─ AskUserQuestion:
+      ├─ Confirm: Allow / Modify / Cancel
+      ├─ Execution: Agent / Codex / Auto
+      └─ Review: Gemini / Agent / Skip
+
+Phase 5: Execute
+   ├─ Build executionContext (plan + explorations + clarifications + selections)
+   └─ → Hand off to Phase 4: Lite Execute (phases/04-lite-execute.md) --in-memory
+```
+
+## Implementation
+
+### Phase 1: Intelligent Multi-Angle Exploration
+
+**Session Setup** (MANDATORY - follow exactly):
+```javascript
+// Helper: Get UTC+8 (China Standard Time) ISO string
+const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
+
+const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
+const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-11-29
+
+const sessionId = `${taskSlug}-${dateStr}`  // e.g., "implement-jwt-refresh-2025-11-29"
+const sessionFolder = `.workflow/.lite-plan/${sessionId}`
+
+bash(`mkdir -p ${sessionFolder} && test -d ${sessionFolder} && echo "SUCCESS: ${sessionFolder}" || echo "FAILED: ${sessionFolder}"`)
+```
+
+**Exploration Decision Logic**:
+```javascript
+needsExploration = (
+  flags.includes('--explore') || flags.includes('-e') ||
+  task.mentions_specific_files ||
+  task.requires_codebase_context ||
+  task.needs_architecture_understanding ||
+  task.modifies_existing_code
+)
+
+if (!needsExploration) {
+  // Skip to Phase 2 (Clarification) or Phase 3 (Planning)
+  proceed_to_next_phase()
+}
+```
+
+**⚠️ Context Protection**: File reading ≥50k chars → force `needsExploration=true` (delegate to cli-explore-agent)
+
+**Complexity Assessment** (Intelligent Analysis):
+```javascript
+// analyzes task complexity based on:
+// - Scope: How many systems/modules are affected?
+// - Depth: Surface change vs architectural impact?
+// - Risk: Potential for breaking existing functionality?
+// - Dependencies: How interconnected is the change?
+
+const complexity = analyzeTaskComplexity(task_description)
+// Returns: 'Low' | 'Medium' | 'High'
+// Low: Single file, isolated change, minimal risk
+// Medium: Multiple files, some dependencies, moderate risk
+// High: Cross-module, architectural, high risk
+
+// Angle assignment based on task type (orchestrator decides, not agent)
+const ANGLE_PRESETS = {
+  architecture: ['architecture', 'dependencies', 'modularity', 'integration-points'],
+  security: ['security', 'auth-patterns', 'dataflow', 'validation'],
+  performance: ['performance', 'bottlenecks', 'caching', 'data-access'],
+  bugfix: ['error-handling', 'dataflow', 'state-management', 'edge-cases'],
+  feature: ['patterns', 'integration-points', 'testing', 'dependencies']
+}
+
+function selectAngles(taskDescription, count) {
+  const text = taskDescription.toLowerCase()
+  let preset = 'feature' // default
+
+  if (/refactor|architect|restructure|modular/.test(text)) preset = 'architecture'
+  else if (/security|auth|permission|access/.test(text)) preset = 'security'
+  else if (/performance|slow|optimi|cache/.test(text)) preset = 'performance'
+  else if (/fix|bug|error|issue|broken/.test(text)) preset = 'bugfix'
+
+  return ANGLE_PRESETS[preset].slice(0, count)
+}
+
+const selectedAngles = selectAngles(task_description, complexity === 'High' ? 4 : (complexity === 'Medium' ? 3 : 1))
+
+// Planning strategy determination
+const planningStrategy = complexity === 'Low'
+  ? 'Direct Claude Planning'
+  : 'cli-lite-planning-agent'
+
+console.log(`
+## Exploration Plan
+
+Task Complexity: ${complexity}
+Selected Angles: ${selectedAngles.join(', ')}
+Planning Strategy: ${planningStrategy}
+
+Launching ${selectedAngles.length} parallel explorations...
+`)
+```
+
+**Launch Parallel Explorations** - Orchestrator assigns angle to each agent:
+
+**⚠️ CRITICAL - NO BACKGROUND EXECUTION**:
+- **MUST NOT use `run_in_background: true`** - exploration results are REQUIRED before planning
+
+
+```javascript
+// Launch agents with pre-assigned angles
+const explorationTasks = selectedAngles.map((angle, index) =>
+  Task(
+    subagent_type="cli-explore-agent",
+    run_in_background=false,  // ⚠️ MANDATORY: Must wait for results
+    description=`Explore: ${angle}`,
+    prompt=`
+## Task Objective
+Execute **${angle}** exploration for task planning context. Analyze codebase from this specific angle to discover relevant structure, patterns, and constraints.
+
+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output File**: ${sessionFolder}/exploration-${angle}.json
+
+## Assigned Context
+- **Exploration Angle**: ${angle}
+- **Task Description**: ${task_description}
+- **Exploration Index**: ${index + 1} of ${selectedAngles.length}
+
+## MANDATORY FIRST STEPS (Execute by Agent)
+**You (cli-explore-agent) MUST execute these steps in order:**
+1. Run: ccw tool exec get_modules_by_depth '{}' (project structure)
+2. Run: rg -l "{keyword_from_task}" --type ts (locate relevant files)
+3. Execute: cat ~/.claude/workflows/cli-templates/schemas/explore-json-schema.json (get output schema reference)
+4. Read: .workflow/project-tech.json (technology stack and architecture context)
+5. Read: .workflow/project-guidelines.json (user-defined constraints and conventions)
+
+## Exploration Strategy (${angle} focus)
+
+**Step 1: Structural Scan** (Bash)
+- get_modules_by_depth.sh → identify modules related to ${angle}
+- find/rg → locate files relevant to ${angle} aspect
+- Analyze imports/dependencies from ${angle} perspective
+
+**Step 2: Semantic Analysis** (Gemini CLI)
+- How does existing code handle ${angle} concerns?
+- What patterns are used for ${angle}?
+- Where would new code integrate from ${angle} viewpoint?
+
+**Step 3: Write Output**
+- Consolidate ${angle} findings into JSON
+- Identify ${angle}-specific clarification needs
+
+## Expected Output
+
+**Schema Reference**: Schema obtained in MANDATORY FIRST STEPS step 3, follow schema exactly
+
+**Required Fields** (all ${angle} focused):
+- project_structure: Modules/architecture relevant to ${angle}
+- relevant_files: Files affected from ${angle} perspective
+  **IMPORTANT**: Use object format with relevance scores for synthesis:
+  \`[{path: "src/file.ts", relevance: 0.85, rationale: "Core ${angle} logic"}]\`
+  Scores: 0.7+ high priority, 0.5-0.7 medium, <0.5 low
+- patterns: ${angle}-related patterns to follow
+- dependencies: Dependencies relevant to ${angle}
+- integration_points: Where to integrate from ${angle} viewpoint (include file:line locations)
+- constraints: ${angle}-specific limitations/conventions
+- clarification_needs: ${angle}-related ambiguities (options array + recommended index)
+- _metadata.exploration_angle: "${angle}"
+
+## Success Criteria
+- [ ] Schema obtained via cat explore-json-schema.json
+- [ ] get_modules_by_depth.sh executed
+- [ ] At least 3 relevant files identified with ${angle} rationale
+- [ ] Patterns are actionable (code examples, not generic advice)
+- [ ] Integration points include file:line locations
+- [ ] Constraints are project-specific to ${angle}
+- [ ] JSON output follows schema exactly
+- [ ] clarification_needs includes options + recommended
+
+## Execution
+**Write**: \`${sessionFolder}/exploration-${angle}.json\`
+**Return**: 2-3 sentence summary of ${angle} findings
+`
+  )
+)
+
+// Execute all exploration tasks in parallel
+```
+
+**Auto-discover Generated Exploration Files**:
+```javascript
+// After explorations complete, auto-discover all exploration-*.json files
+const explorationFiles = bash(`find ${sessionFolder} -name "exploration-*.json" -type f`)
+  .split('\n')
+  .filter(f => f.trim())
+
+// Read metadata to build manifest
+const explorationManifest = {
+  session_id: sessionId,
+  task_description: task_description,
+  timestamp: getUtc8ISOString(),
+  complexity: complexity,
+  exploration_count: explorationCount,
+  explorations: explorationFiles.map(file => {
+    const data = JSON.parse(Read(file))
+    const filename = path.basename(file)
+    return {
+      angle: data._metadata.exploration_angle,
+      file: filename,
+      path: file,
+      index: data._metadata.exploration_index
+    }
+  })
+}
+
+Write(`${sessionFolder}/explorations-manifest.json`, JSON.stringify(explorationManifest, null, 2))
+
+console.log(`
+## Exploration Complete
+
+Generated exploration files in ${sessionFolder}:
+${explorationManifest.explorations.map(e => `- exploration-${e.angle}.json (angle: ${e.angle})`).join('\n')}
+
+Manifest: explorations-manifest.json
+Angles explored: ${explorationManifest.explorations.map(e => e.angle).join(', ')}
+`)
+```
+
+**Output**:
+- `${sessionFolder}/exploration-{angle1}.json`
+- `${sessionFolder}/exploration-{angle2}.json`
+- ... (1-4 files based on complexity)
+- `${sessionFolder}/explorations-manifest.json`
+
+---
+
+### Phase 2: Clarification (Optional, Multi-Round)
+
+**Skip if**: No exploration or `clarification_needs` is empty across all explorations
+
+**⚠️ CRITICAL**: AskUserQuestion tool limits max 4 questions per call. **MUST execute multiple rounds** to exhaust all clarification needs - do NOT stop at round 1.
+
+**Aggregate clarification needs from all exploration angles**:
+```javascript
+// Load manifest and all exploration files
+const manifest = JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
+const explorations = manifest.explorations.map(exp => ({
+  angle: exp.angle,
+  data: JSON.parse(Read(exp.path))
+}))
+
+// Aggregate clarification needs from all explorations
+const allClarifications = []
+explorations.forEach(exp => {
+  if (exp.data.clarification_needs?.length > 0) {
+    exp.data.clarification_needs.forEach(need => {
+      allClarifications.push({
+        ...need,
+        source_angle: exp.angle
+      })
+    })
+  }
+})
+
+// Intelligent deduplication: analyze allClarifications by intent
+// - Identify questions with similar intent across different angles
+// - Merge similar questions: combine options, consolidate context
+// - Produce dedupedClarifications with unique intents only
+const dedupedClarifications = intelligentMerge(allClarifications)
+
+// Parse --yes flag
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+if (autoYes) {
+  // Auto mode: Skip clarification phase
+  console.log(`[--yes] Skipping ${dedupedClarifications.length} clarification questions`)
+  console.log(`Proceeding to planning with exploration results...`)
+  // Continue to Phase 3
+} else if (dedupedClarifications.length > 0) {
+  // Interactive mode: Multi-round clarification
+  const BATCH_SIZE = 4
+  const totalRounds = Math.ceil(dedupedClarifications.length / BATCH_SIZE)
+
+  for (let i = 0; i < dedupedClarifications.length; i += BATCH_SIZE) {
+    const batch = dedupedClarifications.slice(i, i + BATCH_SIZE)
+    const currentRound = Math.floor(i / BATCH_SIZE) + 1
+
+    console.log(`### Clarification Round ${currentRound}/${totalRounds}`)
+
+    AskUserQuestion({
+      questions: batch.map(need => ({
+        question: `[${need.source_angle}] ${need.question}\n\nContext: ${need.context}`,
+        header: need.source_angle.substring(0, 12),
+        multiSelect: false,
+        options: need.options.map((opt, index) => ({
+          label: need.recommended === index ? `${opt} ★` : opt,
+          description: need.recommended === index ? `Recommended` : `Use ${opt}`
+        }))
+      }))
+    })
+
+    // Store batch responses in clarificationContext before next round
+  }
+}
+```
+
+**Output**: `clarificationContext` (in-memory)
+
+---
+
+### Phase 3: Planning
+
+**Planning Strategy Selection** (based on Phase 1 complexity):
+
+**IMPORTANT**: Phase 3 is **planning only** - NO code execution. All execution happens in Phase 5 via lite-execute.
+
+**Executor Assignment** (Claude 智能分配，plan 生成后执行):
+
+```javascript
+// 分配规则（优先级从高到低）：
+// 1. 用户明确指定："用 gemini 分析..." → gemini, "codex 实现..." → codex
+// 2. 默认 → agent
+
+const executorAssignments = {}  // { taskId: { executor: 'gemini'|'codex'|'agent', reason: string } }
+plan.tasks.forEach(task => {
+  // Claude 根据上述规则语义分析，为每个 task 分配 executor
+  executorAssignments[task.id] = { executor: '...', reason: '...' }
+})
+```
+
+**Low Complexity** - Direct planning by Claude:
+```javascript
+// Step 1: Read schema
+const schema = Bash(`cat ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json`)
+
+// Step 2: ⚠️ MANDATORY - Read and review ALL exploration files
+const manifest = JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
+manifest.explorations.forEach(exp => {
+  const explorationData = Read(exp.path)
+  console.log(`\n### Exploration: ${exp.angle}\n${explorationData}`)
+})
+
+// Step 3: Generate plan following schema (Claude directly, no agent)
+// ⚠️ Plan MUST incorporate insights from exploration files read in Step 2
+const plan = {
+  summary: "...",
+  approach: "...",
+  tasks: [...],  // Each task: { id, title, scope, ..., depends_on, execution_group, complexity }
+  estimated_time: "...",
+  recommended_execution: "Agent",
+  complexity: "Low",
+  _metadata: { timestamp: getUtc8ISOString(), source: "direct-planning", planning_mode: "direct" }
+}
+
+// Step 4: Write plan to session folder
+Write(`${sessionFolder}/plan.json`, JSON.stringify(plan, null, 2))
+
+// Step 5: MUST continue to Phase 4 (Confirmation) - DO NOT execute code here
+```
+
+**Medium/High Complexity** - Invoke cli-lite-planning-agent:
+
+```javascript
+Task(
+  subagent_type="cli-lite-planning-agent",
+  run_in_background=false,
+  description="Generate detailed implementation plan",
+  prompt=`
+Generate implementation plan and write plan.json.
+
+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output Files**:
+- ${sessionFolder}/planning-context.md (evidence + understanding)
+- ${sessionFolder}/plan.json (implementation plan)
+
+## Output Schema Reference
+Execute: cat ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json (get schema reference before generating plan)
+
+## Project Context (MANDATORY - Read Both Files)
+1. Read: .workflow/project-tech.json (technology stack, architecture, key components)
+2. Read: .workflow/project-guidelines.json (user-defined constraints and conventions)
+
+**CRITICAL**: All generated tasks MUST comply with constraints in project-guidelines.json
+
+## Task Description
+${task_description}
+
+## Multi-Angle Exploration Context
+
+${manifest.explorations.map(exp => `### Exploration: ${exp.angle} (${exp.file})
+Path: ${exp.path}
+
+Read this file for detailed ${exp.angle} analysis.`).join('\n\n')}
+
+Total explorations: ${manifest.exploration_count}
+Angles covered: ${manifest.explorations.map(e => e.angle).join(', ')}
+
+Manifest: ${sessionFolder}/explorations-manifest.json
+
+## User Clarifications
+${JSON.stringify(clarificationContext) || "None"}
+
+## Complexity Level
+${complexity}
+
+## Requirements
+Generate plan.json following the schema obtained above. Key constraints:
+- tasks: 2-7 structured tasks (**group by feature/module, NOT by file**)
+- _metadata.exploration_angles: ${JSON.stringify(manifest.explorations.map(e => e.angle))}
+
+## Task Grouping Rules
+1. **Group by feature**: All changes for one feature = one task (even if 3-5 files)
+2. **Group by context**: Tasks with similar context or related functional changes can be grouped together
+3. **Minimize agent count**: Simple, unrelated tasks can also be grouped to reduce agent execution overhead
+4. **Avoid file-per-task**: Do NOT create separate tasks for each file
+5. **Substantial tasks**: Each task should represent 15-60 minutes of work
+6. **True dependencies only**: Only use depends_on when Task B cannot start without Task A's output
+7. **Prefer parallel**: Most tasks should be independent (no depends_on)
+
+## Execution
+1. Read schema file (cat command above)
+2. Execute CLI planning using Gemini (Qwen fallback)
+3. Read ALL exploration files for comprehensive context
+4. Synthesize findings and generate plan following schema
+5. **Write**: \`${sessionFolder}/planning-context.md\` (evidence paths + understanding)
+6. **Write**: \`${sessionFolder}/plan.json\`
+7. Return brief completion summary
+`
+)
+```
+
+**Output**: `${sessionFolder}/plan.json`
+
+---
+
+### Phase 4: Task Confirmation & Execution Selection
+
+**Step 4.1: Display Plan**
+```javascript
+const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
+
+console.log(`
+## Implementation Plan
+
+**Summary**: ${plan.summary}
+**Approach**: ${plan.approach}
+
+**Tasks** (${plan.tasks.length}):
+${plan.tasks.map((t, i) => `${i+1}. ${t.title} (${t.file})`).join('\n')}
+
+**Complexity**: ${plan.complexity}
+**Estimated Time**: ${plan.estimated_time}
+**Recommended**: ${plan.recommended_execution}
+`)
+```
+
+**Step 4.2: Collect Confirmation**
+```javascript
+// Parse --yes flag
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+let userSelection
+
+if (autoYes) {
+  // Auto mode: Use defaults
+  console.log(`[--yes] Auto-confirming plan:`)
+  console.log(`  - Confirmation: Allow`)
+  console.log(`  - Execution: Auto`)
+  console.log(`  - Review: Skip`)
+
+  userSelection = {
+    confirmation: "Allow",
+    execution_method: "Auto",
+    code_review_tool: "Skip"
+  }
+} else {
+  // Interactive mode: Ask user
+  // Note: Execution "Other" option allows specifying CLI tools from ~/.claude/cli-tools.json
+  userSelection = AskUserQuestion({
+    questions: [
+      {
+        question: `Confirm plan? (${plan.tasks.length} tasks, ${plan.complexity})`,
+        header: "Confirm",
+        multiSelect: false,
+        options: [
+          { label: "Allow", description: "Proceed as-is" },
+          { label: "Modify", description: "Adjust before execution" },
+          { label: "Cancel", description: "Abort workflow" }
+        ]
+      },
+      {
+        question: "Execution method:",
+        header: "Execution",
+        multiSelect: false,
+        options: [
+          { label: "Agent", description: "@code-developer agent" },
+          { label: "Codex", description: "codex CLI tool" },
+          { label: "Auto", description: `Auto: ${plan.complexity === 'Low' ? 'Agent' : 'Codex'}` }
+        ]
+      },
+      {
+        question: "Code review after execution?",
+        header: "Review",
+        multiSelect: false,
+        options: [
+          { label: "Gemini Review", description: "Gemini CLI review" },
+          { label: "Codex Review", description: "Git-aware review (prompt OR --uncommitted)" },
+          { label: "Agent Review", description: "@code-reviewer agent" },
+          { label: "Skip", description: "No review" }
+        ]
+      }
+    ]
+  })
+}
+```
+
+---
+
+### Phase 5: Execute to Execution
+
+**CRITICAL**: lite-plan NEVER executes code directly. ALL execution MUST go through lite-execute.
+
+**Step 5.1: Build executionContext**
+
+```javascript
+// Load manifest and all exploration files
+const manifest = JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
+const explorations = {}
+
+manifest.explorations.forEach(exp => {
+  if (file_exists(exp.path)) {
+    explorations[exp.angle] = JSON.parse(Read(exp.path))
+  }
+})
+
+const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
+
+executionContext = {
+  planObject: plan,
+  explorationsContext: explorations,
+  explorationAngles: manifest.explorations.map(e => e.angle),
+  explorationManifest: manifest,
+  clarificationContext: clarificationContext || null,
+  executionMethod: userSelection.execution_method,  // 全局默认，可被 executorAssignments 覆盖
+  codeReviewTool: userSelection.code_review_tool,
+  originalUserInput: task_description,
+
+  // 任务级 executor 分配（优先于全局 executionMethod）
+  executorAssignments: executorAssignments,  // { taskId: { executor, reason } }
+
+  session: {
+    id: sessionId,
+    folder: sessionFolder,
+    artifacts: {
+      explorations: manifest.explorations.map(exp => ({
+        angle: exp.angle,
+        path: exp.path
+      })),
+      explorations_manifest: `${sessionFolder}/explorations-manifest.json`,
+      plan: `${sessionFolder}/plan.json`
+    }
+  }
+}
+```
+
+**Step 5.2: Execute**
+
+```javascript
+// → Hand off to Phase 4: Lite Execute (phases/04-lite-execute.md) --in-memory
+```
+
+## Session Folder Structure
+
+```
+.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/
+├── exploration-{angle1}.json      # Exploration angle 1
+├── exploration-{angle2}.json      # Exploration angle 2
+├── exploration-{angle3}.json      # Exploration angle 3 (if applicable)
+├── exploration-{angle4}.json      # Exploration angle 4 (if applicable)
+├── explorations-manifest.json     # Exploration index
+└── plan.json                      # Implementation plan
+```
+
+**Example**:
+```
+.workflow/.lite-plan/implement-jwt-refresh-2025-11-25-14-30-25/
+├── exploration-architecture.json
+├── exploration-auth-patterns.json
+├── exploration-security.json
+├── explorations-manifest.json
+└── plan.json
+```
+
+## Error Handling
+
+| Error | Resolution |
+|-------|------------|
+| Exploration agent failure | Skip exploration, continue with task description only |
+| Planning agent failure | Fallback to direct planning by Claude |
+| Clarification timeout | Use exploration findings as-is |
+| Confirmation timeout | Save context, display resume instructions |
+| Modify loop > 3 times | Suggest breaking task or using full planning workflow (workflow-plan/SKILL.md) |
+
+---
+
+## Post-Phase Update
+
+After Phase 1 (Lite Plan) completes:
+- **Output Created**: `executionContext` with plan.json, explorations, clarifications, user selections
+- **Session Artifacts**: All files in `.workflow/.lite-plan/{session-id}/`
+- **Next Action**: Auto-continue to [Phase 4: Lite Execute](04-lite-execute.md) with --in-memory
+- **TodoWrite**: Mark "Lite Plan - Planning" as completed, start "Execution (Phase 4)"
--- a/.claude/skills/workflow-lite-plan/phases/02-multi-cli-plan.md
+++ b/.claude/skills/workflow-lite-plan/phases/02-multi-cli-plan.md
@@ -0,0 +1,570 @@
+# Phase 2: Multi-CLI Plan
+
+## Auto Mode
+
+When `--yes` or `-y`: Auto-approve plan, use recommended solution and execution method (Agent, Skip review).
+
+## Overview
+
+Multi-CLI collaborative planning with ACE context gathering and iterative cross-verification. Uses cli-discuss-agent for Gemini+Codex+Claude analysis to converge on optimal execution plan.
+
+## Quick Start
+
+**Parameters**:
+- `<task-description>` (required): Task description
+- `--max-rounds` (optional): Maximum discussion rounds (default: 3)
+- `--tools` (optional): CLI tools for analysis (default: gemini,codex)
+- `--mode` (optional): Execution mode: parallel or serial
+
+**Context Source**: ACE semantic search + Multi-CLI analysis
+**Output Directory**: `.workflow/.multi-cli-plan/{session-id}/`
+**Default Max Rounds**: 3 (convergence may complete earlier)
+**CLI Tools**: @cli-discuss-agent (analysis), @cli-lite-planning-agent (plan generation)
+**Execution**: Auto-hands off to Phase 4: Lite Execute (phases/04-lite-execute.md) after plan approval
+
+## What & Why
+
+### Core Concept
+
+Multi-CLI collaborative planning with **three-phase architecture**: ACE context gathering → Iterative multi-CLI discussion → Plan generation. Orchestrator delegates analysis to agents, only handles user decisions and session management.
+
+**Process**:
+- **Phase 1**: ACE semantic search gathers codebase context
+- **Phase 2**: cli-discuss-agent orchestrates Gemini/Codex/Claude for cross-verified analysis
+- **Phase 3-5**: User decision → Plan generation → Execution handoff
+
+**vs Single-CLI Planning**:
+- **Single**: One model perspective, potential blind spots
+- **Multi-CLI**: Cross-verification catches inconsistencies, builds consensus on solutions
+
+### Value Proposition
+
+1. **Multi-Perspective Analysis**: Gemini + Codex + Claude analyze from different angles
+2. **Cross-Verification**: Identify agreements/disagreements, build confidence
+3. **User-Driven Decisions**: Every round ends with user decision point
+4. **Iterative Convergence**: Progressive refinement until consensus reached
+
+### Orchestrator Boundary (CRITICAL)
+
+- **ONLY command** for multi-CLI collaborative planning
+- Manages: Session state, user decisions, agent delegation, phase transitions
+- Delegates: CLI execution to @cli-discuss-agent, plan generation to @cli-lite-planning-agent
+
+### Execution Flow
+
+```
+Phase 1: Context Gathering
+   └─ ACE semantic search, extract keywords, build context package
+
+Phase 2: Multi-CLI Discussion (Iterative, via @cli-discuss-agent)
+   ├─ Round N: Agent executes Gemini + Codex + Claude
+   ├─ Cross-verify findings, synthesize solutions
+   ├─ Write synthesis.json to rounds/{N}/
+   └─ Loop until convergence or max rounds
+
+Phase 3: Present Options
+   └─ Display solutions with trade-offs from agent output
+
+Phase 4: User Decision
+   ├─ Select solution approach
+   ├─ Select execution method (Agent/Codex/Auto)
+   ├─ Select code review tool (Skip/Gemini/Codex/Agent)
+   └─ Route:
+      ├─ Approve → Phase 5
+      ├─ Need More Analysis → Return to Phase 2
+      └─ Cancel → Save session
+
+Phase 5: Plan Generation & Execution Handoff
+   ├─ Generate plan.json (via @cli-lite-planning-agent)
+   ├─ Build executionContext with user selections
+   └─ Hand off to Phase 4: Lite Execute (phases/04-lite-execute.md) --in-memory
+```
+
+### Agent Roles
+
+| Agent | Responsibility |
+|-------|---------------|
+| **Orchestrator** | Session management, ACE context, user decisions, phase transitions, executionContext assembly |
+| **@cli-discuss-agent** | Multi-CLI execution (Gemini/Codex/Claude), cross-verification, solution synthesis, synthesis.json output |
+| **@cli-lite-planning-agent** | Task decomposition, plan.json generation following schema |
+
+## Core Responsibilities
+
+### Phase 1: Context Gathering
+
+**Session Initialization**:
+```javascript
+const sessionId = `MCP-${taskSlug}-${date}`
+const sessionFolder = `.workflow/.multi-cli-plan/${sessionId}`
+Bash(`mkdir -p ${sessionFolder}/rounds`)
+```
+
+**ACE Context Queries**:
+```javascript
+const aceQueries = [
+  `Project architecture related to ${keywords}`,
+  `Existing implementations of ${keywords[0]}`,
+  `Code patterns for ${keywords} features`,
+  `Integration points for ${keywords[0]}`
+]
+// Execute via mcp__ace-tool__search_context
+```
+
+**Context Package** (passed to agent):
+- `relevant_files[]` - Files identified by ACE
+- `detected_patterns[]` - Code patterns found
+- `architecture_insights` - Structure understanding
+
+### Phase 2: Agent Delegation
+
+**Core Principle**: Orchestrator only delegates and reads output - NO direct CLI execution.
+
+**⚠️ CRITICAL - CLI EXECUTION REQUIREMENT**:
+- **MUST** execute CLI calls via `Bash` with `run_in_background: true`
+- **MUST** wait for hook callback to receive complete results
+- **MUST NOT** proceed with next phase until CLI execution fully completes
+- Do NOT use `TaskOutput` polling during CLI execution - wait passively for results
+- Minimize scope: Proceed only when 100% result available
+
+**Agent Invocation**:
+```javascript
+Task({
+  subagent_type: "cli-discuss-agent",
+  run_in_background: false,
+  description: `Discussion round ${currentRound}`,
+  prompt: `
+## Input Context
+- task_description: ${taskDescription}
+- round_number: ${currentRound}
+- session: { id: "${sessionId}", folder: "${sessionFolder}" }
+- ace_context: ${JSON.stringify(contextPackageage)}
+- previous_rounds: ${JSON.stringify(analysisResults)}
+- user_feedback: ${userFeedback || 'None'}
+- cli_config: { tools: ["gemini", "codex"], mode: "parallel", fallback_chain: ["gemini", "codex", "claude"] }
+
+## Execution Process
+1. Parse input context (handle JSON strings)
+2. Check if ACE supplementary search needed
+3. Build CLI prompts with context
+4. Execute CLIs (parallel or serial per cli_config.mode)
+5. Parse CLI outputs, handle failures with fallback
+6. Perform cross-verification between CLI results
+7. Synthesize solutions, calculate scores
+8. Calculate convergence, generate clarification questions
+9. Write synthesis.json
+
+## Output
+Write: ${sessionFolder}/rounds/${currentRound}/synthesis.json
+
+## Completion Checklist
+- [ ] All configured CLI tools executed (or fallback triggered)
+- [ ] Cross-verification completed with agreements/disagreements
+- [ ] 2-3 solutions generated with file:line references
+- [ ] Convergence score calculated (0.0-1.0)
+- [ ] synthesis.json written with all Primary Fields
+`
+})
+```
+
+**Read Agent Output**:
+```javascript
+const synthesis = JSON.parse(Read(`${sessionFolder}/rounds/${round}/synthesis.json`))
+// Access top-level fields: solutions, convergence, cross_verification, clarification_questions
+```
+
+**Convergence Decision**:
+```javascript
+if (synthesis.convergence.recommendation === 'converged') {
+  // Proceed to Phase 3
+} else if (synthesis.convergence.recommendation === 'user_input_needed') {
+  // Collect user feedback, return to Phase 2
+} else {
+  // Continue to next round if new_insights && round < maxRounds
+}
+```
+
+### Phase 3: Present Options
+
+**Display from Agent Output** (no processing):
+```javascript
+console.log(`
+## Solution Options
+
+${synthesis.solutions.map((s, i) => `
+**Option ${i+1}: ${s.name}**
+Source: ${s.source_cli.join(' + ')}
+Effort: ${s.effort} | Risk: ${s.risk}
+
+Pros: ${s.pros.join(', ')}
+Cons: ${s.cons.join(', ')}
+
+Files: ${s.affected_files.slice(0,3).map(f => `${f.file}:${f.line}`).join(', ')}
+`).join('\n')}
+
+## Cross-Verification
+Agreements: ${synthesis.cross_verification.agreements.length}
+Disagreements: ${synthesis.cross_verification.disagreements.length}
+`)
+```
+
+### Phase 4: User Decision
+
+**Decision Options**:
+```javascript
+AskUserQuestion({
+  questions: [
+    {
+      question: "Which solution approach?",
+      header: "Solution",
+      multiSelect: false,
+      options: solutions.map((s, i) => ({
+        label: `Option ${i+1}: ${s.name}`,
+        description: `${s.effort} effort, ${s.risk} risk`
+      })).concat([
+        { label: "Need More Analysis", description: "Return to Phase 2" }
+      ])
+    },
+    {
+      question: "Execution method:",
+      header: "Execution",
+      multiSelect: false,
+      options: [
+        { label: "Agent", description: "@code-developer agent" },
+        { label: "Codex", description: "codex CLI tool" },
+        { label: "Auto", description: "Auto-select based on complexity" }
+      ]
+    },
+    {
+      question: "Code review after execution?",
+      header: "Review",
+      multiSelect: false,
+      options: [
+        { label: "Skip", description: "No review" },
+        { label: "Gemini Review", description: "Gemini CLI tool" },
+        { label: "Codex Review", description: "codex review --uncommitted" },
+        { label: "Agent Review", description: "Current agent review" }
+      ]
+    }
+  ]
+})
+```
+
+**Routing**:
+- Approve + execution method → Phase 5
+- Need More Analysis → Phase 2 with feedback
+- Cancel → Save session for resumption
+
+### Phase 5: Plan Generation & Execution Handoff
+
+**Step 1: Build Context-Package** (Orchestrator responsibility):
+```javascript
+// Extract key information from user decision and synthesis
+const contextPackage = {
+  // Core solution details
+  solution: {
+    name: selectedSolution.name,
+    source_cli: selectedSolution.source_cli,
+    feasibility: selectedSolution.feasibility,
+    effort: selectedSolution.effort,
+    risk: selectedSolution.risk,
+    summary: selectedSolution.summary
+  },
+  // Implementation plan (tasks, flow, milestones)
+  implementation_plan: selectedSolution.implementation_plan,
+  // Dependencies
+  dependencies: selectedSolution.dependencies || { internal: [], external: [] },
+  // Technical concerns
+  technical_concerns: selectedSolution.technical_concerns || [],
+  // Consensus from cross-verification
+  consensus: {
+    agreements: synthesis.cross_verification.agreements,
+    resolved_conflicts: synthesis.cross_verification.resolution
+  },
+  // User constraints (from Phase 4 feedback)
+  constraints: userConstraints || [],
+  // Task context
+  task_description: taskDescription,
+  session_id: sessionId
+}
+
+// Write context-package for traceability
+Write(`${sessionFolder}/context-package.json`, JSON.stringify(contextPackage, null, 2))
+```
+
+**Context-Package Schema**:
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `solution` | object | User-selected solution from synthesis |
+| `solution.name` | string | Solution identifier |
+| `solution.feasibility` | number | Viability score (0-1) |
+| `solution.summary` | string | Brief analysis summary |
+| `implementation_plan` | object | Task breakdown with flow and dependencies |
+| `implementation_plan.approach` | string | High-level technical strategy |
+| `implementation_plan.tasks[]` | array | Discrete tasks with id, name, depends_on, files |
+| `implementation_plan.execution_flow` | string | Task sequence (e.g., "T1 → T2 → T3") |
+| `implementation_plan.milestones` | string[] | Key checkpoints |
+| `dependencies` | object | Module and package dependencies |
+| `technical_concerns` | string[] | Risks and blockers |
+| `consensus` | object | Cross-verified agreements from multi-CLI |
+| `constraints` | string[] | User-specified constraints from Phase 4 |
+
+```json
+{
+  "solution": {
+    "name": "Strategy Pattern Refactoring",
+    "source_cli": ["gemini", "codex"],
+    "feasibility": 0.88,
+    "effort": "medium",
+    "risk": "low",
+    "summary": "Extract payment gateway interface, implement strategy pattern for multi-gateway support"
+  },
+  "implementation_plan": {
+    "approach": "Define interface → Create concrete strategies → Implement factory → Migrate existing code",
+    "tasks": [
+      {"id": "T1", "name": "Define PaymentGateway interface", "depends_on": [], "files": [{"file": "src/types/payment.ts", "line": 1, "action": "create"}], "key_point": "Include all existing Stripe methods"},
+      {"id": "T2", "name": "Implement StripeGateway", "depends_on": ["T1"], "files": [{"file": "src/payment/stripe.ts", "line": 1, "action": "create"}], "key_point": "Wrap existing logic"},
+      {"id": "T3", "name": "Create GatewayFactory", "depends_on": ["T1"], "files": [{"file": "src/payment/factory.ts", "line": 1, "action": "create"}], "key_point": null},
+      {"id": "T4", "name": "Migrate processor to use factory", "depends_on": ["T2", "T3"], "files": [{"file": "src/payment/processor.ts", "line": 45, "action": "modify"}], "key_point": "Backward compatible"}
+    ],
+    "execution_flow": "T1 → (T2 | T3) → T4",
+    "milestones": ["Interface defined", "Gateway implementations complete", "Migration done"]
+  },
+  "dependencies": {
+    "internal": ["@/lib/payment-gateway", "@/types/payment"],
+    "external": ["stripe@^14.0.0"]
+  },
+  "technical_concerns": ["Existing tests must pass", "No breaking API changes"],
+  "consensus": {
+    "agreements": ["Use strategy pattern", "Keep existing API"],
+    "resolved_conflicts": "Factory over DI for simpler integration"
+  },
+  "constraints": ["backward compatible", "no breaking changes to PaymentResult type"],
+  "task_description": "Refactor payment processing for multi-gateway support",
+  "session_id": "MCP-payment-refactor-2026-01-14"
+}
+```
+
+**Step 2: Invoke Planning Agent**:
+```javascript
+Task({
+  subagent_type: "cli-lite-planning-agent",
+  run_in_background: false,
+  description: "Generate implementation plan",
+  prompt: `
+## Schema Reference
+Execute: cat ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json
+
+## Context-Package (from orchestrator)
+${JSON.stringify(contextPackage, null, 2)}
+
+## Execution Process
+1. Read plan-json-schema.json for output structure
+2. Read project-tech.json and project-guidelines.json
+3. Parse context-package fields:
+   - solution: name, feasibility, summary
+   - implementation_plan: tasks[], execution_flow, milestones
+   - dependencies: internal[], external[]
+   - technical_concerns: risks/blockers
+   - consensus: agreements, resolved_conflicts
+   - constraints: user requirements
+4. Use implementation_plan.tasks[] as task foundation
+5. Preserve task dependencies (depends_on) and execution_flow
+6. Expand tasks with detailed acceptance criteria
+7. Generate plan.json following schema exactly
+
+## Output
+- ${sessionFolder}/plan.json
+
+## Completion Checklist
+- [ ] plan.json preserves task dependencies from implementation_plan
+- [ ] Task execution order follows execution_flow
+- [ ] Key_points reflected in task descriptions
+- [ ] User constraints applied to implementation
+- [ ] Acceptance criteria are testable
+- [ ] Schema fields match plan-json-schema.json exactly
+`
+})
+```
+
+**Step 3: Build executionContext**:
+```javascript
+// After plan.json is generated by cli-lite-planning-agent
+const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
+
+// Build executionContext (same structure as lite-plan)
+executionContext = {
+  planObject: plan,
+  explorationsContext: null,  // Multi-CLI doesn't use exploration files
+  explorationAngles: [],      // No exploration angles
+  explorationManifest: null,  // No manifest
+  clarificationContext: null,  // Store user feedback from Phase 2 if exists
+  executionMethod: userSelection.execution_method,  // From Phase 4
+  codeReviewTool: userSelection.code_review_tool,   // From Phase 4
+  originalUserInput: taskDescription,
+
+  // Optional: Task-level executor assignments
+  executorAssignments: null,  // Could be enhanced in future
+
+  session: {
+    id: sessionId,
+    folder: sessionFolder,
+    artifacts: {
+      explorations: [],  // No explorations in multi-CLI workflow
+      explorations_manifest: null,
+      plan: `${sessionFolder}/plan.json`,
+      synthesis_rounds: Array.from({length: currentRound}, (_, i) =>
+        `${sessionFolder}/rounds/${i+1}/synthesis.json`
+      ),
+      context_package: `${sessionFolder}/context-package.json`
+    }
+  }
+}
+```
+
+**Step 4: Hand off to Execution**:
+```javascript
+// Hand off to Phase 4: Lite Execute (phases/04-lite-execute.md) with in-memory context
+// executionContext is passed in-memory to the execution phase
+```
+
+## Output File Structure
+
+```
+.workflow/.multi-cli-plan/{MCP-task-slug-YYYY-MM-DD}/
+├── session-state.json          # Session tracking (orchestrator)
+├── rounds/
+│   ├── 1/synthesis.json        # Round 1 analysis (cli-discuss-agent)
+│   ├── 2/synthesis.json        # Round 2 analysis (cli-discuss-agent)
+│   └── .../
+├── context-package.json        # Extracted context for planning (orchestrator)
+└── plan.json                   # Structured plan (cli-lite-planning-agent)
+```
+
+**File Producers**:
+
+| File | Producer | Content |
+|------|----------|---------|
+| `session-state.json` | Orchestrator | Session metadata, rounds, decisions |
+| `rounds/*/synthesis.json` | cli-discuss-agent | Solutions, convergence, cross-verification |
+| `context-package.json` | Orchestrator | Extracted solution, dependencies, consensus for planning |
+| `plan.json` | cli-lite-planning-agent | Structured tasks for lite-execute |
+
+## synthesis.json Schema
+
+```json
+{
+  "round": 1,
+  "solutions": [{
+    "name": "Solution Name",
+    "source_cli": ["gemini", "codex"],
+    "feasibility": 0.85,
+    "effort": "low|medium|high",
+    "risk": "low|medium|high",
+    "summary": "Brief analysis summary",
+    "implementation_plan": {
+      "approach": "High-level technical approach",
+      "tasks": [
+        {"id": "T1", "name": "Task", "depends_on": [], "files": [], "key_point": "..."}
+      ],
+      "execution_flow": "T1 → T2 → T3",
+      "milestones": ["Checkpoint 1", "Checkpoint 2"]
+    },
+    "dependencies": {"internal": [], "external": []},
+    "technical_concerns": ["Risk 1", "Blocker 2"]
+  }],
+  "convergence": {
+    "score": 0.85,
+    "new_insights": false,
+    "recommendation": "converged|continue|user_input_needed"
+  },
+  "cross_verification": {
+    "agreements": [],
+    "disagreements": [],
+    "resolution": "..."
+  },
+  "clarification_questions": []
+}
+```
+
+**Key Planning Fields**:
+
+| Field | Purpose |
+|-------|---------|
+| `feasibility` | Viability score (0-1) |
+| `implementation_plan.tasks[]` | Discrete tasks with dependencies |
+| `implementation_plan.execution_flow` | Task sequence visualization |
+| `implementation_plan.milestones` | Key checkpoints |
+| `technical_concerns` | Risks and blockers |
+
+**Note**: Solutions ranked by internal scoring (array order = priority)
+
+## TodoWrite Structure
+
+**Initialization**:
+```javascript
+TodoWrite({ todos: [
+  { content: "Phase 1: Context Gathering", status: "in_progress", activeForm: "Gathering context" },
+  { content: "Phase 2: Multi-CLI Discussion", status: "pending", activeForm: "Running discussion" },
+  { content: "Phase 3: Present Options", status: "pending", activeForm: "Presenting options" },
+  { content: "Phase 4: User Decision", status: "pending", activeForm: "Awaiting decision" },
+  { content: "Phase 5: Plan Generation", status: "pending", activeForm: "Generating plan" }
+]})
+```
+
+**During Discussion Rounds**:
+```javascript
+TodoWrite({ todos: [
+  { content: "Phase 1: Context Gathering", status: "completed", activeForm: "Gathering context" },
+  { content: "Phase 2: Multi-CLI Discussion", status: "in_progress", activeForm: "Running discussion" },
+  { content: "  → Round 1: Initial analysis", status: "completed", activeForm: "Analyzing" },
+  { content: "  → Round 2: Deep verification", status: "in_progress", activeForm: "Verifying" },
+  { content: "Phase 3: Present Options", status: "pending", activeForm: "Presenting options" },
+  // ...
+]})
+```
+
+## Error Handling
+
+| Error | Resolution |
+|-------|------------|
+| ACE search fails | Fall back to Glob/Grep for file discovery |
+| Agent fails | Retry once, then present partial results |
+| CLI timeout (in agent) | Agent uses fallback: gemini → codex → claude |
+| No convergence | Present best options, flag uncertainty |
+| synthesis.json parse error | Request agent retry |
+| User cancels | Save session for later resumption |
+
+## Configuration
+
+| Flag | Default | Description |
+|------|---------|-------------|
+| `--max-rounds` | 3 | Maximum discussion rounds |
+| `--tools` | gemini,codex | CLI tools for analysis |
+| `--mode` | parallel | Execution mode: parallel or serial |
+| `--auto-execute` | false | Auto-execute after approval |
+
+## Best Practices
+
+1. **Be Specific**: Detailed task descriptions improve ACE context quality
+2. **Provide Feedback**: Use clarification rounds to refine requirements
+3. **Trust Cross-Verification**: Multi-CLI consensus indicates high confidence
+4. **Review Trade-offs**: Consider pros/cons before selecting solution
+5. **Check synthesis.json**: Review agent output for detailed analysis
+6. **Iterate When Needed**: Don't hesitate to request more analysis
+
+## Related Phases
+
+- Simpler single-round planning: [Phase 1: Lite Plan](01-lite-plan.md)
+- Shared execution engine: [Phase 4: Lite Execute](04-lite-execute.md)
+- Full planning workflow: [workflow-plan/SKILL.md](../../workflow-plan/SKILL.md)
+
+---
+
+## Post-Phase Update
+
+After Phase 2 (Multi-CLI Plan) completes:
+- **Output Created**: `executionContext` with plan.json, synthesis rounds, context-package, user selections
+- **Session Artifacts**: All files in `.workflow/.multi-cli-plan/{session-id}/`
+- **Next Action**: Auto-continue to [Phase 4: Lite Execute](04-lite-execute.md) with --in-memory
+- **TodoWrite**: Mark "Multi-CLI Plan - Planning" as completed, start "Execution (Phase 4)"
--- a/.claude/skills/workflow-lite-plan/phases/03-lite-fix.md
+++ b/.claude/skills/workflow-lite-plan/phases/03-lite-fix.md
@@ -0,0 +1,799 @@
+# Phase 3: Lite Fix
+
+## Overview
+
+Intelligent lightweight bug fixing command with dynamic workflow adaptation based on severity assessment. Focuses on diagnosis phases (root cause analysis, impact assessment, fix planning, confirmation) and delegates execution to Phase 4: Lite Execute (phases/04-lite-execute.md).
+
+**Core capabilities:**
+- Intelligent bug analysis with automatic severity detection
+- Dynamic code diagnosis (cli-explore-agent) for root cause identification
+- Interactive clarification after diagnosis to gather missing information
+- Adaptive fix planning strategy (direct Claude vs cli-lite-planning-agent) based on complexity
+- Two-step confirmation: fix-plan display -> multi-dimensional input collection
+- Execution handoff with complete context to Phase 4: Lite Execute (phases/04-lite-execute.md)
+
+## Parameters
+
+- `-y, --yes`: Skip all confirmations (auto mode)
+- `--hotfix, -h`: Production hotfix mode (minimal diagnosis, fast fix)
+- `<bug-description>` (required): Bug description, error message, or path to .md file
+
+## Output Artifacts
+
+| Artifact | Description |
+|----------|-------------|
+| `diagnosis-{angle}.json` | Per-angle diagnosis results (1-4 files based on severity) |
+| `diagnoses-manifest.json` | Index of all diagnosis files |
+| `planning-context.md` | Evidence paths + synthesized understanding |
+| `fix-plan.json` | Structured fix plan (fix-plan-json-schema.json) |
+
+**Output Directory**: `.workflow/.lite-fix/{bug-slug}-{YYYY-MM-DD}/`
+
+**Agent Usage**:
+- Low/Medium severity → Direct Claude planning (no agent)
+- High/Critical severity → `cli-lite-planning-agent` generates `fix-plan.json`
+
+**Schema Reference**: `~/.claude/workflows/cli-templates/schemas/fix-plan-json-schema.json`
+
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Clarification Questions**: Skipped (no clarification phase)
+- **Fix Plan Confirmation**: Auto-selected "Allow"
+- **Execution Method**: Auto-selected "Auto"
+- **Code Review**: Auto-selected "Skip"
+- **Severity**: Uses auto-detected severity (no manual override)
+- **Hotfix Mode**: Respects --hotfix flag if present, otherwise normal mode
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+const hotfixMode = $ARGUMENTS.includes('--hotfix') || $ARGUMENTS.includes('-h')
+```
+
+## Execution Process
+
+```
+Phase 1: Bug Analysis & Diagnosis
+   |- Parse input (description, error message, or .md file)
+   |- Intelligent severity pre-assessment (Low/Medium/High/Critical)
+   |- Diagnosis decision (auto-detect or --hotfix flag)
+   |- Context protection: If file reading >=50k chars -> force cli-explore-agent
+   +- Decision:
+      |- needsDiagnosis=true -> Launch parallel cli-explore-agents (1-4 based on severity)
+      +- needsDiagnosis=false (hotfix) -> Skip directly to Phase 3 (Fix Planning)
+
+Phase 2: Clarification (optional, multi-round)
+   |- Aggregate clarification_needs from all diagnosis angles
+   |- Deduplicate similar questions
+   +- Decision:
+      |- Has clarifications -> AskUserQuestion (max 4 questions per round, multiple rounds allowed)
+      +- No clarifications -> Skip to Phase 3
+
+Phase 3: Fix Planning (NO CODE EXECUTION - planning only)
+   +- Decision (based on Phase 1 severity):
+      |- Low/Medium -> Load schema: cat ~/.claude/workflows/cli-templates/schemas/fix-plan-json-schema.json -> Direct Claude planning (following schema) -> fix-plan.json -> MUST proceed to Phase 4
+      +- High/Critical -> cli-lite-planning-agent -> fix-plan.json -> MUST proceed to Phase 4
+
+Phase 4: Confirmation & Selection
+   |- Display fix-plan summary (tasks, severity, estimated time)
+   +- AskUserQuestion:
+      |- Confirm: Allow / Modify / Cancel
+      |- Execution: Agent / Codex / Auto
+      +- Review: Gemini / Agent / Skip
+
+Phase 5: Execute
+   |- Build executionContext (fix-plan + diagnoses + clarifications + selections)
+   +- Hand off to Phase 4: Lite Execute (phases/04-lite-execute.md) --in-memory --mode bugfix
+```
+
+## Implementation
+
+### Phase 1: Intelligent Multi-Angle Diagnosis
+
+**Session Setup** (MANDATORY - follow exactly):
+```javascript
+// Helper: Get UTC+8 (China Standard Time) ISO string
+const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
+
+const bugSlug = bug_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
+const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-11-29
+
+const sessionId = `${bugSlug}-${dateStr}`  // e.g., "user-avatar-upload-fails-2025-11-29"
+const sessionFolder = `.workflow/.lite-fix/${sessionId}`
+
+bash(`mkdir -p ${sessionFolder} && test -d ${sessionFolder} && echo "SUCCESS: ${sessionFolder}" || echo "FAILED: ${sessionFolder}"`)
+```
+
+**Diagnosis Decision Logic**:
+```javascript
+const hotfixMode = $ARGUMENTS.includes('--hotfix') || $ARGUMENTS.includes('-h')
+
+needsDiagnosis = (
+  !hotfixMode &&
+  (
+    bug.lacks_specific_error_message ||
+    bug.requires_codebase_context ||
+    bug.needs_execution_tracing ||
+    bug.root_cause_unclear
+  )
+)
+
+if (!needsDiagnosis) {
+  // Skip to Phase 2 (Clarification) or Phase 3 (Fix Planning)
+  proceed_to_next_phase()
+}
+```
+
+**Context Protection**: File reading >=50k chars -> force `needsDiagnosis=true` (delegate to cli-explore-agent)
+
+**Severity Pre-Assessment** (Intelligent Analysis):
+```javascript
+// Analyzes bug severity based on:
+// - Symptoms: Error messages, crash reports, user complaints
+// - Scope: How many users/features are affected?
+// - Urgency: Production down vs minor inconvenience
+// - Impact: Data loss, security, business impact
+
+const severity = analyzeBugSeverity(bug_description)
+// Returns: 'Low' | 'Medium' | 'High' | 'Critical'
+// Low: Minor UI issue, localized, no data impact
+// Medium: Multiple users affected, degraded functionality
+// High: Significant functionality broken, many users affected
+// Critical: Production down, data loss risk, security issue
+
+// Angle assignment based on bug type (orchestrator decides, not agent)
+const DIAGNOSIS_ANGLE_PRESETS = {
+  runtime_error: ['error-handling', 'dataflow', 'state-management', 'edge-cases'],
+  performance: ['performance', 'bottlenecks', 'caching', 'data-access'],
+  security: ['security', 'auth-patterns', 'dataflow', 'validation'],
+  data_corruption: ['data-integrity', 'state-management', 'transactions', 'validation'],
+  ui_bug: ['state-management', 'event-handling', 'rendering', 'data-binding'],
+  integration: ['api-contracts', 'error-handling', 'timeouts', 'fallbacks']
+}
+
+function selectDiagnosisAngles(bugDescription, count) {
+  const text = bugDescription.toLowerCase()
+  let preset = 'runtime_error' // default
+
+  if (/slow|timeout|performance|lag|hang/.test(text)) preset = 'performance'
+  else if (/security|auth|permission|access|token/.test(text)) preset = 'security'
+  else if (/corrupt|data|lost|missing|inconsistent/.test(text)) preset = 'data_corruption'
+  else if (/ui|display|render|style|click|button/.test(text)) preset = 'ui_bug'
+  else if (/api|integration|connect|request|response/.test(text)) preset = 'integration'
+
+  return DIAGNOSIS_ANGLE_PRESETS[preset].slice(0, count)
+}
+
+const selectedAngles = selectDiagnosisAngles(bug_description, severity === 'Critical' ? 4 : (severity === 'High' ? 3 : (severity === 'Medium' ? 2 : 1)))
+
+console.log(`
+## Diagnosis Plan
+
+Bug Severity: ${severity}
+Selected Angles: ${selectedAngles.join(', ')}
+
+Launching ${selectedAngles.length} parallel diagnoses...
+`)
+```
+
+**Launch Parallel Diagnoses** - Orchestrator assigns angle to each agent:
+
+```javascript
+// Launch agents with pre-assigned diagnosis angles
+const diagnosisTasks = selectedAngles.map((angle, index) =>
+  Task(
+    subagent_type="cli-explore-agent",
+    run_in_background=false,
+    description=`Diagnose: ${angle}`,
+    prompt=`
+## Task Objective
+Execute **${angle}** diagnosis for bug root cause analysis. Analyze codebase from this specific angle to discover root cause, affected paths, and fix hints.
+
+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output File**: ${sessionFolder}/diagnosis-${angle}.json
+
+## Assigned Context
+- **Diagnosis Angle**: ${angle}
+- **Bug Description**: ${bug_description}
+- **Diagnosis Index**: ${index + 1} of ${selectedAngles.length}
+
+## MANDATORY FIRST STEPS (Execute by Agent)
+**You (cli-explore-agent) MUST execute these steps in order:**
+1. Run: ccw tool exec get_modules_by_depth '{}' (project structure)
+2. Run: rg -l "{error_keyword_from_bug}" --type ts (locate relevant files)
+3. Execute: cat ~/.claude/workflows/cli-templates/schemas/diagnosis-json-schema.json (get output schema reference)
+4. Read: .workflow/project-tech.json (technology stack and architecture context)
+5. Read: .workflow/project-guidelines.json (user-defined constraints and conventions)
+
+## Diagnosis Strategy (${angle} focus)
+
+**Step 1: Error Tracing** (Bash)
+- rg for error messages, stack traces, log patterns
+- git log --since='2 weeks ago' for recent changes
+- Trace execution path in affected modules
+
+**Step 2: Root Cause Analysis** (Gemini CLI)
+- What code paths lead to this ${angle} issue?
+- What edge cases are not handled from ${angle} perspective?
+- What recent changes might have introduced this bug?
+
+**Step 3: Write Output**
+- Consolidate ${angle} findings into JSON
+- Identify ${angle}-specific clarification needs
+- Provide fix hints based on ${angle} analysis
+
+## Expected Output
+
+**Schema Reference**: Schema obtained in MANDATORY FIRST STEPS step 3, follow schema exactly
+
+**Required Fields** (all ${angle} focused):
+- symptom: Bug symptoms and error messages
+- root_cause: Root cause hypothesis from ${angle} perspective
+  **IMPORTANT**: Use structured format:
+  \`{file: "src/module/file.ts", line_range: "45-60", issue: "Description", confidence: 0.85}\`
+- affected_files: Files involved from ${angle} perspective
+  **IMPORTANT**: Use object format with relevance scores:
+  \`[{path: "src/file.ts", relevance: 0.85, rationale: "Contains ${angle} logic"}]\`
+- reproduction_steps: Steps to reproduce the bug
+- fix_hints: Suggested fix approaches from ${angle} viewpoint
+- dependencies: Dependencies relevant to ${angle} diagnosis
+- constraints: ${angle}-specific limitations affecting fix
+- clarification_needs: ${angle}-related ambiguities (options array + recommended index)
+- _metadata.diagnosis_angle: "${angle}"
+- _metadata.diagnosis_index: ${index + 1}
+
+## Success Criteria
+- [ ] Schema obtained via cat diagnosis-json-schema.json
+- [ ] get_modules_by_depth.sh executed
+- [ ] Root cause identified with confidence score
+- [ ] At least 3 affected files identified with ${angle} rationale
+- [ ] Fix hints are actionable (specific code changes, not generic advice)
+- [ ] Reproduction steps are verifiable
+- [ ] JSON output follows schema exactly
+- [ ] clarification_needs includes options + recommended
+
+## Execution
+**Write**: \`${sessionFolder}/diagnosis-${angle}.json\`
+**Return**: 2-3 sentence summary of ${angle} diagnosis findings
+`
+  )
+)
+
+// Execute all diagnosis tasks in parallel
+```
+
+**Auto-discover Generated Diagnosis Files**:
+```javascript
+// After diagnoses complete, auto-discover all diagnosis-*.json files
+const diagnosisFiles = bash(`find ${sessionFolder} -name "diagnosis-*.json" -type f`)
+  .split('\n')
+  .filter(f => f.trim())
+
+// Read metadata to build manifest
+const diagnosisManifest = {
+  session_id: sessionId,
+  bug_description: bug_description,
+  timestamp: getUtc8ISOString(),
+  severity: severity,
+  diagnosis_count: diagnosisFiles.length,
+  diagnoses: diagnosisFiles.map(file => {
+    const data = JSON.parse(Read(file))
+    const filename = path.basename(file)
+    return {
+      angle: data._metadata.diagnosis_angle,
+      file: filename,
+      path: file,
+      index: data._metadata.diagnosis_index
+    }
+  })
+}
+
+Write(`${sessionFolder}/diagnoses-manifest.json`, JSON.stringify(diagnosisManifest, null, 2))
+
+console.log(`
+## Diagnosis Complete
+
+Generated diagnosis files in ${sessionFolder}:
+${diagnosisManifest.diagnoses.map(d => `- diagnosis-${d.angle}.json (angle: ${d.angle})`).join('\n')}
+
+Manifest: diagnoses-manifest.json
+Angles diagnosed: ${diagnosisManifest.diagnoses.map(d => d.angle).join(', ')}
+`)
+```
+
+**Output**:
+- `${sessionFolder}/diagnosis-{angle1}.json`
+- `${sessionFolder}/diagnosis-{angle2}.json`
+- ... (1-4 files based on severity)
+- `${sessionFolder}/diagnoses-manifest.json`
+
+---
+
+### Phase 2: Clarification (Optional, Multi-Round)
+
+**Skip if**: No diagnosis or `clarification_needs` is empty across all diagnoses
+
+**⚠️ CRITICAL**: AskUserQuestion tool limits max 4 questions per call. **MUST execute multiple rounds** to exhaust all clarification needs - do NOT stop at round 1.
+
+**Aggregate clarification needs from all diagnosis angles**:
+```javascript
+// Load manifest and all diagnosis files
+const manifest = JSON.parse(Read(`${sessionFolder}/diagnoses-manifest.json`))
+const diagnoses = manifest.diagnoses.map(diag => ({
+  angle: diag.angle,
+  data: JSON.parse(Read(diag.path))
+}))
+
+// Aggregate clarification needs from all diagnoses
+const allClarifications = []
+diagnoses.forEach(diag => {
+  if (diag.data.clarification_needs?.length > 0) {
+    diag.data.clarification_needs.forEach(need => {
+      allClarifications.push({
+        ...need,
+        source_angle: diag.angle
+      })
+    })
+  }
+})
+
+// Deduplicate by question similarity
+function deduplicateClarifications(clarifications) {
+  const unique = []
+  clarifications.forEach(c => {
+    const isDuplicate = unique.some(u =>
+      u.question.toLowerCase() === c.question.toLowerCase()
+    )
+    if (!isDuplicate) unique.push(c)
+  })
+  return unique
+}
+
+const uniqueClarifications = deduplicateClarifications(allClarifications)
+
+// Parse --yes flag
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+if (autoYes) {
+  // Auto mode: Skip clarification phase
+  console.log(`[--yes] Skipping ${uniqueClarifications.length} clarification questions`)
+  console.log(`Proceeding to fix planning with diagnosis results...`)
+  // Continue to Phase 3
+} else if (uniqueClarifications.length > 0) {
+  // Interactive mode: Multi-round clarification
+  // ⚠️ MUST execute ALL rounds until uniqueClarifications exhausted
+  const BATCH_SIZE = 4
+  const totalRounds = Math.ceil(uniqueClarifications.length / BATCH_SIZE)
+
+  for (let i = 0; i < uniqueClarifications.length; i += BATCH_SIZE) {
+    const batch = uniqueClarifications.slice(i, i + BATCH_SIZE)
+    const currentRound = Math.floor(i / BATCH_SIZE) + 1
+
+    console.log(`### Clarification Round ${currentRound}/${totalRounds}`)
+
+    AskUserQuestion({
+      questions: batch.map(need => ({
+        question: `[${need.source_angle}] ${need.question}\n\nContext: ${need.context}`,
+        header: need.source_angle,
+        multiSelect: false,
+        options: need.options.map((opt, index) => {
+          const isRecommended = need.recommended === index
+          return {
+            label: isRecommended ? `${opt} ★` : opt,
+            description: isRecommended ? `Use ${opt} approach (Recommended)` : `Use ${opt} approach`
+          }
+        })
+      }))
+    })
+
+    // Store batch responses in clarificationContext before next round
+  }
+}
+```
+
+**Output**: `clarificationContext` (in-memory)
+
+---
+
+### Phase 3: Fix Planning
+
+**Planning Strategy Selection** (based on Phase 1 severity):
+
+**IMPORTANT**: Phase 3 is **planning only** - NO code execution. All execution happens in Phase 5 via lite-execute.
+
+**Low/Medium Severity** - Direct planning by Claude:
+```javascript
+// Step 1: Read schema
+const schema = Bash(`cat ~/.claude/workflows/cli-templates/schemas/fix-plan-json-schema.json`)
+
+// Step 2: Generate fix-plan following schema (Claude directly, no agent)
+// For Medium complexity: include rationale + verification (optional, but recommended)
+const fixPlan = {
+  summary: "...",
+  root_cause: "...",
+  strategy: "immediate_patch|comprehensive_fix|refactor",
+  tasks: [...],  // Each task: { id, title, scope, ..., depends_on, complexity }
+  estimated_time: "...",
+  recommended_execution: "Agent",
+  severity: severity,
+  risk_level: "...",
+
+  // Medium complexity fields (optional for direct planning, auto-filled for Low)
+  ...(severity === "Medium" ? {
+    design_decisions: [
+      {
+        decision: "Use immediate_patch strategy for minimal risk",
+        rationale: "Keeps changes localized and quick to review",
+        tradeoff: "Defers comprehensive refactoring"
+      }
+    ],
+    tasks_with_rationale: {
+      // Each task gets rationale if Medium
+      task_rationale_example: {
+        rationale: {
+          chosen_approach: "Direct fix approach",
+          alternatives_considered: ["Workaround", "Refactor"],
+          decision_factors: ["Minimal impact", "Quick turnaround"],
+          tradeoffs: "Doesn't address underlying issue"
+        },
+        verification: {
+          unit_tests: ["test_bug_fix_basic"],
+          integration_tests: [],
+          manual_checks: ["Reproduce issue", "Verify fix"],
+          success_metrics: ["Issue resolved", "No regressions"]
+        }
+      }
+    }
+  } : {}),
+
+  _metadata: {
+    timestamp: getUtc8ISOString(),
+    source: "direct-planning",
+    planning_mode: "direct",
+    complexity: severity === "Medium" ? "Medium" : "Low"
+  }
+}
+
+// Step 3: Merge task rationale into tasks array
+if (severity === "Medium") {
+  fixPlan.tasks = fixPlan.tasks.map(task => ({
+    ...task,
+    rationale: fixPlan.tasks_with_rationale[task.id]?.rationale || {
+      chosen_approach: "Standard fix",
+      alternatives_considered: [],
+      decision_factors: ["Correctness", "Simplicity"],
+      tradeoffs: "None"
+    },
+    verification: fixPlan.tasks_with_rationale[task.id]?.verification || {
+      unit_tests: [`test_${task.id}_basic`],
+      integration_tests: [],
+      manual_checks: ["Verify fix works"],
+      success_metrics: ["Test pass"]
+    }
+  }))
+  delete fixPlan.tasks_with_rationale  // Clean up temp field
+}
+
+// Step 4: Write fix-plan to session folder
+Write(`${sessionFolder}/fix-plan.json`, JSON.stringify(fixPlan, null, 2))
+
+// Step 5: MUST continue to Phase 4 (Confirmation) - DO NOT execute code here
+```
+
+**High/Critical Severity** - Invoke cli-lite-planning-agent:
+
+```javascript
+Task(
+  subagent_type="cli-lite-planning-agent",
+  run_in_background=false,
+  description="Generate detailed fix plan",
+  prompt=`
+Generate fix plan and write fix-plan.json.
+
+## Output Location
+
+**Session Folder**: ${sessionFolder}
+**Output Files**:
+- ${sessionFolder}/planning-context.md (evidence + understanding)
+- ${sessionFolder}/fix-plan.json (fix plan)
+
+## Output Schema Reference
+Execute: cat ~/.claude/workflows/cli-templates/schemas/fix-plan-json-schema.json (get schema reference before generating plan)
+
+## Project Context (MANDATORY - Read Both Files)
+1. Read: .workflow/project-tech.json (technology stack, architecture, key components)
+2. Read: .workflow/project-guidelines.json (user-defined constraints and conventions)
+
+**CRITICAL**: All fix tasks MUST comply with constraints in project-guidelines.json
+
+## Bug Description
+${bug_description}
+
+## Multi-Angle Diagnosis Context
+
+${manifest.diagnoses.map(diag => `### Diagnosis: ${diag.angle} (${diag.file})
+Path: ${diag.path}
+
+Read this file for detailed ${diag.angle} analysis.`).join('\n\n')}
+
+Total diagnoses: ${manifest.diagnosis_count}
+Angles covered: ${manifest.diagnoses.map(d => d.angle).join(', ')}
+
+Manifest: ${sessionFolder}/diagnoses-manifest.json
+
+## User Clarifications
+${JSON.stringify(clarificationContext) || "None"}
+
+## Severity Level
+${severity}
+
+## Requirements
+Generate fix-plan.json with:
+- summary: 2-3 sentence overview of the fix
+- root_cause: Consolidated root cause from all diagnoses
+- strategy: "immediate_patch" | "comprehensive_fix" | "refactor"
+- tasks: 1-5 structured fix tasks (**IMPORTANT: group by fix area, NOT by file**)
+  - **Task Granularity Principle**: Each task = one complete fix unit
+  - title: action verb + target (e.g., "Fix token validation edge case")
+  - scope: module path (src/auth/) or feature name
+  - action: "Fix" | "Update" | "Refactor" | "Add" | "Delete"
+  - description
+  - modification_points: ALL files to modify for this fix (group related changes)
+  - implementation (2-5 steps covering all modification_points)
+  - acceptance: Quantified acceptance criteria
+  - depends_on: task IDs this task depends on (use sparingly)
+
+  **High/Critical complexity fields per task** (REQUIRED):
+  - rationale:
+    - chosen_approach: Why this fix approach (not alternatives)
+    - alternatives_considered: Other approaches evaluated
+    - decision_factors: Key factors influencing choice
+    - tradeoffs: Known tradeoffs of this approach
+  - verification:
+    - unit_tests: Test names to add/verify
+    - integration_tests: Integration test names
+    - manual_checks: Manual verification steps
+    - success_metrics: Quantified success criteria
+  - risks:
+    - description: Risk description
+    - probability: Low|Medium|High
+    - impact: Low|Medium|High
+    - mitigation: How to mitigate
+    - fallback: Fallback if fix fails
+  - code_skeleton (optional): Key interfaces/functions to implement
+    - interfaces: [{name, definition, purpose}]
+    - key_functions: [{signature, purpose, returns}]
+
+**Top-level High/Critical fields** (REQUIRED):
+- data_flow: How data flows through affected code
+  - diagram: "A → B → C" style flow
+  - stages: [{stage, input, output, component}]
+- design_decisions: Global fix decisions
+  - [{decision, rationale, tradeoff}]
+
+- estimated_time, recommended_execution, severity, risk_level
+- _metadata:
+  - timestamp, source, planning_mode
+  - complexity: "High" | "Critical"
+  - diagnosis_angles: ${JSON.stringify(manifest.diagnoses.map(d => d.angle))}
+
+## Task Grouping Rules
+1. **Group by fix area**: All changes for one fix = one task (even if 2-3 files)
+2. **Avoid file-per-task**: Do NOT create separate tasks for each file
+3. **Substantial tasks**: Each task should represent 10-45 minutes of work
+4. **True dependencies only**: Only use depends_on when Task B cannot start without Task A's output
+5. **Prefer parallel**: Most tasks should be independent (no depends_on)
+
+## Execution
+1. Read ALL diagnosis files for comprehensive context
+2. Execute CLI planning using Gemini (Qwen fallback) with --rule planning-fix-strategy template
+3. Synthesize findings from multiple diagnosis angles
+4. Generate fix-plan with:
+   - For High/Critical: REQUIRED new fields (rationale, verification, risks, code_skeleton, data_flow, design_decisions)
+   - Each task MUST have rationale (why this fix), verification (how to verify success), and risks (potential issues)
+5. Parse output and structure fix-plan
+6. **Write**: \`${sessionFolder}/planning-context.md\` (evidence paths + understanding)
+7. **Write**: \`${sessionFolder}/fix-plan.json\`
+8. Return brief completion summary
+
+## Output Format for CLI
+Include these sections in your fix-plan output:
+- Summary, Root Cause, Strategy (existing)
+- Data Flow: Diagram showing affected code paths
+- Design Decisions: Key architectural choices in the fix
+- Tasks: Each with rationale (Medium/High), verification (Medium/High), risks (High), code_skeleton (High)
+`
+)
+```
+
+**Output**: `${sessionFolder}/fix-plan.json`
+
+---
+
+### Phase 4: Task Confirmation & Execution Selection
+
+**Step 4.1: Display Fix Plan**
+```javascript
+const fixPlan = JSON.parse(Read(`${sessionFolder}/fix-plan.json`))
+
+console.log(`
+## Fix Plan
+
+**Summary**: ${fixPlan.summary}
+**Root Cause**: ${fixPlan.root_cause}
+**Strategy**: ${fixPlan.strategy}
+
+**Tasks** (${fixPlan.tasks.length}):
+${fixPlan.tasks.map((t, i) => `${i+1}. ${t.title} (${t.scope})`).join('\n')}
+
+**Severity**: ${fixPlan.severity}
+**Risk Level**: ${fixPlan.risk_level}
+**Estimated Time**: ${fixPlan.estimated_time}
+**Recommended**: ${fixPlan.recommended_execution}
+`)
+```
+
+**Step 4.2: Collect Confirmation**
+```javascript
+// Parse --yes flag
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+let userSelection
+
+if (autoYes) {
+  // Auto mode: Use defaults
+  console.log(`[--yes] Auto-confirming fix plan:`)
+  console.log(`  - Confirmation: Allow`)
+  console.log(`  - Execution: Auto`)
+  console.log(`  - Review: Skip`)
+
+  userSelection = {
+    confirmation: "Allow",
+    execution_method: "Auto",
+    code_review_tool: "Skip"
+  }
+} else {
+  // Interactive mode: Ask user
+  userSelection = AskUserQuestion({
+    questions: [
+      {
+        question: `Confirm fix plan? (${fixPlan.tasks.length} tasks, ${fixPlan.severity} severity)`,
+        header: "Confirm",
+        multiSelect: false,
+        options: [
+          { label: "Allow", description: "Proceed as-is" },
+          { label: "Modify", description: "Adjust before execution" },
+          { label: "Cancel", description: "Abort workflow" }
+        ]
+      },
+      {
+        question: "Execution method:",
+        header: "Execution",
+        multiSelect: false,
+        options: [
+          { label: "Agent", description: "@code-developer agent" },
+          { label: "Codex", description: "codex CLI tool" },
+          { label: "Auto", description: `Auto: ${fixPlan.severity === 'Low' ? 'Agent' : 'Codex'}` }
+        ]
+      },
+      {
+        question: "Code review after fix?",
+        header: "Review",
+        multiSelect: false,
+        options: [
+          { label: "Gemini Review", description: "Gemini CLI" },
+          { label: "Agent Review", description: "@code-reviewer" },
+          { label: "Skip", description: "No review" }
+        ]
+      }
+    ]
+  })
+}
+```
+
+---
+
+### Phase 5: Execute to Execution
+
+**CRITICAL**: lite-fix NEVER executes code directly. ALL execution MUST go through lite-execute.
+
+**Step 5.1: Build executionContext**
+
+```javascript
+// Load manifest and all diagnosis files
+const manifest = JSON.parse(Read(`${sessionFolder}/diagnoses-manifest.json`))
+const diagnoses = {}
+
+manifest.diagnoses.forEach(diag => {
+  if (file_exists(diag.path)) {
+    diagnoses[diag.angle] = JSON.parse(Read(diag.path))
+  }
+})
+
+const fixPlan = JSON.parse(Read(`${sessionFolder}/fix-plan.json`))
+
+executionContext = {
+  mode: "bugfix",
+  severity: fixPlan.severity,
+  planObject: {
+    ...fixPlan,
+    // Ensure complexity is set based on severity for new field consumption
+    complexity: fixPlan.complexity || (fixPlan.severity === 'Critical' ? 'High' : (fixPlan.severity === 'High' ? 'High' : 'Medium'))
+  },
+  diagnosisContext: diagnoses,
+  diagnosisAngles: manifest.diagnoses.map(d => d.angle),
+  diagnosisManifest: manifest,
+  clarificationContext: clarificationContext || null,
+  executionMethod: userSelection.execution_method,
+  codeReviewTool: userSelection.code_review_tool,
+  originalUserInput: bug_description,
+  session: {
+    id: sessionId,
+    folder: sessionFolder,
+    artifacts: {
+      diagnoses: manifest.diagnoses.map(diag => ({
+        angle: diag.angle,
+        path: diag.path
+      })),
+      diagnoses_manifest: `${sessionFolder}/diagnoses-manifest.json`,
+      fix_plan: `${sessionFolder}/fix-plan.json`
+    }
+  }
+}
+```
+
+**Step 5.2: Execute**
+
+```javascript
+// Hand off to Phase 4: Lite Execute (phases/04-lite-execute.md) --in-memory --mode bugfix
+// executionContext is passed in-memory to the execution phase
+```
+
+## Session Folder Structure
+
+```
+.workflow/.lite-fix/{bug-slug}-{YYYY-MM-DD}/
+├── diagnosis-{angle1}.json      # Diagnosis angle 1
+├── diagnosis-{angle2}.json      # Diagnosis angle 2
+├── diagnosis-{angle3}.json      # Diagnosis angle 3 (if applicable)
+├── diagnosis-{angle4}.json      # Diagnosis angle 4 (if applicable)
+├── diagnoses-manifest.json      # Diagnosis index
+├── planning-context.md          # Evidence + understanding
+└── fix-plan.json                # Fix plan
+```
+
+**Example**:
+```
+.workflow/.lite-fix/user-avatar-upload-fails-413-2025-11-25/
+├── diagnosis-error-handling.json
+├── diagnosis-dataflow.json
+├── diagnosis-validation.json
+├── diagnoses-manifest.json
+├── planning-context.md
+└── fix-plan.json
+```
+
+## Error Handling
+
+| Error | Resolution |
+|-------|------------|
+| Diagnosis agent failure | Skip diagnosis, continue with bug description only |
+| Planning agent failure | Fallback to direct planning by Claude |
+| Clarification timeout | Use diagnosis findings as-is |
+| Confirmation timeout | Save context, display resume instructions |
+| Modify loop > 3 times | Suggest breaking task or using full planning workflow (workflow-plan/SKILL.md) |
+| Root cause unclear | Extend diagnosis time or use broader angles |
+| Too complex for lite-fix | Escalate to full planning workflow (workflow-plan/SKILL.md) |
+
+---
+
+## Post-Phase Update
+
+After Phase 3 (Lite Fix) completes:
+- **Output Created**: `executionContext` with fix-plan.json, diagnoses, clarifications, user selections
+- **Session Artifacts**: All files in `.workflow/.lite-fix/{session-id}/`
+- **Next Action**: Auto-continue to [Phase 4: Lite Execute](04-lite-execute.md) with --in-memory --mode bugfix
+- **TodoWrite**: Mark "Lite Fix - Planning" as completed, start "Execution (Phase 4)"
--- a/.claude/skills/workflow-lite-plan/phases/04-lite-execute.md
+++ b/.claude/skills/workflow-lite-plan/phases/04-lite-execute.md
@@ -0,0 +1,738 @@
+# Phase 4: Lite Execute
+
+## Overview
+
+Flexible task execution phase supporting three input modes: in-memory plan (from planning phases), direct prompt description, or file content. Handles execution orchestration, progress tracking, and optional code review.
+
+**Core capabilities:**
+- Multi-mode input (in-memory plan, prompt description, or file path)
+- Execution orchestration (Agent or Codex) with full context
+- Live progress tracking via TodoWrite at execution call level
+- Optional code review with selected tool (Gemini, Agent, or custom)
+- Context continuity across multiple executions
+- Intelligent format detection (Enhanced Task JSON vs plain text)
+
+## Parameters
+
+- `--in-memory`: Use plan from memory (called by planning phases)
+- `<input>`: Task description string, or path to file (required)
+
+## Input Modes
+
+### Mode 1: In-Memory Plan
+
+**Trigger**: Called by planning phase after confirmation with `--in-memory` flag
+
+**Input Source**: `executionContext` global variable set by planning phase
+
+**Content**: Complete execution context (see Data Structures section)
+
+**Behavior**:
+- Skip execution method selection (already set by planning phase)
+- Directly proceed to execution with full context
+- All planning artifacts available (exploration, clarifications, plan)
+
+### Mode 2: Prompt Description
+
+**Trigger**: User calls with task description string
+
+**Input**: Simple task description (e.g., "Add unit tests for auth module")
+
+**Behavior**:
+- Store prompt as `originalUserInput`
+- Create simple execution plan from prompt
+- AskUserQuestion: Select execution method (Agent/Codex/Auto)
+- AskUserQuestion: Select code review tool (Skip/Gemini/Agent/Other)
+- Proceed to execution with `originalUserInput` included
+
+**User Interaction**:
+```javascript
+// Parse --yes flag
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+let userSelection
+
+if (autoYes) {
+  // Auto mode: Use defaults
+  console.log(`[--yes] Auto-confirming execution:`)
+  console.log(`  - Execution method: Auto`)
+  console.log(`  - Code review: Skip`)
+
+  userSelection = {
+    execution_method: "Auto",
+    code_review_tool: "Skip"
+  }
+} else {
+  // Interactive mode: Ask user
+  userSelection = AskUserQuestion({
+    questions: [
+      {
+        question: "Select execution method:",
+        header: "Execution",
+        multiSelect: false,
+        options: [
+          { label: "Agent", description: "@code-developer agent" },
+          { label: "Codex", description: "codex CLI tool" },
+          { label: "Auto", description: "Auto-select based on complexity" }
+        ]
+      },
+      {
+        question: "Enable code review after execution?",
+        header: "Code Review",
+        multiSelect: false,
+        options: [
+          { label: "Skip", description: "No review" },
+          { label: "Gemini Review", description: "Gemini CLI tool" },
+          { label: "Codex Review", description: "Git-aware review (prompt OR --uncommitted)" },
+          { label: "Agent Review", description: "Current agent review" }
+        ]
+      }
+    ]
+  })
+}
+```
+
+### Mode 3: File Content
+
+**Trigger**: User calls with file path
+
+**Input**: Path to file containing task description or plan.json
+
+**Step 1: Read and Detect Format**
+
+```javascript
+fileContent = Read(filePath)
+
+// Attempt JSON parsing
+try {
+  jsonData = JSON.parse(fileContent)
+
+  // Check if plan.json from lite-plan session
+  if (jsonData.summary && jsonData.approach && jsonData.tasks) {
+    planObject = jsonData
+    originalUserInput = jsonData.summary
+    isPlanJson = true
+  } else {
+    // Valid JSON but not plan.json - treat as plain text
+    originalUserInput = fileContent
+    isPlanJson = false
+  }
+} catch {
+  // Not valid JSON - treat as plain text prompt
+  originalUserInput = fileContent
+  isPlanJson = false
+}
+```
+
+**Step 2: Create Execution Plan**
+
+If `isPlanJson === true`:
+- Use `planObject` directly
+- User selects execution method and code review
+
+If `isPlanJson === false`:
+- Treat file content as prompt (same behavior as Mode 2)
+- Create simple execution plan from content
+
+**Step 3: User Interaction**
+
+- AskUserQuestion: Select execution method (Agent/Codex/Auto)
+- AskUserQuestion: Select code review tool
+- Proceed to execution with full context
+
+## Execution Process
+
+```
+Input Parsing:
+   └─ Decision (mode detection):
+      ├─ --in-memory flag → Mode 1: Load executionContext → Skip user selection
+      ├─ Ends with .md/.json/.txt → Mode 3: Read file → Detect format
+      │   ├─ Valid plan.json → Use planObject → User selects method + review
+      │   └─ Not plan.json → Treat as prompt → User selects method + review
+      └─ Other → Mode 2: Prompt description → User selects method + review
+
+Execution:
+   ├─ Step 1: Initialize result tracking (previousExecutionResults = [])
+   ├─ Step 2: Task grouping & batch creation
+   │   ├─ Extract explicit depends_on (no file/keyword inference)
+   │   ├─ Group: independent tasks → single parallel batch (maximize utilization)
+   │   ├─ Group: dependent tasks → sequential phases (respect dependencies)
+   │   └─ Create TodoWrite list for batches
+   ├─ Step 3: Launch execution
+   │   ├─ Phase 1: All independent tasks (single batch, concurrent)
+   │   └─ Phase 2+: Dependent tasks by dependency order
+   ├─ Step 4: Track progress (TodoWrite updates per batch)
+   └─ Step 5: Code review (if codeReviewTool ≠ "Skip")
+
+Output:
+   └─ Execution complete with results in previousExecutionResults[]
+```
+
+## Detailed Execution Steps
+
+### Step 1: Initialize Execution Tracking
+
+**Operations**:
+- Initialize result tracking for multi-execution scenarios
+- Set up `previousExecutionResults` array for context continuity
+- **In-Memory Mode**: Echo execution strategy from planning phase for transparency
+
+```javascript
+// Initialize result tracking
+previousExecutionResults = []
+
+// In-Memory Mode: Echo execution strategy (transparency before execution)
+if (executionContext) {
+  console.log(`
+Execution Strategy (from planning phase):
+   Method: ${executionContext.executionMethod}
+   Review: ${executionContext.codeReviewTool}
+   Tasks: ${executionContext.planObject.tasks.length}
+   Complexity: ${executionContext.planObject.complexity}
+${executionContext.executorAssignments ? `   Assignments: ${JSON.stringify(executionContext.executorAssignments)}` : ''}
+  `)
+}
+```
+
+### Step 2: Task Grouping & Batch Creation
+
+**Dependency Analysis & Grouping Algorithm**:
+```javascript
+// Use explicit depends_on from plan.json (no inference from file/keywords)
+function extractDependencies(tasks) {
+  const taskIdToIndex = {}
+  tasks.forEach((t, i) => { taskIdToIndex[t.id] = i })
+
+  return tasks.map((task, i) => {
+    // Only use explicit depends_on from plan.json
+    const deps = (task.depends_on || [])
+      .map(depId => taskIdToIndex[depId])
+      .filter(idx => idx !== undefined && idx < i)
+    return { ...task, taskIndex: i, dependencies: deps }
+  })
+}
+
+// Group into batches: maximize parallel execution
+function createExecutionCalls(tasks, executionMethod) {
+  const tasksWithDeps = extractDependencies(tasks)
+  const processed = new Set()
+  const calls = []
+
+  // Phase 1: All independent tasks → single parallel batch (maximize utilization)
+  const independentTasks = tasksWithDeps.filter(t => t.dependencies.length === 0)
+  if (independentTasks.length > 0) {
+    independentTasks.forEach(t => processed.add(t.taskIndex))
+    calls.push({
+      method: executionMethod,
+      executionType: "parallel",
+      groupId: "P1",
+      taskSummary: independentTasks.map(t => t.title).join(' | '),
+      tasks: independentTasks
+    })
+  }
+
+  // Phase 2: Dependent tasks → sequential batches (respect dependencies)
+  let sequentialIndex = 1
+  let remaining = tasksWithDeps.filter(t => !processed.has(t.taskIndex))
+
+  while (remaining.length > 0) {
+    // Find tasks whose dependencies are all satisfied
+    const ready = remaining.filter(t =>
+      t.dependencies.every(d => processed.has(d))
+    )
+
+    if (ready.length === 0) {
+      console.warn('Circular dependency detected, forcing remaining tasks')
+      ready.push(...remaining)
+    }
+
+    // Group ready tasks (can run in parallel within this phase)
+    ready.forEach(t => processed.add(t.taskIndex))
+    calls.push({
+      method: executionMethod,
+      executionType: ready.length > 1 ? "parallel" : "sequential",
+      groupId: ready.length > 1 ? `P${calls.length + 1}` : `S${sequentialIndex++}`,
+      taskSummary: ready.map(t => t.title).join(ready.length > 1 ? ' | ' : ' → '),
+      tasks: ready
+    })
+
+    remaining = remaining.filter(t => !processed.has(t.taskIndex))
+  }
+
+  return calls
+}
+
+executionCalls = createExecutionCalls(planObject.tasks, executionMethod).map(c => ({ ...c, id: `[${c.groupId}]` }))
+
+TodoWrite({
+  todos: executionCalls.map(c => ({
+    content: `${c.executionType === "parallel" ? "⚡" : "→"} ${c.id} (${c.tasks.length} tasks)`,
+    status: "pending",
+    activeForm: `Executing ${c.id}`
+  }))
+})
+```
+
+### Step 3: Launch Execution
+
+**Executor Resolution** (任务级 executor 优先于全局设置):
+```javascript
+// 获取任务的 executor（优先使用 executorAssignments，fallback 到全局 executionMethod）
+function getTaskExecutor(task) {
+  const assignments = executionContext?.executorAssignments || {}
+  if (assignments[task.id]) {
+    return assignments[task.id].executor  // 'gemini' | 'codex' | 'agent'
+  }
+  // Fallback: 全局 executionMethod 映射
+  const method = executionContext?.executionMethod || 'Auto'
+  if (method === 'Agent') return 'agent'
+  if (method === 'Codex') return 'codex'
+  // Auto: 根据复杂度
+  return planObject.complexity === 'Low' ? 'agent' : 'codex'
+}
+
+// 按 executor 分组任务
+function groupTasksByExecutor(tasks) {
+  const groups = { gemini: [], codex: [], agent: [] }
+  tasks.forEach(task => {
+    const executor = getTaskExecutor(task)
+    groups[executor].push(task)
+  })
+  return groups
+}
+```
+
+**Execution Flow**: Parallel batches concurrently → Sequential batches in order
+```javascript
+const parallel = executionCalls.filter(c => c.executionType === "parallel")
+const sequential = executionCalls.filter(c => c.executionType === "sequential")
+
+// Phase 1: Launch all parallel batches (single message with multiple tool calls)
+if (parallel.length > 0) {
+  TodoWrite({ todos: executionCalls.map(c => ({ status: c.executionType === "parallel" ? "in_progress" : "pending" })) })
+  parallelResults = await Promise.all(parallel.map(c => executeBatch(c)))
+  previousExecutionResults.push(...parallelResults)
+  TodoWrite({ todos: executionCalls.map(c => ({ status: parallel.includes(c) ? "completed" : "pending" })) })
+}
+
+// Phase 2: Execute sequential batches one by one
+for (const call of sequential) {
+  TodoWrite({ todos: executionCalls.map(c => ({ status: c === call ? "in_progress" : "..." })) })
+  result = await executeBatch(call)
+  previousExecutionResults.push(result)
+  TodoWrite({ todos: executionCalls.map(c => ({ status: "completed" or "pending" })) })
+}
+```
+
+### Unified Task Prompt Builder
+
+**Task Formatting Principle**: Each task is a self-contained checklist. The executor only needs to know what THIS task requires. Same template for Agent and CLI.
+
+```javascript
+function buildExecutionPrompt(batch) {
+  // Task template (6 parts: Modification Points → Why → How → Reference → Risks → Done)
+  const formatTask = (t) => `
+## ${t.title}
+
+**Scope**: \`${t.scope}\`  |  **Action**: ${t.action}
+
+### Modification Points
+${t.modification_points.map(p => `- **${p.file}** → \`${p.target}\`: ${p.change}`).join('\n')}
+
+${t.rationale ? `
+### Why this approach (Medium/High)
+${t.rationale.chosen_approach}
+${t.rationale.decision_factors?.length > 0 ? `\nKey factors: ${t.rationale.decision_factors.join(', ')}` : ''}
+${t.rationale.tradeoffs ? `\nTradeoffs: ${t.rationale.tradeoffs}` : ''}
+` : ''}
+
+### How to do it
+${t.description}
+
+${t.implementation.map(step => `- ${step}`).join('\n')}
+
+${t.code_skeleton ? `
+### Code skeleton (High)
+${t.code_skeleton.interfaces?.length > 0 ? `**Interfaces**: ${t.code_skeleton.interfaces.map(i => `\`${i.name}\` - ${i.purpose}`).join(', ')}` : ''}
+${t.code_skeleton.key_functions?.length > 0 ? `\n**Functions**: ${t.code_skeleton.key_functions.map(f => `\`${f.signature}\` - ${f.purpose}`).join(', ')}` : ''}
+${t.code_skeleton.classes?.length > 0 ? `\n**Classes**: ${t.code_skeleton.classes.map(c => `\`${c.name}\` - ${c.purpose}`).join(', ')}` : ''}
+` : ''}
+
+### Reference
+- Pattern: ${t.reference?.pattern || 'N/A'}
+- Files: ${t.reference?.files?.join(', ') || 'N/A'}
+${t.reference?.examples ? `- Notes: ${t.reference.examples}` : ''}
+
+${t.risks?.length > 0 ? `
+### Risk mitigations (High)
+${t.risks.map(r => `- ${r.description} → **${r.mitigation}**`).join('\n')}
+` : ''}
+
+### Done when
+${t.acceptance.map(c => `- [ ] ${c}`).join('\n')}
+${t.verification?.success_metrics?.length > 0 ? `\n**Success metrics**: ${t.verification.success_metrics.join(', ')}` : ''}`
+
+  // Build prompt
+  const sections = []
+
+  if (originalUserInput) sections.push(`## Goal\n${originalUserInput}`)
+
+  sections.push(`## Tasks\n${batch.tasks.map(formatTask).join('\n\n---\n')}`)
+
+  // Context (reference only)
+  const context = []
+  if (previousExecutionResults.length > 0) {
+    context.push(`### Previous Work\n${previousExecutionResults.map(r => `- ${r.tasksSummary}: ${r.status}`).join('\n')}`)
+  }
+  if (clarificationContext) {
+    context.push(`### Clarifications\n${Object.entries(clarificationContext).map(([q, a]) => `- ${q}: ${a}`).join('\n')}`)
+  }
+  if (executionContext?.planObject?.data_flow?.diagram) {
+    context.push(`### Data Flow\n${executionContext.planObject.data_flow.diagram}`)
+  }
+  if (executionContext?.session?.artifacts?.plan) {
+    context.push(`### Artifacts\nPlan: ${executionContext.session.artifacts.plan}`)
+  }
+  // Project guidelines (user-defined constraints)
+  context.push(`### Project Guidelines\n@.workflow/project-guidelines.json`)
+  if (context.length > 0) sections.push(`## Context\n${context.join('\n\n')}`)
+
+  sections.push(`Complete each task according to its "Done when" checklist.`)
+
+  return sections.join('\n\n')
+}
+```
+
+**Option A: Agent Execution**
+
+When to use:
+- `getTaskExecutor(task) === "agent"`
+- or `executionMethod = "Agent"` (global fallback)
+- or `executionMethod = "Auto" AND complexity = "Low"` (global fallback)
+
+```javascript
+Task(
+  subagent_type="code-developer",
+  run_in_background=false,
+  description=batch.taskSummary,
+  prompt=buildExecutionPrompt(batch)
+)
+```
+
+**Result Collection**: After completion, collect result following `executionResult` structure (see Data Structures section)
+
+**Option B: CLI Execution (Codex)**
+
+When to use:
+- `getTaskExecutor(task) === "codex"`
+- or `executionMethod = "Codex"` (global fallback)
+- or `executionMethod = "Auto" AND complexity = "Medium/High"` (global fallback)
+
+```bash
+ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write
+```
+
+**Execution with fixed IDs** (predictable ID pattern):
+```javascript
+// Launch CLI in background, wait for task hook callback
+// Generate fixed execution ID: ${sessionId}-${groupId}
+const sessionId = executionContext?.session?.id || 'standalone'
+const fixedExecutionId = `${sessionId}-${batch.groupId}`  // e.g., "implement-auth-2025-12-13-P1"
+
+// Check if resuming from previous failed execution
+const previousCliId = batch.resumeFromCliId || null
+
+// Build command with fixed ID (and optional resume for continuation)
+const cli_command = previousCliId
+  ? `ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
+  : `ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
+
+// Execute in background, stop output and wait for task hook callback
+Bash(
+  command=cli_command,
+  run_in_background=true
+)
+// STOP HERE - CLI executes in background, task hook will notify on completion
+```
+
+**Resume on Failure** (with fixed ID):
+```javascript
+// If execution failed or timed out, offer resume option
+if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
+  console.log(`
+Execution incomplete. Resume available:
+   Fixed ID: ${fixedExecutionId}
+   Lookup: ccw cli detail ${fixedExecutionId}
+   Resume: ccw cli -p "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
+`)
+
+  // Store for potential retry in same session
+  batch.resumeFromCliId = fixedExecutionId
+}
+```
+
+**Result Collection**: After completion, analyze output and collect result following `executionResult` structure (include `cliExecutionId` for resume capability)
+
+**Option C: CLI Execution (Gemini)**
+
+When to use: `getTaskExecutor(task) === "gemini"` (analysis tasks)
+
+```bash
+# Use unified buildExecutionPrompt, switch tool and mode
+ccw cli -p "${buildExecutionPrompt(batch)}" --tool gemini --mode analysis --id ${sessionId}-${batch.groupId}
+```
+
+### Step 4: Progress Tracking
+
+Progress tracked at batch level (not individual task level). Icons: ⚡ (parallel, concurrent), → (sequential, one-by-one)
+
+### Step 5: Code Review (Optional)
+
+**Skip Condition**: Only run if `codeReviewTool ≠ "Skip"`
+
+**Review Focus**: Verify implementation against plan acceptance criteria and verification requirements
+- Read plan.json for task acceptance criteria and verification checklist
+- Check each acceptance criterion is fulfilled
+- Verify success metrics from verification field (Medium/High complexity)
+- Run unit/integration tests specified in verification field
+- Validate code quality and identify issues
+- Ensure alignment with planned approach and risk mitigations
+
+**Operations**:
+- Agent Review: Current agent performs direct review
+- Gemini Review: Execute gemini CLI with review prompt
+- Codex Review: Two options - (A) with prompt for complex reviews, (B) `--uncommitted` flag only for quick reviews
+- Custom tool: Execute specified CLI tool (qwen, etc.)
+
+**Unified Review Template** (All tools use same standard):
+
+**Review Criteria**:
+- **Acceptance Criteria**: Verify each criterion from plan.tasks[].acceptance
+- **Verification Checklist** (Medium/High): Check unit_tests, integration_tests, success_metrics from plan.tasks[].verification
+- **Code Quality**: Analyze quality, identify issues, suggest improvements
+- **Plan Alignment**: Validate implementation matches planned approach and risk mitigations
+
+**Shared Prompt Template** (used by all CLI tools):
+```
+PURPOSE: Code review for implemented changes against plan acceptance criteria and verification requirements
+TASK: • Verify plan acceptance criteria fulfillment • Check verification requirements (unit tests, success metrics) • Analyze code quality • Identify issues • Suggest improvements • Validate plan adherence and risk mitigations
+MODE: analysis
+CONTEXT: @**/* @{plan.json} [@{exploration.json}] | Memory: Review lite-execute changes against plan requirements including verification checklist
+EXPECTED: Quality assessment with:
+  - Acceptance criteria verification (all tasks)
+  - Verification checklist validation (Medium/High: unit_tests, integration_tests, success_metrics)
+  - Issue identification
+  - Recommendations
+  Explicitly check each acceptance criterion and verification item from plan.json tasks.
+CONSTRAINTS: Focus on plan acceptance criteria, verification requirements, and plan adherence | analysis=READ-ONLY
+```
+
+**Tool-Specific Execution** (Apply shared prompt template above):
+
+```bash
+# Method 1: Agent Review (current agent)
+# - Read plan.json: ${executionContext.session.artifacts.plan}
+# - Apply unified review criteria (see Shared Prompt Template)
+# - Report findings directly
+
+# Method 2: Gemini Review (recommended)
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
+# CONTEXT includes: @**/* @${plan.json} [@${exploration.json}]
+
+# Method 3: Qwen Review (alternative)
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
+# Same prompt as Gemini, different execution engine
+
+# Method 4: Codex Review (git-aware) - Two mutually exclusive options:
+
+# Option A: With custom prompt (reviews uncommitted by default)
+ccw cli -p "[Shared Prompt Template with artifacts]" --tool codex --mode review
+# Use for complex reviews with specific focus areas
+
+# Option B: Target flag only (no prompt allowed)
+ccw cli --tool codex --mode review --uncommitted
+# Quick review of uncommitted changes without custom instructions
+
+# IMPORTANT: -p prompt and target flags (--uncommitted/--base/--commit) are MUTUALLY EXCLUSIVE
+```
+
+**Multi-Round Review with Fixed IDs**:
+```javascript
+// Generate fixed review ID
+const reviewId = `${sessionId}-review`
+
+// First review pass with fixed ID
+const reviewResult = Bash(`ccw cli -p "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
+
+// If issues found, continue review dialog with fixed ID chain
+if (hasUnresolvedIssues(reviewResult)) {
+  // Resume with follow-up questions
+  Bash(`ccw cli -p "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
+}
+```
+
+**Implementation Note**: Replace `[Shared Prompt Template with artifacts]` placeholder with actual template content, substituting:
+- `@{plan.json}` → `@${executionContext.session.artifacts.plan}`
+- `[@{exploration.json}]` → exploration files from artifacts (if exists)
+
+### Step 6: Update Development Index
+
+**Trigger**: After all executions complete (regardless of code review)
+
+**Skip Condition**: Skip if `.workflow/project-tech.json` does not exist
+
+**Operations**:
+```javascript
+const projectJsonPath = '.workflow/project-tech.json'
+if (!fileExists(projectJsonPath)) return  // Silent skip
+
+const projectJson = JSON.parse(Read(projectJsonPath))
+
+// Initialize if needed
+if (!projectJson.development_index) {
+  projectJson.development_index = { feature: [], enhancement: [], bugfix: [], refactor: [], docs: [] }
+}
+
+// Detect category from keywords
+function detectCategory(text) {
+  text = text.toLowerCase()
+  if (/\b(fix|bug|error|issue|crash)\b/.test(text)) return 'bugfix'
+  if (/\b(refactor|cleanup|reorganize)\b/.test(text)) return 'refactor'
+  if (/\b(doc|readme|comment)\b/.test(text)) return 'docs'
+  if (/\b(add|new|create|implement)\b/.test(text)) return 'feature'
+  return 'enhancement'
+}
+
+// Detect sub_feature from task file paths
+function detectSubFeature(tasks) {
+  const dirs = tasks.map(t => t.file?.split('/').slice(-2, -1)[0]).filter(Boolean)
+  const counts = dirs.reduce((a, d) => { a[d] = (a[d] || 0) + 1; return a }, {})
+  return Object.entries(counts).sort((a, b) => b[1] - a[1])[0]?.[0] || 'general'
+}
+
+const category = detectCategory(`${planObject.summary} ${planObject.approach}`)
+const entry = {
+  title: planObject.summary.slice(0, 60),
+  sub_feature: detectSubFeature(planObject.tasks),
+  date: new Date().toISOString().split('T')[0],
+  description: planObject.approach.slice(0, 100),
+  status: previousExecutionResults.every(r => r.status === 'completed') ? 'completed' : 'partial',
+  session_id: executionContext?.session?.id || null
+}
+
+projectJson.development_index[category].push(entry)
+projectJson.statistics.last_updated = new Date().toISOString()
+Write(projectJsonPath, JSON.stringify(projectJson, null, 2))
+
+console.log(`Development index: [${category}] ${entry.title}`)
+```
+
+## Best Practices
+
+**Input Modes**: In-memory (planning phase), prompt (standalone), file (JSON/text)
+**Task Grouping**: Based on explicit depends_on only; independent tasks run in single parallel batch
+**Execution**: All independent tasks launch concurrently via single Claude message with multiple tool calls
+
+## Error Handling
+
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Missing executionContext | --in-memory without context | Error: "No execution context found. Only available when called by planning phase." |
+| File not found | File path doesn't exist | Error: "File not found: {path}. Check file path." |
+| Empty file | File exists but no content | Error: "File is empty: {path}. Provide task description." |
+| Invalid Enhanced Task JSON | JSON missing required fields | Warning: "Missing required fields. Treating as plain text." |
+| Malformed JSON | JSON parsing fails | Treat as plain text (expected for non-JSON files) |
+| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli -p "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
+| Execution timeout | CLI exceeded timeout | Use fixed ID for resume with extended timeout |
+| Codex unavailable | Codex not installed | Show installation instructions, offer Agent execution |
+| Fixed ID not found | Custom ID lookup failed | Check `ccw cli history`, verify date directories |
+
+## Data Structures
+
+### executionContext (Input - Mode 1)
+
+Passed from planning phase via global variable:
+
+```javascript
+{
+  planObject: {
+    summary: string,
+    approach: string,
+    tasks: [...],
+    estimated_time: string,
+    recommended_execution: string,
+    complexity: string
+  },
+  explorationsContext: {...} | null,       // Multi-angle explorations
+  explorationAngles: string[],             // List of exploration angles
+  explorationManifest: {...} | null,       // Exploration manifest
+  clarificationContext: {...} | null,
+  executionMethod: "Agent" | "Codex" | "Auto",  // Global default
+  codeReviewTool: "Skip" | "Gemini Review" | "Agent Review" | string,
+  originalUserInput: string,
+
+  // Task-level executor assignments (priority over executionMethod)
+  executorAssignments: {
+    [taskId]: { executor: "gemini" | "codex" | "agent", reason: string }
+  },
+
+  // Session artifacts location (saved by planning phase)
+  session: {
+    id: string,                        // Session identifier: {taskSlug}-{shortTimestamp}
+    folder: string,                    // Session folder path: .workflow/.lite-plan/{session-id}
+    artifacts: {
+      explorations: [{angle, path}],   // exploration-{angle}.json paths
+      explorations_manifest: string,   // explorations-manifest.json path
+      plan: string                     // plan.json path (always present)
+    }
+  }
+}
+```
+
+**Artifact Usage**:
+- Artifact files contain detailed planning context
+- Pass artifact paths to CLI tools and agents for enhanced context
+- See execution options above for usage examples
+
+### executionResult (Output)
+
+Collected after each execution call completes:
+
+```javascript
+{
+  executionId: string,                 // e.g., "[Agent-1]", "[Codex-1]"
+  status: "completed" | "partial" | "failed",
+  tasksSummary: string,                // Brief description of tasks handled
+  completionSummary: string,           // What was completed
+  keyOutputs: string,                  // Files created/modified, key changes
+  notes: string,                       // Important context for next execution
+  fixedCliId: string | null            // Fixed CLI execution ID (e.g., "implement-auth-2025-12-13-P1")
+}
+```
+
+Appended to `previousExecutionResults` array for context continuity in multi-execution scenarios.
+
+## Post-Completion Expansion
+
+After completion, ask user whether to expand as issue (test/enhance/refactor/doc). Selected items create new issues accordingly.
+
+**Fixed ID Pattern**: `${sessionId}-${groupId}` enables predictable lookup without auto-generated timestamps.
+
+**Resume Usage**: If `status` is "partial" or "failed", use `fixedCliId` to resume:
+```bash
+# Lookup previous execution
+ccw cli detail ${fixedCliId}
+
+# Resume with new fixed ID for retry
+ccw cli -p "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
+```
+
+---
+
+## Post-Phase Update
+
+After Phase 4 (Lite Execute) completes:
+- **Output Created**: Executed tasks, optional code review results, updated development index
+- **Execution Results**: `previousExecutionResults[]` with status per batch
+- **Next Action**: Workflow complete. Optionally expand to issue (test/enhance/refactor/doc)
+- **TodoWrite**: Mark all execution batches as completed
--- a/.claude/skills/workflow-plan/SKILL.md
+++ b/.claude/skills/workflow-plan/SKILL.md
@@ -41,6 +41,25 @@ allowed-tools: Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob,

 When `--yes` or `-y`: Auto-continue all phases (skip confirmations), use recommended conflict resolutions.

+## Usage
+
+```
+Skill(skill="workflow-plan", args="<task description>")
+Skill(skill="workflow-plan", args="[-y|--yes] \"<task description>\"")
+
+# Flags
+-y, --yes    Skip all confirmations (auto mode)
+
+# Arguments
+<task description>    Task description text, structured GOAL/SCOPE/CONTEXT, or path to .md file
+
+# Examples
+Skill(skill="workflow-plan", args="\"Build authentication system\"")                    # Simple task
+Skill(skill="workflow-plan", args="\"Add JWT auth with email/password and refresh\"")   # Detailed task
+Skill(skill="workflow-plan", args="-y \"Implement user profile page\"")                 # Auto mode
+Skill(skill="workflow-plan", args="\"requirements.md\"")                                # From file
+```
+
 ## Execution Flow

 ```
--- a/.claude/skills/workflow-tdd-plan/SKILL.md
+++ b/.claude/skills/workflow-tdd-plan/SKILL.md
@@ -0,0 +1,747 @@
+---
+name: workflow-tdd-plan
+description: TDD workflow planning with Red-Green-Refactor task chain generation, test-first development structure, cycle tracking, and post-execution compliance verification. Triggers on "workflow:tdd-plan", "workflow:tdd-verify".
+allowed-tools: Task, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash, Glob, Grep, Skill
+---
+
+# Workflow TDD Plan
+
+6-phase TDD planning workflow that orchestrates session discovery, context gathering, test coverage analysis, conflict resolution, and TDD task generation to produce implementation plans with Red-Green-Refactor cycles. Includes post-execution TDD compliance verification.
+
+## Architecture Overview
+
+```
+┌──────────────────────────────────────────────────────────────────┐
+│  Workflow TDD Plan Orchestrator (SKILL.md)                       │
+│  → Pure coordinator: Execute phases, parse outputs, pass context │
+└───────────────┬──────────────────────────────────────────────────┘
+                │
+   ┌────────────┼────────────┬────────────┬────────────┐
+   ↓            ↓            ↓            ↓            ↓
+┌────────┐ ┌────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
+│ Phase 1│ │ Phase 2│ │ Phase 3  │ │ Phase 4  │ │ Phase 5  │
+│Session │ │Context │ │Test Covg │ │Conflict  │ │TDD Task  │
+│Discover│ │Gather  │ │Analysis  │ │Resolve   │ │Generate  │
+│ (ext)  │ │ (ext)  │ │ (local)  │ │(ext,cond)│ │ (local)  │
+└────────┘ └────────┘ └──────────┘ └──────────┘ └──────────┘
+    ↓           ↓           ↓            ↓            ↓
+ sessionId  contextPath  testContext  resolved    IMPL_PLAN.md
+            conflict_risk             artifacts   task JSONs
+
+Phase 6: TDD Structure Validation (inline in SKILL.md)
+
+Post-execution verification:
+┌──────────────┐     ┌───────────────────┐
+│  TDD Verify  │────→│ Coverage Analysis │
+│  (local)     │     │ (local)           │
+└──────────────┘     └───────────────────┘
+phases/03-tdd-        phases/04-tdd-
+verify.md             coverage-analysis.md
+```
+
+## Key Design Principles
+
+1. **Pure Orchestrator**: Execute phases in sequence, parse outputs, pass context between them
+2. **Auto-Continue**: All phases run autonomously without user intervention between phases
+3. **Task Attachment Model**: Sub-tasks are attached/collapsed dynamically in TodoWrite
+4. **Progressive Phase Loading**: Phase docs are read on-demand, not all at once
+5. **Conditional Execution**: Phase 4 only executes when conflict_risk >= medium
+6. **TDD-First**: Every feature starts with a failing test (Red phase)
+
+**CLI Tool Selection**: CLI tool usage is determined semantically from user's task description. Include "use Codex/Gemini/Qwen" in your request for CLI execution.
+
+**Task Attachment Model**:
+- Skill execute **expands workflow** by attaching sub-tasks to current TodoWrite
+- When executing a sub-command, its internal tasks are attached to the orchestrator's TodoWrite
+- Orchestrator **executes these attached tasks** sequentially
+- After completion, attached tasks are **collapsed** back to high-level phase summary
+- This is **task expansion**, not external delegation
+
+**Auto-Continue Mechanism**:
+- TodoList tracks current phase status and dynamically manages task attachment/collapse
+- When each phase finishes executing, automatically execute next pending phase
+- All phases run autonomously without user interaction
+- **CONTINUOUS EXECUTION** - Do not stop until all phases complete
+
+## Auto Mode
+
+When `--yes` or `-y`: Auto-continue all phases (skip confirmations), use recommended conflict resolutions, skip TDD clarifications.
+
+## Usage
+
+```
+Skill(skill="workflow-tdd-plan", args="<task description>")
+Skill(skill="workflow-tdd-plan", args="[-y|--yes] \"<task description>\"")
+
+# Flags
+-y, --yes    Skip all confirmations (auto mode)
+
+# Arguments
+<task description>    Task description text, TDD-structured format, or path to .md file
+
+# Examples
+Skill(skill="workflow-tdd-plan", args="\"Build user authentication with tests\"")              # Simple TDD task
+Skill(skill="workflow-tdd-plan", args="\"Add JWT auth with email/password and token refresh\"") # Detailed task
+Skill(skill="workflow-tdd-plan", args="-y \"Implement payment processing\"")                    # Auto mode
+Skill(skill="workflow-tdd-plan", args="\"tdd-requirements.md\"")                                # From file
+```
+
+## TDD Compliance Requirements
+
+### The Iron Law
+
+```
+NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
+```
+
+**Enforcement Method**:
+- Phase 5: `implementation_approach` includes test-first steps (Red → Green → Refactor)
+- Green phase: Includes test-fix-cycle configuration (max 3 iterations)
+- Auto-revert: Triggered when max iterations reached without passing tests
+
+**Verification**: Phase 6 validates Red-Green-Refactor structure in all generated tasks
+
+### TDD Compliance Checkpoint
+
+| Checkpoint | Validation Phase | Evidence Required |
+|------------|------------------|-------------------|
+| Test-first structure | Phase 5 | `implementation_approach` has 3 steps |
+| Red phase exists | Phase 6 | Step 1: `tdd_phase: "red"` |
+| Green phase with test-fix | Phase 6 | Step 2: `tdd_phase: "green"` + test-fix-cycle |
+| Refactor phase exists | Phase 6 | Step 3: `tdd_phase: "refactor"` |
+
+### Core TDD Principles
+
+**Red Flags - STOP and Reassess**:
+- Code written before test
+- Test passes immediately (no Red phase witnessed)
+- Cannot explain why test should fail
+- "Just this once" rationalization
+- "Tests after achieve same goals" thinking
+
+**Why Order Matters**:
+- Tests written after code pass immediately → proves nothing
+- Test-first forces edge case discovery before implementation
+- Tests-after verify what was built, not what's required
+
+## Core Rules
+
+1. **Start Immediately**: First action is TodoWrite initialization, second action is execute Phase 1
+2. **No Preliminary Analysis**: Do not read files before Phase 1
+3. **Parse Every Output**: Extract required data for next phase
+4. **Auto-Continue via TodoList**: Check TodoList status to execute next pending phase automatically
+5. **Track Progress**: Update TodoWrite dynamically with task attachment/collapse pattern
+6. **TDD Context**: All descriptions include "TDD:" prefix
+7. **Task Attachment Model**: Skill execute **attaches** sub-tasks to current workflow. Orchestrator **executes** these attached tasks itself, then **collapses** them after completion
+8. **CRITICAL: DO NOT STOP**: Continuous multi-phase workflow. After executing all attached tasks, immediately collapse them and execute next phase
+
+## Execution Flow
+
+```
+Input Parsing:
+   └─ Convert user input to TDD-structured format (TDD:/GOAL/SCOPE/CONTEXT/TEST_FOCUS)
+
+Phase 1: Session Discovery
+   └─ Ref: workflow-plan/phases/01-session-discovery.md (external)
+      └─ Output: sessionId (WFS-xxx)
+
+Phase 2: Context Gathering
+   └─ Ref: workflow-plan/phases/02-context-gathering.md (external)
+      ├─ Tasks attached: Analyze structure → Identify integration → Generate package
+      └─ Output: contextPath + conflict_risk
+
+Phase 3: Test Coverage Analysis                    ← ATTACHED (3 tasks)
+   └─ Ref: phases/01-test-context-gather.md
+      ├─ Phase 3.1: Detect test framework
+      ├─ Phase 3.2: Analyze existing test coverage
+      └─ Phase 3.3: Identify coverage gaps
+      └─ Output: test-context-package.json           ← COLLAPSED
+
+Phase 4: Conflict Resolution (conditional)
+   └─ Decision (conflict_risk check):
+      ├─ conflict_risk ≥ medium → Ref: workflow-plan/phases/03-conflict-resolution.md (external)
+      │   ├─ Tasks attached: Detect conflicts → Present to user → Apply strategies
+      │   └─ Output: Modified brainstorm artifacts     ← COLLAPSED
+      └─ conflict_risk < medium → Skip to Phase 5
+
+Phase 5: TDD Task Generation                       ← ATTACHED (3 tasks)
+   └─ Ref: phases/02-task-generate-tdd.md
+      ├─ Phase 5.1: Discovery - analyze TDD requirements
+      ├─ Phase 5.2: Planning - design Red-Green-Refactor cycles
+      └─ Phase 5.3: Output - generate IMPL tasks with internal TDD phases
+      └─ Output: IMPL-*.json, IMPL_PLAN.md           ← COLLAPSED
+
+Phase 6: TDD Structure Validation (inline)
+   └─ Internal validation + summary returned
+   └─ Recommend: plan-verify (external)
+
+Return:
+   └─ Summary with recommended next steps
+```
+
+### Phase Reference Documents
+
+**Local phases** (read on-demand when phase executes):
+
+| Phase | Document | Purpose |
+|-------|----------|---------|
+| Phase 3 | [phases/01-test-context-gather.md](phases/01-test-context-gather.md) | Test coverage context gathering via test-context-search-agent |
+| Phase 5 | [phases/02-task-generate-tdd.md](phases/02-task-generate-tdd.md) | TDD task JSON generation via action-planning-agent |
+
+**External phases** (from workflow-plan skill):
+
+| Phase | Document | Purpose |
+|-------|----------|---------|
+| Phase 1 | workflow-plan/phases/01-session-discovery.md | Session creation/discovery |
+| Phase 2 | workflow-plan/phases/02-context-gathering.md | Project context collection |
+| Phase 4 | workflow-plan/phases/03-conflict-resolution.md | Conflict detection and resolution (conditional) |
+
+**Post-execution verification**:
+
+| Phase | Document | Purpose |
+|-------|----------|---------|
+| TDD Verify | [phases/03-tdd-verify.md](phases/03-tdd-verify.md) | TDD compliance verification with quality gate |
+| Coverage Analysis | [phases/04-tdd-coverage-analysis.md](phases/04-tdd-coverage-analysis.md) | Test coverage and cycle analysis (called by TDD Verify) |
+
+## 6-Phase Execution
+
+### Phase 1: Session Discovery
+
+**Step 1.1: Execute** - Session discovery and initialization
+
+Read and execute: `workflow-plan/phases/01-session-discovery.md` with `--type tdd --auto "TDD: [structured-description]"`
+
+**TDD Structured Format**:
+```
+TDD: [Feature Name]
+GOAL: [Objective]
+SCOPE: [Included/excluded]
+CONTEXT: [Background]
+TEST_FOCUS: [Test scenarios]
+```
+
+**Parse**: Extract sessionId
+
+**TodoWrite**: Mark phase 1 completed, phase 2 in_progress
+
+**After Phase 1**: Return to user showing Phase 1 results, then auto-continue to Phase 2
+
+---
+
+### Phase 2: Context Gathering
+
+**Step 2.1: Execute** - Context gathering and analysis
+
+Read and execute: `workflow-plan/phases/02-context-gathering.md` with `--session [sessionId] "TDD: [structured-description]"`
+
+**Use Same Structured Description**: Pass the same structured format from Phase 1
+
+**Input**: `sessionId` from Phase 1
+
+**Parse Output**:
+- Extract: context-package.json path (store as `contextPath`)
+- Typical pattern: `.workflow/active/[sessionId]/.process/context-package.json`
+
+**Validation**:
+- Context package path extracted
+- File exists and is valid JSON
+
+**TodoWrite**: Mark phase 2 completed, phase 3 in_progress
+
+**After Phase 2**: Return to user showing Phase 2 results, then auto-continue to Phase 3
+
+---
+
+### Phase 3: Test Coverage Analysis
+
+**Step 3.1: Execute** - Test coverage analysis and framework detection
+
+Read and execute: `phases/01-test-context-gather.md` with `--session [sessionId]`
+
+**Purpose**: Analyze existing codebase for:
+- Existing test patterns and conventions
+- Current test coverage
+- Related components and integration points
+- Test framework detection
+
+**Parse**: Extract testContextPath (`.workflow/active/[sessionId]/.process/test-context-package.json`)
+
+**TodoWrite Update (Phase 3 - tasks attached)**:
+```json
+[
+  {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"},
+  {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"},
+  {"content": "Phase 3: Test Coverage Analysis", "status": "in_progress", "activeForm": "Executing test coverage analysis"},
+  {"content": "  → Detect test framework and conventions", "status": "in_progress", "activeForm": "Detecting test framework"},
+  {"content": "  → Analyze existing test coverage", "status": "pending", "activeForm": "Analyzing test coverage"},
+  {"content": "  → Identify coverage gaps", "status": "pending", "activeForm": "Identifying coverage gaps"},
+  {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"},
+  {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"}
+]
+```
+
+**Note**: Skill execute **attaches** test-context-gather's 3 tasks. Orchestrator **executes** these tasks.
+
+**Next Action**: Tasks attached → **Execute Phase 3.1-3.3** sequentially
+
+**TodoWrite Update (Phase 3 completed - tasks collapsed)**:
+```json
+[
+  {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"},
+  {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"},
+  {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"},
+  {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"},
+  {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"}
+]
+```
+
+**After Phase 3**: Return to user showing test coverage results, then auto-continue to Phase 4/5
+
+---
+
+### Phase 4: Conflict Resolution (Optional)
+
+**Trigger**: Only execute when context-package.json indicates conflict_risk is "medium" or "high"
+
+**Step 4.1: Execute** - Conflict detection and resolution
+
+Read and execute: `workflow-plan/phases/03-conflict-resolution.md` with `--session [sessionId] --context [contextPath]`
+
+**Input**:
+- sessionId from Phase 1
+- contextPath from Phase 2
+- conflict_risk from context-package.json
+
+**Parse Output**:
+- Extract: Execution status (success/skipped/failed)
+- Verify: conflict-resolution.json file path (if executed)
+
+**Skip Behavior**:
+- If conflict_risk is "none" or "low", skip directly to Phase 5
+- Display: "No significant conflicts detected, proceeding to TDD task generation"
+
+**TodoWrite Update (Phase 4 - tasks attached, if conflict_risk >= medium)**:
+```json
+[
+  {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"},
+  {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"},
+  {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"},
+  {"content": "Phase 4: Conflict Resolution", "status": "in_progress", "activeForm": "Executing conflict resolution"},
+  {"content": "  → Detect conflicts with CLI analysis", "status": "in_progress", "activeForm": "Detecting conflicts"},
+  {"content": "  → Log and analyze detected conflicts", "status": "pending", "activeForm": "Analyzing conflicts"},
+  {"content": "  → Apply resolution strategies", "status": "pending", "activeForm": "Applying resolution strategies"},
+  {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"},
+  {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"}
+]
+```
+
+**TodoWrite Update (Phase 4 completed - tasks collapsed)**:
+```json
+[
+  {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"},
+  {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"},
+  {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"},
+  {"content": "Phase 4: Conflict Resolution", "status": "completed", "activeForm": "Executing conflict resolution"},
+  {"content": "Phase 5: TDD Task Generation", "status": "pending", "activeForm": "Executing TDD task generation"},
+  {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"}
+]
+```
+
+**After Phase 4**: Return to user showing conflict resolution results, then auto-continue to Phase 5
+
+**Memory State Check**:
+- Evaluate current context window usage and memory state
+- If memory usage is high (>110K tokens or approaching context limits):
+
+  **Step 4.5: Execute** - Memory compaction (external skill: compact)
+
+  - This optimizes memory before proceeding to Phase 5
+- Memory compaction is particularly important after analysis phase which may generate extensive documentation
+
+---
+
+### Phase 5: TDD Task Generation
+
+**Step 5.1: Execute** - TDD task generation via action-planning-agent with Phase 0 user configuration
+
+Read and execute: `phases/02-task-generate-tdd.md` with `--session [sessionId]`
+
+**Note**: Phase 0 now includes:
+- Supplementary materials collection (file paths or inline content)
+- Execution method preference (Agent/Hybrid/CLI)
+- CLI tool preference (Codex/Gemini/Qwen/Auto)
+- These preferences are passed to agent for task generation
+
+**Parse**: Extract feature count, task count, CLI execution IDs assigned
+
+**Validate**:
+- IMPL_PLAN.md exists (unified plan with TDD Implementation Tasks section)
+- IMPL-*.json files exist (one per feature, or container + subtasks for complex features)
+- TODO_LIST.md exists with internal TDD phase indicators
+- Each IMPL task includes:
+  - `meta.tdd_workflow: true`
+  - `meta.cli_execution_id: {session_id}-{task_id}`
+  - `meta.cli_execution: { "strategy": "new|resume|fork|merge_fork", ... }`
+  - `flow_control.implementation_approach` with exactly 3 steps (red/green/refactor)
+  - Green phase includes test-fix-cycle configuration
+  - `context.focus_paths`: absolute or clear relative paths
+  - `flow_control.pre_analysis`: includes exploration integration_points analysis
+- IMPL_PLAN.md contains workflow_type: "tdd" in frontmatter
+- Task count <=18 (compliance with hard limit)
+
+**Red Flag Detection** (Non-Blocking Warnings):
+- Task count >18: `Warning: Task count exceeds hard limit - request re-scope`
+- Missing cli_execution_id: `Warning: Task lacks CLI execution ID for resume support`
+- Missing test-fix-cycle: `Warning: Green phase lacks auto-revert configuration`
+- Generic task names: `Warning: Vague task names suggest unclear TDD cycles`
+- Missing focus_paths: `Warning: Task lacks clear file scope for implementation`
+
+**Action**: Log warnings to `.workflow/active/[sessionId]/.process/tdd-warnings.log` (non-blocking)
+
+**TodoWrite Update (Phase 5 - tasks attached)**:
+```json
+[
+  {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"},
+  {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"},
+  {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"},
+  {"content": "Phase 5: TDD Task Generation", "status": "in_progress", "activeForm": "Executing TDD task generation"},
+  {"content": "  → Discovery - analyze TDD requirements", "status": "in_progress", "activeForm": "Analyzing TDD requirements"},
+  {"content": "  → Planning - design Red-Green-Refactor cycles", "status": "pending", "activeForm": "Designing TDD cycles"},
+  {"content": "  → Output - generate IMPL tasks with internal TDD phases", "status": "pending", "activeForm": "Generating TDD tasks"},
+  {"content": "Phase 6: TDD Structure Validation", "status": "pending", "activeForm": "Validating TDD structure"}
+]
+```
+
+**TodoWrite Update (Phase 5 completed - tasks collapsed)**:
+```json
+[
+  {"content": "Phase 1: Session Discovery", "status": "completed", "activeForm": "Executing session discovery"},
+  {"content": "Phase 2: Context Gathering", "status": "completed", "activeForm": "Executing context gathering"},
+  {"content": "Phase 3: Test Coverage Analysis", "status": "completed", "activeForm": "Executing test coverage analysis"},
+  {"content": "Phase 5: TDD Task Generation", "status": "completed", "activeForm": "Executing TDD task generation"},
+  {"content": "Phase 6: TDD Structure Validation", "status": "in_progress", "activeForm": "Validating TDD structure"}
+]
+```
+
+### Phase 6: TDD Structure Validation & Action Plan Verification (RECOMMENDED)
+
+**Internal validation first, then recommend external verification**
+
+**Internal Validation**:
+1. Each task contains complete TDD workflow (Red-Green-Refactor internally)
+2. Task structure validation:
+   - `meta.tdd_workflow: true` in all IMPL tasks
+   - `meta.cli_execution_id` present (format: {session_id}-{task_id})
+   - `meta.cli_execution` strategy assigned (new/resume/fork/merge_fork)
+   - `flow_control.implementation_approach` has exactly 3 steps
+   - Each step has correct `tdd_phase`: "red", "green", "refactor"
+   - `context.focus_paths` are absolute or clear relative paths
+   - `flow_control.pre_analysis` includes exploration integration analysis
+3. Dependency validation:
+   - Sequential features: IMPL-N depends_on ["IMPL-(N-1)"] if needed
+   - Complex features: IMPL-N.M depends_on ["IMPL-N.(M-1)"] for subtasks
+   - CLI execution strategies correctly assigned based on dependency graph
+4. Agent assignment: All IMPL tasks use @code-developer
+5. Test-fix cycle: Green phase step includes test-fix-cycle logic with max_iterations
+6. Task count: Total tasks <=18 (simple + subtasks hard limit)
+7. User configuration:
+   - Execution method choice reflected in task structure
+   - CLI tool preference documented in implementation guidance (if CLI selected)
+
+**Red Flag Checklist** (from TDD best practices):
+- [ ] No tasks skip Red phase (`tdd_phase: "red"` exists in step 1)
+- [ ] Test files referenced in Red phase (explicit paths, not placeholders)
+- [ ] Green phase has test-fix-cycle with `max_iterations` configured
+- [ ] Refactor phase has clear completion criteria
+
+**Non-Compliance Warning Format**:
+```
+Warning TDD Red Flag: [issue description]
+   Task: [IMPL-N]
+   Recommendation: [action to fix]
+```
+
+**Evidence Gathering** (Before Completion Claims):
+
+```bash
+# Verify session artifacts exist
+ls -la .workflow/active/[sessionId]/{IMPL_PLAN.md,TODO_LIST.md}
+ls -la .workflow/active/[sessionId]/.task/IMPL-*.json
+
+# Count generated artifacts
+echo "IMPL tasks: $(ls .workflow/active/[sessionId]/.task/IMPL-*.json 2>/dev/null | wc -l)"
+
+# Sample task structure verification (first task)
+jq '{id, tdd: .meta.tdd_workflow, cli_id: .meta.cli_execution_id, phases: [.flow_control.implementation_approach[].tdd_phase]}' \
+  "$(ls .workflow/active/[sessionId]/.task/IMPL-*.json | head -1)"
+```
+
+**Evidence Required Before Summary**:
+| Evidence Type | Verification Method | Pass Criteria |
+|---------------|---------------------|---------------|
+| File existence | `ls -la` artifacts | All files present |
+| Task count | Count IMPL-*.json | Count matches claims (<=18) |
+| TDD structure | jq sample extraction | Shows red/green/refactor + cli_execution_id |
+| CLI execution IDs | jq extraction | All tasks have cli_execution_id assigned |
+| Warning log | Check tdd-warnings.log | Logged (may be empty) |
+
+**Return Summary**:
+```
+TDD Planning complete for session: [sessionId]
+
+Features analyzed: [N]
+Total tasks: [M] (1 task per simple feature + subtasks for complex features)
+
+Task breakdown:
+- Simple features: [K] tasks (IMPL-1 to IMPL-K)
+- Complex features: [L] features with [P] subtasks
+- Total task count: [M] (within 18-task hard limit)
+
+Structure:
+- IMPL-1: {Feature 1 Name} (Internal: Red → Green → Refactor)
+- IMPL-2: {Feature 2 Name} (Internal: Red → Green → Refactor)
+- IMPL-3: {Complex Feature} (Container)
+  - IMPL-3.1: {Sub-feature A} (Internal: Red → Green → Refactor)
+  - IMPL-3.2: {Sub-feature B} (Internal: Red → Green → Refactor)
+[...]
+
+Plans generated:
+- Unified Implementation Plan: .workflow/active/[sessionId]/IMPL_PLAN.md
+  (includes TDD Implementation Tasks section with workflow_type: "tdd")
+- Task List: .workflow/active/[sessionId]/TODO_LIST.md
+  (with internal TDD phase indicators and CLI execution strategies)
+- Task JSONs: .workflow/active/[sessionId]/.task/IMPL-*.json
+  (with cli_execution_id and execution strategies for resume support)
+
+TDD Configuration:
+- Each task contains complete Red-Green-Refactor cycle
+- Green phase includes test-fix cycle (max 3 iterations)
+- Auto-revert on max iterations reached
+- CLI execution strategies: new/resume/fork/merge_fork based on dependency graph
+
+User Configuration Applied:
+- Execution Method: [agent|hybrid|cli]
+- CLI Tool Preference: [codex|gemini|qwen|auto]
+- Supplementary Materials: [included|none]
+- Task generation follows cli-tools-usage.md guidelines
+
+ACTION REQUIRED: Before execution, ensure you understand WHY each Red phase test is expected to fail.
+   This is crucial for valid TDD - if you don't know why the test fails, you can't verify it tests the right thing.
+
+Recommended Next Steps:
+1. plan-verify (external) --session [sessionId]  # Verify TDD plan quality and dependencies
+2. workflow:execute (external) --session [sessionId]  # Start TDD execution with CLI strategies
+3. phases/03-tdd-verify.md [sessionId]  # Post-execution TDD compliance check
+
+Quality Gate: Consider running plan-verify to validate TDD task structure, dependencies, and CLI execution strategies
+```
+
+## Input Processing
+
+Convert user input to TDD-structured format:
+
+**Simple text** → Add TDD context
+**Detailed text** → Extract components with TEST_FOCUS
+**File/Issue** → Read and structure with TDD
+
+## Data Flow
+
+```
+User Input (task description)
+    ↓
+[Convert to TDD Structured Format]
+    ↓ TDD Structured Description:
+    ↓   TDD: [Feature Name]
+    ↓   GOAL: [objective]
+    ↓   SCOPE: [boundaries]
+    ↓   CONTEXT: [background]
+    ↓   TEST_FOCUS: [test scenarios]
+    ↓
+Phase 1: session:start --type tdd --auto "TDD: structured-description"
+    ↓ Output: sessionId
+    ↓
+Phase 2: context-gather --session sessionId "TDD: structured-description"
+    ↓ Output: contextPath + conflict_risk
+    ↓
+Phase 3: test-context-gather --session sessionId
+    ↓ Output: testContextPath (test-context-package.json)
+    ↓
+Phase 4: conflict-resolution [AUTO-TRIGGERED if conflict_risk >= medium]
+    ↓ Output: Modified brainstorm artifacts
+    ↓ Skip if conflict_risk is none/low → proceed directly to Phase 5
+    ↓
+Phase 5: task-generate-tdd --session sessionId
+    ↓ Output: IMPL_PLAN.md, task JSONs, TODO_LIST.md
+    ↓
+Phase 6: Internal validation + summary
+    ↓
+Return summary to user
+```
+
+## TodoWrite Pattern
+
+**Core Concept**: Dynamic task attachment and collapse for TDD workflow with test coverage analysis and Red-Green-Refactor cycle generation.
+
+### Key Principles
+
+1. **Task Attachment** (when Skill executed):
+   - Sub-command's internal tasks are **attached** to orchestrator's TodoWrite
+   - First attached task marked as `in_progress`, others as `pending`
+   - Orchestrator **executes** these attached tasks sequentially
+
+2. **Task Collapse** (after sub-tasks complete):
+   - Remove detailed sub-tasks from TodoWrite
+   - **Collapse** to high-level phase summary
+   - Maintains clean orchestrator-level view
+
+3. **Continuous Execution**:
+   - After collapse, automatically proceed to next pending phase
+   - No user intervention required between phases
+   - TodoWrite dynamically reflects current execution state
+
+**Lifecycle Summary**: Initial pending tasks → Phase executed (tasks ATTACHED) → Sub-tasks executed sequentially → Phase completed (tasks COLLAPSED to summary) → Next phase begins (conditional Phase 4 if conflict_risk >= medium) → Repeat until all phases complete.
+
+### TDD-Specific Features
+
+- **Phase 3**: Test coverage analysis detects existing patterns and gaps
+- **Phase 5**: Generated IMPL tasks contain internal Red-Green-Refactor cycles
+- **Conditional Phase 4**: Conflict resolution only if conflict_risk >= medium
+
+**Note**: See individual Phase descriptions (Phase 3, 4, 5) for detailed TodoWrite Update examples with full JSON structures.
+
+## Execution Flow Diagram
+
+```
+TDD Workflow Orchestrator
+│
+├─ Phase 1: Session Discovery
+│  └─ workflow-plan/phases/01-session-discovery.md --auto
+│     └─ Returns: sessionId
+│
+├─ Phase 2: Context Gathering
+│  └─ workflow-plan/phases/02-context-gathering.md
+│     └─ Returns: context-package.json path
+│
+├─ Phase 3: Test Coverage Analysis                    ← ATTACHED (3 tasks)
+│  └─ phases/01-test-context-gather.md
+│     ├─ Phase 3.1: Detect test framework
+│     ├─ Phase 3.2: Analyze existing test coverage
+│     └─ Phase 3.3: Identify coverage gaps
+│     └─ Returns: test-context-package.json           ← COLLAPSED
+│
+├─ Phase 4: Conflict Resolution (conditional)
+│  IF conflict_risk >= medium:
+│  └─ workflow-plan/phases/03-conflict-resolution.md   ← ATTACHED (3 tasks)
+│     ├─ Phase 4.1: Detect conflicts with CLI
+│     ├─ Phase 4.2: Log and analyze detected conflicts
+│     └─ Phase 4.3: Apply resolution strategies
+│     └─ Returns: conflict-resolution.json            ← COLLAPSED
+│  ELSE:
+│  └─ Skip to Phase 5
+│
+├─ Phase 5: TDD Task Generation                       ← ATTACHED (3 tasks)
+│  └─ phases/02-task-generate-tdd.md
+│     ├─ Phase 5.1: Discovery - analyze TDD requirements
+│     ├─ Phase 5.2: Planning - design Red-Green-Refactor cycles
+│     └─ Phase 5.3: Output - generate IMPL tasks with internal TDD phases
+│     └─ Returns: IMPL-*.json, IMPL_PLAN.md           ← COLLAPSED
+│        (Each IMPL task contains internal Red-Green-Refactor cycle)
+│
+└─ Phase 6: TDD Structure Validation
+   └─ Internal validation + summary returned
+   └─ Recommend: plan-verify (external)
+
+Key Points:
+• ← ATTACHED: Sub-tasks attached to orchestrator TodoWrite
+• ← COLLAPSED: Sub-tasks executed and collapsed to phase summary
+• TDD-specific: Each generated IMPL task contains complete Red-Green-Refactor cycle
+```
+
+## Error Handling
+
+- **Parsing failure**: Retry once, then report
+- **Validation failure**: Report missing/invalid data
+- **Command failure**: Keep phase in_progress, report error
+- **TDD validation failure**: Report incomplete chains or wrong dependencies
+
+### TDD Warning Patterns
+
+| Pattern | Warning Message | Recommended Action |
+|---------|----------------|-------------------|
+| Task count >10 | High task count detected | Consider splitting into multiple sessions |
+| Missing test-fix-cycle | Green phase lacks auto-revert | Add `max_iterations: 3` to task config |
+| Red phase missing test path | Test file path not specified | Add explicit test file paths |
+| Generic task names | Vague names like "Add feature" | Use specific behavior descriptions |
+| No refactor criteria | Refactor phase lacks completion criteria | Define clear refactor scope |
+
+### Non-Blocking Warning Policy
+
+**All warnings are advisory** - they do not halt execution:
+1. Warnings logged to `.process/tdd-warnings.log`
+2. Summary displayed in Phase 6 output
+3. User decides whether to address before execution
+
+### Error Handling Quick Reference
+
+| Error Type | Detection | Recovery Action |
+|------------|-----------|-----------------|
+| Parsing failure | Empty/malformed output | Retry once, then report |
+| Missing context-package | File read error | Re-run context-gather (workflow-plan/phases/02-context-gathering.md) |
+| Invalid task JSON | jq parse error | Report malformed file path |
+| Task count exceeds 18 | Count validation >=19 | Request re-scope, split into multiple sessions |
+| Missing cli_execution_id | All tasks lack ID | Regenerate tasks with phase 0 user config |
+| Test-context missing | File not found | Re-run phases/01-test-context-gather.md |
+| Phase timeout | No response | Retry phase, check CLI connectivity |
+| CLI tool not available | Tool not in cli-tools.json | Fall back to alternative preferred tool |
+
+## Post-Execution: TDD Verification
+
+After TDD tasks have been executed (via workflow:execute), run TDD compliance verification:
+
+Read and execute: `phases/03-tdd-verify.md` with `--session [sessionId]`
+
+This generates a comprehensive TDD_COMPLIANCE_REPORT.md with quality gate recommendation.
+
+## Related Skills
+
+**Prerequisite**:
+- None - TDD planning is self-contained (can optionally run brainstorm before)
+
+**Called by This Skill** (6 phases):
+- workflow-plan/phases/01-session-discovery.md - Phase 1: Create or discover TDD workflow session
+- workflow-plan/phases/02-context-gathering.md - Phase 2: Gather project context and analyze codebase
+- phases/01-test-context-gather.md - Phase 3: Analyze existing test patterns and coverage
+- workflow-plan/phases/03-conflict-resolution.md - Phase 4: Detect and resolve conflicts (conditional)
+- compact (external skill) - Phase 4.5: Memory optimization (if context approaching limits)
+- phases/02-task-generate-tdd.md - Phase 5: Generate TDD tasks
+
+**Follow-up**:
+- plan-verify (external) - Recommended: Verify TDD plan quality and structure before execution
+- workflow:status (external) - Review TDD task breakdown
+- workflow:execute (external) - Begin TDD implementation
+- phases/03-tdd-verify.md - Post-execution: Verify TDD compliance and generate quality report
+
+## Next Steps Decision Table
+
+| Situation | Recommended Action | Purpose |
+|-----------|-------------------|---------|
+| First time planning | Run plan-verify (external) | Validate task structure before execution |
+| Warnings in tdd-warnings.log | Review log, refine tasks | Address Red Flags before proceeding |
+| High task count warning | Consider new session | Split into focused sub-sessions |
+| Ready to implement | Run workflow:execute (external) | Begin TDD Red-Green-Refactor cycles |
+| After implementation | Run phases/03-tdd-verify.md | Generate TDD compliance report |
+| Need to review tasks | Run workflow:status (external) | Inspect current task breakdown |
+
+### TDD Workflow State Transitions
+
+```
+workflow-tdd-plan (this skill)
+        ↓
+[Planning Complete] ──→ plan-verify (external, recommended)
+        ↓
+[Verified/Ready] ─────→ workflow:execute (external)
+        ↓
+[Implementation] ─────→ phases/03-tdd-verify.md (post-execution)
+        ↓
+[Quality Report] ─────→ Done or iterate
+```
--- a/.claude/skills/workflow-tdd-plan/phases/01-test-context-gather.md
+++ b/.claude/skills/workflow-tdd-plan/phases/01-test-context-gather.md
@@ -0,0 +1,213 @@
+# Phase 1: Test Context Gather
+
+## Overview
+
+Orchestrator command that invokes `test-context-search-agent` to gather comprehensive test coverage context for test generation workflows. Generates standardized `test-context-package.json` with coverage analysis, framework detection, and source implementation context.
+
+## Core Philosophy
+
+- **Agent Delegation**: Delegate all test coverage analysis to `test-context-search-agent` for autonomous execution
+- **Detection-First**: Check for existing test-context-package before executing
+- **Coverage-First**: Analyze existing test coverage before planning new tests
+- **Source Context Loading**: Import implementation summaries from source session
+- **Standardized Output**: Generate `.workflow/active/{test_session_id}/.process/test-context-package.json`
+
+## Execution Process
+
+```
+Input Parsing:
+   ├─ Parse flags: --session
+   └─ Validation: test_session_id REQUIRED
+
+Step 1: Test-Context-Package Detection
+   └─ Decision (existing package):
+      ├─ Valid package exists → Return existing (skip execution)
+      └─ No valid package → Continue to Step 2
+
+Step 2: Invoke Test-Context-Search Agent
+   ├─ Phase 1: Session Validation & Source Context Loading
+   │  ├─ Detection: Check for existing test-context-package
+   │  ├─ Test session validation
+   │  └─ Source context loading (summaries, changed files)
+   ├─ Phase 2: Test Coverage Analysis
+   │  ├─ Track 1: Existing test discovery
+   │  ├─ Track 2: Coverage gap analysis
+   │  └─ Track 3: Coverage statistics
+   └─ Phase 3: Framework Detection & Packaging
+      ├─ Framework identification
+      ├─ Convention analysis
+      └─ Generate test-context-package.json
+
+Step 3: Output Verification
+   └─ Verify test-context-package.json created
+```
+
+## Execution Flow
+
+### Step 1: Test-Context-Package Detection
+
+**Execute First** - Check if valid package already exists:
+
+```javascript
+const testContextPath = `.workflow/${test_session_id}/.process/test-context-package.json`;
+
+if (file_exists(testContextPath)) {
+  const existing = Read(testContextPath);
+
+  // Validate package belongs to current test session
+  if (existing?.metadata?.test_session_id === test_session_id) {
+    console.log("Valid test-context-package found for session:", test_session_id);
+    console.log("Coverage Stats:", existing.test_coverage.coverage_stats);
+    console.log("Framework:", existing.test_framework.framework);
+    console.log("Missing Tests:", existing.test_coverage.missing_tests.length);
+    return existing; // Skip execution, return existing
+  } else {
+    console.warn("Invalid test_session_id in existing package, re-generating...");
+  }
+}
+```
+
+### Step 2: Invoke Test-Context-Search Agent
+
+**Only execute if Step 1 finds no valid package**
+
+```javascript
+Task(
+  subagent_type="test-context-search-agent",
+  run_in_background=false,
+  description="Gather test coverage context",
+  prompt=`
+
+## Execution Mode
+**PLAN MODE** (Comprehensive) - Full Phase 1-3 execution
+
+## Session Information
+- **Test Session ID**: ${test_session_id}
+- **Output Path**: .workflow/${test_session_id}/.process/test-context-package.json
+
+## Mission
+Execute complete test-context-search-agent workflow for test generation planning:
+
+### Phase 1: Session Validation & Source Context Loading
+1. **Detection**: Check for existing test-context-package (early exit if valid)
+2. **Test Session Validation**: Load test session metadata, extract source_session reference
+3. **Source Context Loading**: Load source session implementation summaries, changed files, tech stack
+
+### Phase 2: Test Coverage Analysis
+Execute coverage discovery:
+- **Track 1**: Existing test discovery (find *.test.*, *.spec.* files)
+- **Track 2**: Coverage gap analysis (match implementation files to test files)
+- **Track 3**: Coverage statistics (calculate percentages, identify gaps by module)
+
+### Phase 3: Framework Detection & Packaging
+1. Framework identification from package.json/requirements.txt
+2. Convention analysis from existing test patterns
+3. Generate and validate test-context-package.json
+
+## Output Requirements
+Complete test-context-package.json with:
+- **metadata**: test_session_id, source_session_id, task_type, complexity
+- **source_context**: implementation_summaries, tech_stack, project_patterns
+- **test_coverage**: existing_tests[], missing_tests[], coverage_stats
+- **test_framework**: framework, version, test_pattern, conventions
+- **assets**: implementation_summary[], existing_test[], source_code[] with priorities
+- **focus_areas**: Test generation guidance based on coverage gaps
+
+## Quality Validation
+Before completion verify:
+- [ ] Valid JSON format with all required fields
+- [ ] Source session context loaded successfully
+- [ ] Test coverage gaps identified
+- [ ] Test framework detected (or marked as 'unknown')
+- [ ] Coverage percentage calculated correctly
+- [ ] Missing tests catalogued with priority
+- [ ] Execution time < 30 seconds (< 60s for large codebases)
+
+Execute autonomously following agent documentation.
+Report completion with coverage statistics.
+`
+)
+```
+
+### Step 3: Output Verification
+
+After agent completes, verify output:
+
+```javascript
+// Verify file was created
+const outputPath = `.workflow/${test_session_id}/.process/test-context-package.json`;
+if (!file_exists(outputPath)) {
+  throw new Error("Agent failed to generate test-context-package.json");
+}
+
+// Load and display summary
+const testContext = Read(outputPath);
+console.log("Test context package generated successfully");
+console.log("Coverage:", testContext.test_coverage.coverage_stats.coverage_percentage + "%");
+console.log("Tests to generate:", testContext.test_coverage.missing_tests.length);
+```
+
+## Parameter Reference
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `--session` | string | Yes | Test workflow session ID (e.g., WFS-test-auth) |
+
+## Output Schema
+
+Refer to `test-context-search-agent.md` Phase 3.2 for complete `test-context-package.json` schema.
+
+**Key Sections**:
+- **metadata**: Test session info, source session reference, complexity
+- **source_context**: Implementation summaries with changed files and tech stack
+- **test_coverage**: Existing tests, missing tests with priorities, coverage statistics
+- **test_framework**: Framework name, version, patterns, conventions
+- **assets**: Categorized files with relevance (implementation_summary, existing_test, source_code)
+- **focus_areas**: Test generation guidance based on analysis
+
+## Success Criteria
+
+- Valid test-context-package.json generated in `.workflow/active/{test_session_id}/.process/`
+- Source session context loaded successfully
+- Test coverage gaps identified (>90% accuracy)
+- Test framework detected and documented
+- Execution completes within 30 seconds (60s for large codebases)
+- All required schema fields present and valid
+- Coverage statistics calculated correctly
+- Agent reports completion with statistics
+
+## Error Handling
+
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Package validation failed | Invalid test_session_id in existing package | Re-run agent to regenerate |
+| Source session not found | Invalid source_session reference | Verify test session metadata |
+| No implementation summaries | Source session incomplete | Complete source session first |
+| Agent execution timeout | Large codebase or slow analysis | Increase timeout, check file access |
+| Missing required fields | Agent incomplete execution | Check agent logs, verify schema compliance |
+| No test framework detected | Missing test dependencies | Agent marks as 'unknown', manual specification needed |
+
+## Integration
+
+### Called By
+- SKILL.md (Phase 3: Test Coverage Analysis)
+
+### Calls
+- `test-context-search-agent` - Autonomous test coverage analysis
+
+## Notes
+
+- **Detection-first**: Always check for existing test-context-package before invoking agent
+- **No redundancy**: This command is a thin orchestrator, all logic in agent
+- **Framework agnostic**: Supports Jest, Mocha, pytest, RSpec, Go testing, etc.
+- **Coverage focus**: Primary goal is identifying implementation files without tests
+
+---
+
+## Post-Phase Update
+
+After Phase 1 (Test Context Gather) completes:
+- **Output Created**: `test-context-package.json` in `.workflow/active/{session}/.process/`
+- **Data Available**: Test coverage stats, framework info, missing tests list
+- **Next Action**: Continue to Phase 4 (Conflict Resolution, if conflict_risk >= medium) or Phase 5 (TDD Task Generation)
+- **TodoWrite**: Collapse Phase 3 sub-tasks to "Phase 3: Test Coverage Analysis: completed"
--- a/.claude/skills/workflow-tdd-plan/phases/02-task-generate-tdd.md
+++ b/.claude/skills/workflow-tdd-plan/phases/02-task-generate-tdd.md
@@ -0,0 +1,746 @@
+## Auto Mode
+
+When `--yes` or `-y`: Skip user questions, use defaults (no materials, Agent executor).
+
+# Phase 2: TDD Task Generation
+
+## Overview
+Autonomous TDD task JSON and IMPL_PLAN.md generation using action-planning-agent with two-phase execution: discovery and document generation. Generates complete Red-Green-Refactor cycles contained within each task.
+
+## Core Philosophy
+- **Agent-Driven**: Delegate execution to action-planning-agent for autonomous operation
+- **Two-Phase Flow**: Discovery (context gathering) → Output (document generation)
+- **Memory-First**: Reuse loaded documents from conversation memory
+- **MCP-Enhanced**: Use MCP tools for advanced code analysis and research
+- **Semantic CLI Selection**: CLI tool usage determined from user's task description, not flags
+- **Agent Simplicity**: Agent generates content with semantic CLI detection
+- **Path Clarity**: All `focus_paths` prefer absolute paths (e.g., `D:\\project\\src\\module`), or clear relative paths from project root (e.g., `./src/module`)
+- **TDD-First**: Every feature starts with a failing test (Red phase)
+- **Feature-Complete Tasks**: Each task contains complete Red-Green-Refactor cycle
+- **Quantification-Enforced**: All test cases, coverage requirements, and implementation scope MUST include explicit counts and enumerations
+
+## Task Strategy & Philosophy
+
+### Optimized Task Structure (Current)
+- **1 feature = 1 task** containing complete TDD cycle internally
+- Each task executes Red-Green-Refactor phases sequentially
+- Task count = Feature count (typically 5 features = 5 tasks)
+
+**Previous Approach** (Deprecated):
+- 1 feature = 3 separate tasks (TEST-N.M, IMPL-N.M, REFACTOR-N.M)
+- 5 features = 15 tasks with complex dependency chains
+- High context switching cost between phases
+
+### When to Use Subtasks
+- Feature complexity >2500 lines or >6 files per TDD cycle
+- Multiple independent sub-features needing parallel execution
+- Strong technical dependency blocking (e.g., API before UI)
+- Different tech stacks or domains within feature
+
+### Task Limits
+- **Maximum 18 tasks** (hard limit for TDD workflows)
+- **Feature-based**: Complete functional units with internal TDD cycles
+- **Hierarchy**: Flat (<=5 simple features) | Two-level (6-10 for complex features with sub-features)
+- **Re-scope**: If >18 tasks needed, break project into multiple TDD workflow sessions
+
+### TDD Cycle Mapping
+- **Old approach**: 1 feature = 3 tasks (TEST-N.M, IMPL-N.M, REFACTOR-N.M)
+- **Current approach**: 1 feature = 1 task (IMPL-N with internal Red-Green-Refactor phases)
+- **Complex features**: 1 container (IMPL-N) + subtasks (IMPL-N.M) when necessary
+
+## Execution Process
+
+```
+Input Parsing:
+   ├─ Parse flags: --session
+   └─ Validation: session_id REQUIRED
+
+Phase 1: Discovery & Context Loading (Memory-First)
+   ├─ Load session context (if not in memory)
+   ├─ Load context package (if not in memory)
+   ├─ Load test context package (if not in memory)
+   ├─ Extract & load role analyses from context package
+   ├─ Load conflict resolution (if exists)
+   └─ Optional: MCP external research
+
+Phase 2: Agent Execution (Document Generation)
+   ├─ Pre-agent template selection (semantic CLI detection)
+   ├─ Invoke action-planning-agent
+   ├─ Generate TDD Task JSON Files (.task/IMPL-*.json)
+   │  └─ Each task: complete Red-Green-Refactor cycle internally
+   ├─ Create IMPL_PLAN.md (TDD variant)
+   └─ Generate TODO_LIST.md with TDD phase indicators
+```
+
+## Execution Lifecycle
+
+### Phase 0: User Configuration (Interactive)
+
+**Purpose**: Collect user preferences before TDD task generation to ensure generated tasks match execution expectations and provide necessary supplementary context.
+
+**User Questions**:
+```javascript
+AskUserQuestion({
+  questions: [
+    {
+      question: "Do you have supplementary materials or guidelines to include?",
+      header: "Materials",
+      multiSelect: false,
+      options: [
+        { label: "No additional materials", description: "Use existing context only" },
+        { label: "Provide file paths", description: "I'll specify paths to include" },
+        { label: "Provide inline content", description: "I'll paste content directly" }
+      ]
+    },
+    {
+      question: "Select execution method for generated TDD tasks:",
+      header: "Execution",
+      multiSelect: false,
+      options: [
+        { label: "Agent (Recommended)", description: "Claude agent executes Red-Green-Refactor cycles directly" },
+        { label: "Hybrid", description: "Agent orchestrates, calls CLI for complex steps (Red/Green phases)" },
+        { label: "CLI Only", description: "All TDD cycles via CLI tools (codex/gemini/qwen)" }
+      ]
+    },
+    {
+      question: "If using CLI, which tool do you prefer?",
+      header: "CLI Tool",
+      multiSelect: false,
+      options: [
+        { label: "Codex (Recommended)", description: "Best for TDD Red-Green-Refactor cycles" },
+        { label: "Gemini", description: "Best for analysis and large context" },
+        { label: "Qwen", description: "Alternative analysis tool" },
+        { label: "Auto", description: "Let agent decide per-task" }
+      ]
+    }
+  ]
+})
+```
+
+**Handle Materials Response**:
+```javascript
+if (userConfig.materials === "Provide file paths") {
+  // Follow-up question for file paths
+  const pathsResponse = AskUserQuestion({
+    questions: [{
+      question: "Enter file paths to include (comma-separated or one per line):",
+      header: "Paths",
+      multiSelect: false,
+      options: [
+        { label: "Enter paths", description: "Provide paths in text input" }
+      ]
+    }]
+  })
+  userConfig.supplementaryPaths = parseUserPaths(pathsResponse)
+}
+```
+
+**Build userConfig**:
+```javascript
+const userConfig = {
+  supplementaryMaterials: {
+    type: "none|paths|inline",
+    content: [...],  // Parsed paths or inline content
+  },
+  executionMethod: "agent|hybrid|cli",
+  preferredCliTool: "codex|gemini|qwen|auto",
+  enableResume: true  // Always enable resume for CLI executions
+}
+```
+
+**Pass to Agent**: Include `userConfig` in agent prompt for Phase 2.
+
+---
+
+### Phase 1: Context Preparation & Discovery
+
+**Command Responsibility**: Command prepares session paths and metadata, provides to agent for autonomous context loading.
+
+**Memory-First Rule**: Skip file loading if documents already in conversation memory
+
+**Progressive Loading Strategy**: Load context incrementally due to large analysis.md file sizes:
+- **Core**: session metadata + context-package.json (always load)
+- **Selective**: synthesis_output OR (guidance + relevant role analyses) - NOT all role analyses
+- **On-Demand**: conflict resolution (if conflict_risk >= medium), test context
+
+**Path Clarity Requirement**: All `focus_paths` prefer absolute paths (e.g., `D:\\project\\src\\module`), or clear relative paths from project root (e.g., `./src/module`)
+
+**Session Path Structure** (Provided by Command to Agent):
+```
+.workflow/active/WFS-{session-id}/
+├── workflow-session.json          # Session metadata
+├── .process/
+│   ├── context-package.json       # Context package with artifact catalog
+│   ├── test-context-package.json  # Test coverage analysis
+│   └── conflict-resolution.json   # Conflict resolution (if exists)
+├── .task/                         # Output: Task JSON files
+│   ├── IMPL-1.json
+│   ├── IMPL-2.json
+│   └── ...
+├── IMPL_PLAN.md                   # Output: TDD implementation plan
+└── TODO_LIST.md                   # Output: TODO list with TDD phases
+```
+
+**Command Preparation**:
+1. **Assemble Session Paths** for agent prompt:
+   - `session_metadata_path`: `.workflow/active/{session-id}/workflow-session.json`
+   - `context_package_path`: `.workflow/active/{session-id}/.process/context-package.json`
+   - `test_context_package_path`: `.workflow/active/{session-id}/.process/test-context-package.json`
+   - Output directory paths
+
+2. **Provide Metadata** (simple values):
+   - `session_id`: WFS-{session-id}
+   - `workflow_type`: "tdd"
+   - `mcp_capabilities`: {exa_code, exa_web, code_index}
+
+3. **Pass userConfig** from Phase 0
+
+**Agent Context Package** (Agent loads autonomously):
+```javascript
+{
+  "session_id": "WFS-[session-id]",
+  "workflow_type": "tdd",
+
+  // Core (ALWAYS load)
+  "session_metadata": {
+    // If in memory: use cached content
+    // Else: Load from workflow-session.json
+  },
+  "context_package": {
+    // If in memory: use cached content
+    // Else: Load from context-package.json
+  },
+
+  // Selective (load based on progressive strategy)
+  "brainstorm_artifacts": {
+    // Loaded from context-package.json → brainstorm_artifacts section
+    "synthesis_output": {"path": "...", "exists": true},  // Load if exists (highest priority)
+    "guidance_specification": {"path": "...", "exists": true},  // Load if no synthesis
+    "role_analyses": [  // Load SELECTIVELY based on task relevance
+      {
+        "role": "system-architect",
+        "files": [{"path": "...", "type": "primary|supplementary"}]
+      }
+    ]
+  },
+
+  // On-Demand (load if exists)
+  "test_context_package": {
+    // Load from test-context-package.json
+    // Contains existing test patterns and coverage analysis
+  },
+  "conflict_resolution": {
+    // Load from conflict-resolution.json if conflict_risk >= medium
+    // Check context-package.conflict_detection.resolution_file
+  },
+
+  // Capabilities
+  "mcp_capabilities": {
+    "exa_code": true,
+    "exa_web": true,
+    "code_index": true
+  },
+
+  // User configuration from Phase 0
+  "user_config": {
+    // From Phase 0 AskUserQuestion
+  }
+}
+```
+
+**Discovery Actions**:
+1. **Load Session Context** (if not in memory)
+   ```javascript
+   if (!memory.has("workflow-session.json")) {
+     Read(.workflow/active/{session-id}/workflow-session.json)
+   }
+   ```
+
+2. **Load Context Package** (if not in memory)
+   ```javascript
+   if (!memory.has("context-package.json")) {
+     Read(.workflow/active/{session-id}/.process/context-package.json)
+   }
+   ```
+
+3. **Load Test Context Package** (if not in memory)
+   ```javascript
+   if (!memory.has("test-context-package.json")) {
+     Read(.workflow/active/{session-id}/.process/test-context-package.json)
+   }
+   ```
+
+4. **Extract & Load Role Analyses** (from context-package.json)
+   ```javascript
+   // Extract role analysis paths from context package
+   const roleAnalysisPaths = contextPackage.brainstorm_artifacts.role_analyses
+     .flatMap(role => role.files.map(f => f.path));
+
+   // Load each role analysis file
+   roleAnalysisPaths.forEach(path => Read(path));
+   ```
+
+5. **Load Conflict Resolution** (from conflict-resolution.json, if exists)
+   ```javascript
+   // Check for new conflict-resolution.json format
+   if (contextPackage.conflict_detection?.resolution_file) {
+     Read(contextPackage.conflict_detection.resolution_file)  // .process/conflict-resolution.json
+   }
+   // Fallback: legacy brainstorm_artifacts path
+   else if (contextPackage.brainstorm_artifacts?.conflict_resolution?.exists) {
+     Read(contextPackage.brainstorm_artifacts.conflict_resolution.path)
+   }
+   ```
+
+6. **Code Analysis with Native Tools** (optional - enhance understanding)
+   ```bash
+   # Find relevant test files and patterns
+   find . -name "*test*" -type f
+   rg "describe|it\(|test\(" -g "*.ts"
+   ```
+
+7. **MCP External Research** (optional - gather TDD best practices)
+   ```javascript
+   // Get external TDD examples and patterns
+   mcp__exa__get_code_context_exa(
+     query="TypeScript TDD best practices Red-Green-Refactor",
+     tokensNum="dynamic"
+   )
+   ```
+
+### Phase 2: Agent Execution (TDD Document Generation)
+
+**Purpose**: Generate TDD planning documents (IMPL_PLAN.md, task JSONs, TODO_LIST.md) - planning only, NOT code implementation.
+
+**Agent Invocation**:
+```javascript
+Task(
+  subagent_type="action-planning-agent",
+  run_in_background=false,
+  description="Generate TDD planning documents (IMPL_PLAN.md, task JSONs, TODO_LIST.md)",
+  prompt=`
+## TASK OBJECTIVE
+Generate TDD implementation planning documents (IMPL_PLAN.md, task JSONs, TODO_LIST.md) for workflow session
+
+IMPORTANT: This is PLANNING ONLY - you are generating planning documents, NOT implementing code.
+
+CRITICAL: Follow the progressive loading strategy (load analysis.md files incrementally due to file size):
+- **Core**: session metadata + context-package.json (always)
+- **Selective**: synthesis_output OR (guidance + relevant role analyses) - NOT all
+- **On-Demand**: conflict resolution (if conflict_risk >= medium), test context
+
+## SESSION PATHS
+Input:
+  - Session Metadata: .workflow/active/{session-id}/workflow-session.json
+  - Context Package: .workflow/active/{session-id}/.process/context-package.json
+  - Test Context: .workflow/active/{session-id}/.process/test-context-package.json
+
+Output:
+  - Task Dir: .workflow/active/{session-id}/.task/
+  - IMPL_PLAN: .workflow/active/{session-id}/IMPL_PLAN.md
+  - TODO_LIST: .workflow/active/{session-id}/TODO_LIST.md
+
+## CONTEXT METADATA
+Session ID: {session-id}
+Workflow Type: TDD
+MCP Capabilities: {exa_code, exa_web, code_index}
+
+## USER CONFIGURATION (from Phase 0)
+Execution Method: ${userConfig.executionMethod}  // agent|hybrid|cli
+Preferred CLI Tool: ${userConfig.preferredCliTool}  // codex|gemini|qwen|auto
+Supplementary Materials: ${userConfig.supplementaryMaterials}
+
+## EXECUTION METHOD MAPPING
+Based on userConfig.executionMethod, set task-level meta.execution_config:
+
+"agent" →
+  meta.execution_config = { method: "agent", cli_tool: null, enable_resume: false }
+  Agent executes Red-Green-Refactor phases directly
+
+"cli" →
+  meta.execution_config = { method: "cli", cli_tool: userConfig.preferredCliTool, enable_resume: true }
+  Agent executes pre_analysis, then hands off full context to CLI via buildCliHandoffPrompt()
+
+"hybrid" →
+  Per-task decision: Analyze TDD cycle complexity, set method to "agent" OR "cli" per task
+  - Simple cycles (<=5 test cases, <=3 files) → method: "agent"
+  - Complex cycles (>5 test cases, >3 files, integration tests) → method: "cli"
+  CLI tool: userConfig.preferredCliTool, enable_resume: true
+
+IMPORTANT: Do NOT add command field to implementation_approach steps. Execution routing is controlled by task-level meta.execution_config.method only.
+
+## EXPLORATION CONTEXT (from context-package.exploration_results)
+- Load exploration_results from context-package.json
+- Use aggregated_insights.critical_files for focus_paths generation
+- Apply aggregated_insights.constraints to acceptance criteria
+- Reference aggregated_insights.all_patterns for implementation approach
+- Use aggregated_insights.all_integration_points for precise modification locations
+- Use conflict_indicators for risk-aware task sequencing
+
+## CONFLICT RESOLUTION CONTEXT (if exists)
+- Check context-package.conflict_detection.resolution_file for conflict-resolution.json path
+- If exists, load .process/conflict-resolution.json:
+  - Apply planning_constraints as task constraints (for brainstorm-less workflows)
+  - Reference resolved_conflicts for implementation approach alignment
+  - Handle custom_conflicts with explicit task notes
+
+## TEST CONTEXT INTEGRATION
+- Load test-context-package.json for existing test patterns and coverage analysis
+- Extract test framework configuration (Jest/Pytest/etc.)
+- Identify existing test conventions and patterns
+- Map coverage gaps to TDD Red phase test targets
+
+## TDD DOCUMENT GENERATION TASK
+
+**Agent Configuration Reference**: All TDD task generation rules, quantification requirements, Red-Green-Refactor cycle structure, quality standards, and execution details are defined in action-planning-agent.
+
+### TDD-Specific Requirements Summary
+
+#### Task Structure Philosophy
+- **1 feature = 1 task** containing complete TDD cycle internally
+- Each task executes Red-Green-Refactor phases sequentially
+- Task count = Feature count (typically 5 features = 5 tasks)
+- Subtasks only when complexity >2500 lines or >6 files per cycle
+- **Maximum 18 tasks** (hard limit for TDD workflows)
+
+#### TDD Cycle Mapping
+- **Simple features**: IMPL-N with internal Red-Green-Refactor phases
+- **Complex features**: IMPL-N (container) + IMPL-N.M (subtasks)
+- Each cycle includes: test_count, test_cases array, implementation_scope, expected_coverage
+
+#### Required Outputs Summary
+
+##### 1. TDD Task JSON Files (.task/IMPL-*.json)
+- **Location**: \`.workflow/active/{session-id}/.task/\`
+- **Schema**: 6-field structure with TDD-specific metadata
+  - \`id, title, status, context_package_path, meta, context, flow_control\`
+  - \`meta.tdd_workflow\`: true (REQUIRED)
+  - \`meta.max_iterations\`: 3 (Green phase test-fix cycle limit)
+  - \`meta.cli_execution_id\`: Unique CLI execution ID (format: \`{session_id}-{task_id}\`)
+  - \`meta.cli_execution\`: Strategy object (new|resume|fork|merge_fork)
+  - \`context.tdd_cycles\`: Array with quantified test cases and coverage
+  - \`context.focus_paths\`: Absolute or clear relative paths (enhanced with exploration critical_files)
+  - \`flow_control.implementation_approach\`: Exactly 3 steps with \`tdd_phase\` field
+    1. Red Phase (\`tdd_phase: "red"\`): Write failing tests
+    2. Green Phase (\`tdd_phase: "green"\`): Implement to pass tests
+    3. Refactor Phase (\`tdd_phase: "refactor"\`): Improve code quality
+  - \`flow_control.pre_analysis\`: Include exploration integration_points analysis
+  - **meta.execution_config**: Set per userConfig.executionMethod (agent/cli/hybrid)
+- **Details**: See action-planning-agent.md § TDD Task JSON Generation
+
+##### 2. IMPL_PLAN.md (TDD Variant)
+- **Location**: \`.workflow/active/{session-id}/IMPL_PLAN.md\`
+- **Template**: \`~/.claude/workflows/cli-templates/prompts/workflow/impl-plan-template.txt\`
+- **TDD-Specific Frontmatter**: workflow_type="tdd", tdd_workflow=true, feature_count, task_breakdown
+- **TDD Implementation Tasks Section**: Feature-by-feature with internal Red-Green-Refactor cycles
+- **Context Analysis**: Artifact references and exploration insights
+- **Details**: See action-planning-agent.md § TDD Implementation Plan Creation
+
+##### 3. TODO_LIST.md
+- **Location**: \`.workflow/active/{session-id}/TODO_LIST.md\`
+- **Format**: Hierarchical task list with internal TDD phase indicators (Red → Green → Refactor)
+- **Status**: ▸ (container), [ ] (pending), [x] (completed)
+- **Links**: Task JSON references and summaries
+- **Details**: See action-planning-agent.md § TODO List Generation
+
+### CLI EXECUTION ID REQUIREMENTS (MANDATORY)
+
+Each task JSON MUST include:
+- **meta.cli_execution_id**: Unique ID for CLI execution (format: \`{session_id}-{task_id}\`)
+- **meta.cli_execution**: Strategy object based on depends_on:
+  - No deps → \`{ "strategy": "new" }\`
+  - 1 dep (single child) → \`{ "strategy": "resume", "resume_from": "parent-cli-id" }\`
+  - 1 dep (multiple children) → \`{ "strategy": "fork", "resume_from": "parent-cli-id" }\`
+  - N deps → \`{ "strategy": "merge_fork", "resume_from": ["id1", "id2", ...] }\`
+  - **Type**: \`resume_from: string | string[]\` (string for resume/fork, array for merge_fork)
+
+**CLI Execution Strategy Rules**:
+1. **new**: Task has no dependencies - starts fresh CLI conversation
+2. **resume**: Task has 1 parent AND that parent has only this child - continues same conversation
+3. **fork**: Task has 1 parent BUT parent has multiple children - creates new branch with parent context
+4. **merge_fork**: Task has multiple parents - merges all parent contexts into new conversation
+
+**Execution Command Patterns**:
+- new: \`ccw cli -p "[prompt]" --tool [tool] --mode write --id [cli_execution_id]\`
+- resume: \`ccw cli -p "[prompt]" --resume [resume_from] --tool [tool] --mode write\`
+- fork: \`ccw cli -p "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write\`
+- merge_fork: \`ccw cli -p "[prompt]" --resume [resume_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write\` (resume_from is array)
+
+### Quantification Requirements (MANDATORY)
+
+**Core Rules**:
+1. **Explicit Test Case Counts**: Red phase specifies exact number with enumerated list
+2. **Quantified Coverage**: Acceptance includes measurable percentage (e.g., ">=85%")
+3. **Detailed Implementation Scope**: Green phase enumerates files, functions, line counts
+4. **Enumerated Refactoring Targets**: Refactor phase lists specific improvements with counts
+
+**TDD Phase Formats**:
+- **Red Phase**: "Write N test cases: [test1, test2, ...]"
+- **Green Phase**: "Implement N functions in file lines X-Y: [func1() X1-Y1, func2() X2-Y2, ...]"
+- **Refactor Phase**: "Apply N refactorings: [improvement1 (details), improvement2 (details), ...]"
+- **Acceptance**: "All N tests pass with >=X% coverage: verify by [test command]"
+
+**Validation Checklist**:
+- [ ] Every Red phase specifies exact test case count with enumerated list
+- [ ] Every Green phase enumerates files, functions, and estimated line counts
+- [ ] Every Refactor phase lists specific improvements with counts
+- [ ] Every acceptance criterion includes measurable coverage percentage
+- [ ] tdd_cycles array contains test_count and test_cases for each cycle
+- [ ] No vague language ("comprehensive", "complete", "thorough")
+- [ ] cli_execution_id and cli_execution strategy assigned to each task
+
+### Agent Execution Summary
+
+**Key Steps** (Detailed instructions in action-planning-agent.md):
+1. Load task JSON template from provided path
+2. Extract and decompose features with TDD cycles
+3. Generate TDD task JSON files enforcing quantification requirements
+4. Create IMPL_PLAN.md using TDD template variant
+5. Generate TODO_LIST.md with TDD phase indicators
+6. Update session state with TDD metadata
+
+**Quality Gates** (Full checklist in action-planning-agent.md):
+- Task count <=18 (hard limit)
+- Each task has meta.tdd_workflow: true
+- Each task has exactly 3 implementation steps with tdd_phase field ("red", "green", "refactor")
+- Each task has meta.cli_execution_id and meta.cli_execution strategy
+- Green phase includes test-fix cycle logic with max_iterations
+- focus_paths are absolute or clear relative paths (from exploration critical_files)
+- Artifact references mapped correctly from context package
+- Exploration context integrated (critical_files, constraints, patterns, integration_points)
+- Conflict resolution context applied (if conflict_risk >= medium)
+- Test context integrated (existing test patterns and coverage analysis)
+- Documents follow TDD template structure
+- CLI tool selection based on userConfig.executionMethod
+- Quantification requirements enforced (explicit counts, measurable acceptance, exact targets)
+
+## SUCCESS CRITERIA
+- All planning documents generated successfully:
+  - Task JSONs valid and saved to .task/ directory with cli_execution_id
+  - IMPL_PLAN.md created with complete TDD structure
+  - TODO_LIST.md generated matching task JSONs
+- CLI execution strategies assigned based on task dependencies
+- Return completion status with document count and task breakdown summary
+
+## OUTPUT SUMMARY
+Generate all three documents and report:
+- TDD task JSON files created: N files (IMPL-*.json) with cli_execution_id assigned
+- TDD cycles configured: N cycles with quantified test cases
+- CLI execution strategies: new/resume/fork/merge_fork assigned per dependency graph
+- Artifacts integrated: synthesis-spec/guidance-specification, relevant role analyses
+- Exploration context: critical_files, constraints, patterns, integration_points
+- Test context integrated: existing patterns and coverage
+- Conflict resolution: applied (if conflict_risk >= medium)
+- Session ready for TDD execution
+`
+)
+```
+
+### Agent Context Passing
+
+**Context Delegation Model**: Command provides paths and metadata, agent loads context autonomously using progressive loading strategy.
+
+**Command Provides** (in agent prompt):
+```javascript
+// Command assembles these simple values and paths for agent
+const commandProvides = {
+  // Session paths
+  session_metadata_path: ".workflow/active/WFS-{id}/workflow-session.json",
+  context_package_path: ".workflow/active/WFS-{id}/.process/context-package.json",
+  test_context_package_path: ".workflow/active/WFS-{id}/.process/test-context-package.json",
+  output_task_dir: ".workflow/active/WFS-{id}/.task/",
+  output_impl_plan: ".workflow/active/WFS-{id}/IMPL_PLAN.md",
+  output_todo_list: ".workflow/active/WFS-{id}/TODO_LIST.md",
+
+  // Simple metadata
+  session_id: "WFS-{id}",
+  workflow_type: "tdd",
+  mcp_capabilities: { exa_code: true, exa_web: true, code_index: true },
+
+  // User configuration from Phase 0
+  user_config: {
+    supplementaryMaterials: { type: "...", content: [...] },
+    executionMethod: "agent|hybrid|cli",
+    preferredCliTool: "codex|gemini|qwen|auto",
+    enableResume: true
+  }
+}
+```
+
+**Agent Loads Autonomously** (progressive loading):
+```javascript
+// Agent executes progressive loading based on memory state
+const agentLoads = {
+  // Core (ALWAYS load if not in memory)
+  session_metadata: loadIfNotInMemory(session_metadata_path),
+  context_package: loadIfNotInMemory(context_package_path),
+
+  // Selective (based on progressive strategy)
+  // Priority: synthesis_output > guidance + relevant_role_analyses
+  brainstorm_content: loadSelectiveBrainstormArtifacts(context_package),
+
+  // On-Demand (load if exists and relevant)
+  test_context: loadIfExists(test_context_package_path),
+  conflict_resolution: loadConflictResolution(context_package),
+
+  // Optional (if MCP available)
+  exploration_results: extractExplorationResults(context_package),
+  external_research: executeMcpResearch()  // If needed
+}
+```
+
+**Progressive Loading Implementation** (agent responsibility):
+1. **Check memory first** - skip if already loaded
+2. **Load core files** - session metadata + context-package.json
+3. **Smart selective loading** - synthesis_output OR (guidance + task-relevant role analyses)
+4. **On-demand loading** - test context, conflict resolution (if conflict_risk >= medium)
+5. **Extract references** - exploration results, artifact paths from context package
+
+## TDD Task Structure Reference
+
+This section provides quick reference for TDD task JSON structure. For complete implementation details, see the agent invocation prompt in Phase 2 above.
+
+**Quick Reference**:
+- Each TDD task contains complete Red-Green-Refactor cycle
+- Task ID format: `IMPL-N` (simple) or `IMPL-N.M` (complex subtasks)
+- Required metadata:
+  - `meta.tdd_workflow: true`
+  - `meta.max_iterations: 3`
+  - `meta.cli_execution_id: "{session_id}-{task_id}"`
+  - `meta.cli_execution: { "strategy": "new|resume|fork|merge_fork", ... }`
+- Context: `tdd_cycles` array with quantified test cases and coverage:
+  ```javascript
+  tdd_cycles: [
+    {
+      test_count: 5,                    // Number of test cases to write
+      test_cases: ["case1", "case2"],   // Enumerated test scenarios
+      implementation_scope: "...",      // Files and functions to implement
+      expected_coverage: ">=85%"        // Coverage target
+    }
+  ]
+  ```
+- Context: `focus_paths` use absolute or clear relative paths
+- Flow control: Exactly 3 steps with `tdd_phase` field ("red", "green", "refactor")
+- Flow control: `pre_analysis` includes exploration integration_points analysis
+- **meta.execution_config**: Set per `userConfig.executionMethod` (agent/cli/hybrid)
+- See Phase 2 agent prompt for full schema and requirements
+
+## Output Files Structure
+```
+.workflow/active/{session-id}/
+├── IMPL_PLAN.md                     # Unified plan with TDD Implementation Tasks section
+├── TODO_LIST.md                     # Progress tracking with internal TDD phase indicators
+├── .task/
+│   ├── IMPL-1.json                  # Complete TDD task (Red-Green-Refactor internally)
+│   ├── IMPL-2.json                  # Complete TDD task
+│   ├── IMPL-3.json                  # Complex feature container (if needed)
+│   ├── IMPL-3.1.json                # Complex feature subtask (if needed)
+│   ├── IMPL-3.2.json                # Complex feature subtask (if needed)
+│   └── ...
+└── .process/
+    ├── conflict-resolution.json     # Conflict resolution results (if conflict_risk >= medium)
+    ├── test-context-package.json    # Test coverage analysis
+    ├── context-package.json         # Input from context-gather
+    ├── context_package_path         # Path to smart context package
+    └── green-fix-iteration-*.md     # Fix logs from Green phase test-fix cycles
+```
+
+**File Count**:
+- **Old approach**: 5 features = 15 task JSON files (TEST/IMPL/REFACTOR x 5)
+- **New approach**: 5 features = 5 task JSON files (IMPL-N x 5)
+- **Complex feature**: 1 feature = 1 container + M subtasks (IMPL-N + IMPL-N.M)
+
+## Validation Rules
+
+### Task Completeness
+- Every IMPL-N must contain complete TDD workflow in `flow_control.implementation_approach`
+- Each task must have 3 steps with `tdd_phase`: "red", "green", "refactor"
+- Every task must have `meta.tdd_workflow: true`
+
+### Dependency Enforcement
+- Sequential features: IMPL-N depends_on ["IMPL-(N-1)"] if needed
+- Complex feature subtasks: IMPL-N.M depends_on ["IMPL-N.(M-1)"] or parent dependencies
+- No circular dependencies allowed
+
+### Task Limits
+- Maximum 18 total tasks (simple + subtasks) - hard limit for TDD workflows
+- Flat hierarchy (<=5 tasks) or two-level (6-18 tasks with containers)
+- Re-scope requirements if >18 tasks needed
+
+### TDD Workflow Validation
+- `meta.tdd_workflow` must be true
+- `flow_control.implementation_approach` must have exactly 3 steps
+- Each step must have `tdd_phase` field ("red", "green", or "refactor")
+- Green phase step must include test-fix cycle logic
+- `meta.max_iterations` must be present (default: 3)
+
+## Error Handling
+
+### Input Validation Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Session not found | Invalid session ID | Verify session exists |
+| Context missing | Incomplete planning | Run context-gather first |
+
+### TDD Generation Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Task count exceeds 18 | Too many features or subtasks | Re-scope requirements or merge features into multiple TDD sessions |
+| Missing test framework | No test config | Configure testing first |
+| Invalid TDD workflow | Missing tdd_phase or incomplete flow_control | Fix TDD structure in ANALYSIS_RESULTS.md |
+| Missing tdd_workflow flag | Task doesn't have meta.tdd_workflow: true | Add TDD workflow metadata |
+
+## Integration
+
+**Called By**: SKILL.md (Phase 5: TDD Task Generation)
+**Invokes**: `action-planning-agent` for autonomous task generation
+**Followed By**: Phase 6 (TDD Structure Validation in SKILL.md), then workflow:execute (external)
+
+**CLI Tool Selection**: Determined semantically from user's task description. Include "use Codex/Gemini/Qwen" in your request for CLI execution.
+
+**Output**:
+- TDD task JSON files in `.task/` directory (IMPL-N.json format)
+- IMPL_PLAN.md with TDD Implementation Tasks section
+- TODO_LIST.md with internal TDD phase indicators
+- Session state updated with task count and TDD metadata
+- MCP enhancements integrated (if available)
+
+## Test Coverage Analysis Integration
+
+The TDD workflow includes test coverage analysis (via phases/01-test-context-gather.md) to:
+- Detect existing test patterns and conventions
+- Identify current test coverage gaps
+- Discover test framework and configuration
+- Enable integration with existing tests
+
+This makes TDD workflow context-aware instead of assuming greenfield scenarios.
+
+## Iterative Green Phase with Test-Fix Cycle
+
+IMPL (Green phase) tasks include automatic test-fix cycle:
+
+**Process Flow**:
+1. **Initial Implementation**: Write minimal code to pass tests
+2. **Test Execution**: Run test suite
+3. **Success Path**: Tests pass → Complete task
+4. **Failure Path**: Tests fail → Enter iterative fix cycle:
+   - **Gemini Diagnosis**: Analyze failures with bug-fix template
+   - **Fix Application**: Agent executes fixes directly
+   - **Retest**: Verify fix resolves failures
+   - **Repeat**: Up to max_iterations (default: 3)
+5. **Safety Net**: Auto-revert all changes if max iterations reached
+
+## Configuration Options
+- **meta.max_iterations**: Number of fix attempts in Green phase (default: 3)
+- **meta.execution_config.method**: Execution routing (agent/cli) determined from userConfig.executionMethod
+
+---
+
+## Post-Phase Update
+
+After Phase 2 (TDD Task Generation) completes:
+- **Output Created**: IMPL_PLAN.md, TODO_LIST.md, IMPL-*.json task files in `.task/` directory
+- **TDD Structure**: Each task contains complete Red-Green-Refactor cycle internally
+- **CLI Execution IDs**: All tasks assigned unique cli_execution_id for resume support
+- **Next Action**: Phase 6 (TDD Structure Validation) in SKILL.md
+- **TodoWrite**: Collapse Phase 5 sub-tasks to "Phase 5: TDD Task Generation: completed"
--- a/.claude/skills/workflow-tdd-plan/phases/03-tdd-verify.md
+++ b/.claude/skills/workflow-tdd-plan/phases/03-tdd-verify.md
@@ -0,0 +1,575 @@
+# Phase 3: TDD Verify
+
+## Goal
+
+Verify TDD workflow execution quality by validating Red-Green-Refactor cycle compliance, test coverage completeness, and task chain structure integrity. This phase orchestrates multiple analysis steps and generates a comprehensive compliance report with quality gate recommendation.
+
+**Output**: A structured Markdown report saved to `.workflow/active/WFS-{session}/TDD_COMPLIANCE_REPORT.md` containing:
+- Executive summary with compliance score and quality gate recommendation
+- Task chain validation (TEST → IMPL → REFACTOR structure)
+- Test coverage metrics (line, branch, function)
+- Red-Green-Refactor cycle verification
+- Best practices adherence assessment
+- Actionable improvement recommendations
+
+## Operating Constraints
+
+**ORCHESTRATOR MODE**:
+- This phase coordinates coverage analysis (`phases/04-tdd-coverage-analysis.md`) and internal validation
+- MAY write output files: TDD_COMPLIANCE_REPORT.md (primary report), .process/*.json (intermediate artifacts)
+- MUST NOT modify source task files or implementation code
+- MUST NOT create or delete tasks in the workflow
+
+**Quality Gate Authority**: The compliance report provides a binding recommendation (BLOCK_MERGE / REQUIRE_FIXES / PROCEED_WITH_CAVEATS / APPROVED) based on objective compliance criteria.
+
+## Core Responsibilities
+- Verify TDD task chain structure (TEST → IMPL → REFACTOR)
+- Analyze test coverage metrics
+- Validate TDD cycle execution quality
+- Generate compliance report with quality gate recommendation
+
+## Execution Process
+
+```
+Input Parsing:
+   └─ Decision (session argument):
+      ├─ --session provided → Use provided session
+      └─ No session → Auto-detect active session
+
+Phase 1: Session Discovery & Validation
+   ├─ Detect or validate session directory
+   ├─ Check required artifacts exist (.task/*.json, .summaries/*)
+   └─ ERROR if invalid or incomplete
+
+Phase 2: Task Chain Structure Validation
+   ├─ Load all task JSONs from .task/
+   ├─ Validate TDD structure: TEST-N.M → IMPL-N.M → REFACTOR-N.M
+   ├─ Verify dependencies (depends_on)
+   ├─ Validate meta fields (tdd_phase, agent)
+   └─ Extract chain validation data
+
+Phase 3: Coverage & Cycle Analysis
+   ├─ Read and execute: phases/04-tdd-coverage-analysis.md
+   ├─ Parse: test-results.json, coverage-report.json, tdd-cycle-report.md
+   └─ Extract coverage metrics and TDD cycle verification
+
+Phase 4: Compliance Report Generation
+   ├─ Aggregate findings from Phases 1-3
+   ├─ Calculate compliance score (0-100)
+   ├─ Determine quality gate recommendation
+   ├─ Generate TDD_COMPLIANCE_REPORT.md
+   └─ Display summary to user
+```
+
+## 4-Phase Execution
+
+### Phase 1: Session Discovery & Validation
+
+**Step 1.1: Detect Session**
+```bash
+IF --session parameter provided:
+    session_id = provided session
+ELSE:
+    # Auto-detect active session
+    active_sessions = bash(find .workflow/active/ -name "WFS-*" -type d 2>/dev/null)
+    IF active_sessions is empty:
+        ERROR: "No active workflow session found. Use --session <session-id>"
+        EXIT
+    ELSE IF active_sessions has multiple entries:
+        # Use most recently modified session
+        session_id = bash(ls -td .workflow/active/WFS-*/ 2>/dev/null | head -1 | xargs basename)
+    ELSE:
+        session_id = basename(active_sessions[0])
+
+# Derive paths
+session_dir = .workflow/active/WFS-{session_id}
+task_dir = session_dir/.task
+summaries_dir = session_dir/.summaries
+process_dir = session_dir/.process
+```
+
+**Step 1.2: Validate Required Artifacts**
+```bash
+# Check task files exist
+task_files = Glob(task_dir/*.json)
+IF task_files.count == 0:
+    ERROR: "No task JSON files found. Run TDD planning (SKILL.md) first"
+    EXIT
+
+# Check summaries exist (optional but recommended for full analysis)
+summaries_exist = EXISTS(summaries_dir)
+IF NOT summaries_exist:
+    WARNING: "No .summaries/ directory found. Some analysis may be limited."
+```
+
+**Output**: session_id, session_dir, task_files list
+
+---
+
+### Phase 2: Task Chain Structure Validation
+
+**Step 2.1: Load and Parse Task JSONs**
+```bash
+# Single-pass JSON extraction using jq
+validation_data = bash("""
+# Load all tasks and extract structured data
+cd '{session_dir}/.task'
+
+# Extract all task IDs
+task_ids=$(jq -r '.id' *.json 2>/dev/null | sort)
+
+# Extract dependencies for IMPL tasks
+impl_deps=$(jq -r 'select(.id | startswith("IMPL")) | .id + ":" + (.context.depends_on[]? // "none")' *.json 2>/dev/null)
+
+# Extract dependencies for REFACTOR tasks
+refactor_deps=$(jq -r 'select(.id | startswith("REFACTOR")) | .id + ":" + (.context.depends_on[]? // "none")' *.json 2>/dev/null)
+
+# Extract meta fields
+meta_tdd=$(jq -r '.id + ":" + (.meta.tdd_phase // "missing")' *.json 2>/dev/null)
+meta_agent=$(jq -r '.id + ":" + (.meta.agent // "missing")' *.json 2>/dev/null)
+
+# Output as JSON
+jq -n --arg ids "$task_ids" \
+       --arg impl "$impl_deps" \
+       --arg refactor "$refactor_deps" \
+       --arg tdd "$meta_tdd" \
+       --arg agent "$meta_agent" \
+       '{ids: $ids, impl_deps: $impl, refactor_deps: $refactor, tdd: $tdd, agent: $agent}'
+""")
+```
+
+**Step 2.2: Validate TDD Chain Structure**
+```
+Parse validation_data JSON and validate:
+
+For each feature N (extracted from task IDs):
+   1. TEST-N.M exists?
+   2. IMPL-N.M exists?
+   3. REFACTOR-N.M exists? (optional but recommended)
+   4. IMPL-N.M.context.depends_on contains TEST-N.M?
+   5. REFACTOR-N.M.context.depends_on contains IMPL-N.M?
+   6. TEST-N.M.meta.tdd_phase == "red"?
+   7. TEST-N.M.meta.agent == "@code-review-test-agent"?
+   8. IMPL-N.M.meta.tdd_phase == "green"?
+   9. IMPL-N.M.meta.agent == "@code-developer"?
+   10. REFACTOR-N.M.meta.tdd_phase == "refactor"?
+
+Calculate:
+- chain_completeness_score = (complete_chains / total_chains) * 100
+- dependency_accuracy = (correct_deps / total_deps) * 100
+- meta_field_accuracy = (correct_meta / total_meta) * 100
+```
+
+**Output**: chain_validation_report (JSON structure with validation results)
+
+---
+
+### Phase 3: Coverage & Cycle Analysis
+
+**Step 3.1: Call Coverage Analysis Phase**
+
+Read and execute the coverage analysis phase:
+- **Phase file**: `phases/04-tdd-coverage-analysis.md`
+- **Args**: `--session {session_id}`
+
+**Step 3.2: Parse Output Files**
+```bash
+# Check required outputs exist
+IF NOT EXISTS(process_dir/test-results.json):
+    WARNING: "test-results.json not found. Coverage analysis incomplete."
+    coverage_data = null
+ELSE:
+    coverage_data = Read(process_dir/test-results.json)
+
+IF NOT EXISTS(process_dir/coverage-report.json):
+    WARNING: "coverage-report.json not found. Coverage metrics incomplete."
+    metrics = null
+ELSE:
+    metrics = Read(process_dir/coverage-report.json)
+
+IF NOT EXISTS(process_dir/tdd-cycle-report.md):
+    WARNING: "tdd-cycle-report.md not found. Cycle validation incomplete."
+    cycle_data = null
+ELSE:
+    cycle_data = Read(process_dir/tdd-cycle-report.md)
+```
+
+**Step 3.3: Extract Coverage Metrics**
+```
+If coverage_data exists:
+   - line_coverage_percent
+   - branch_coverage_percent
+   - function_coverage_percent
+   - uncovered_files (list)
+   - uncovered_lines (map: file -> line ranges)
+
+If cycle_data exists:
+   - red_phase_compliance (tests failed initially?)
+   - green_phase_compliance (tests pass after impl?)
+   - refactor_phase_compliance (tests stay green during refactor?)
+   - minimal_implementation_score (was impl minimal?)
+```
+
+**Output**: coverage_analysis, cycle_analysis
+
+---
+
+### Phase 4: Compliance Report Generation
+
+**Step 4.1: Calculate Compliance Score**
+```
+Base Score: 100 points
+
+Deductions:
+Chain Structure:
+   - Missing TEST task: -30 points per feature
+   - Missing IMPL task: -30 points per feature
+   - Missing REFACTOR task: -10 points per feature
+   - Wrong dependency: -15 points per error
+   - Wrong agent: -5 points per error
+   - Wrong tdd_phase: -5 points per error
+
+TDD Cycle Compliance:
+   - Test didn't fail initially: -10 points per feature
+   - Tests didn't pass after IMPL: -20 points per feature
+   - Tests broke during REFACTOR: -15 points per feature
+   - Over-engineered IMPL: -10 points per feature
+
+Coverage Quality:
+   - Line coverage < 80%: -5 points
+   - Branch coverage < 70%: -5 points
+   - Function coverage < 80%: -5 points
+   - Critical paths uncovered: -10 points
+
+Final Score: Max(0, Base Score - Total Deductions)
+```
+
+**Step 4.2: Determine Quality Gate**
+```
+IF score >= 90 AND no_critical_violations:
+    recommendation = "APPROVED"
+ELSE IF score >= 70 AND critical_violations == 0:
+    recommendation = "PROCEED_WITH_CAVEATS"
+ELSE IF score >= 50:
+    recommendation = "REQUIRE_FIXES"
+ELSE:
+    recommendation = "BLOCK_MERGE"
+```
+
+**Step 4.3: Generate Report**
+```bash
+report_content = Generate markdown report (see structure below)
+report_path = "{session_dir}/TDD_COMPLIANCE_REPORT.md"
+Write(report_path, report_content)
+```
+
+**Step 4.4: Display Summary to User**
+```bash
+echo "=== TDD Verification Complete ==="
+echo "Session: {session_id}"
+echo "Report: {report_path}"
+echo ""
+echo "Quality Gate: {recommendation}"
+echo "Compliance Score: {score}/100"
+echo ""
+echo "Chain Validation: {chain_completeness_score}%"
+echo "Line Coverage: {line_coverage}%"
+echo "Branch Coverage: {branch_coverage}%"
+echo ""
+echo "Next: Review full report for detailed findings"
+```
+
+## TodoWrite Pattern (Optional)
+
+**Note**: As an orchestrator phase, TodoWrite tracking is optional and primarily useful for long-running verification processes. For most cases, the 4-phase execution is fast enough that progress tracking adds noise without value.
+
+```javascript
+// Only use TodoWrite for complex multi-session verification
+// Skip for single-session verification
+```
+
+## Validation Logic
+
+### Chain Validation Algorithm
+```
+1. Load all task JSONs from .workflow/active/{sessionId}/.task/
+2. Extract task IDs and group by feature number
+3. For each feature:
+   - Check TEST-N.M exists
+   - Check IMPL-N.M exists
+   - Check REFACTOR-N.M exists (optional but recommended)
+   - Verify IMPL-N.M depends_on TEST-N.M
+   - Verify REFACTOR-N.M depends_on IMPL-N.M
+   - Verify meta.tdd_phase values
+   - Verify meta.agent assignments
+4. Calculate chain completeness score
+5. Report incomplete or invalid chains
+```
+
+### Quality Gate Criteria
+
+| Recommendation | Score Range | Critical Violations | Action |
+|----------------|-------------|---------------------|--------|
+| **APPROVED** | ≥90 | 0 | Safe to merge |
+| **PROCEED_WITH_CAVEATS** | ≥70 | 0 | Can proceed, address minor issues |
+| **REQUIRE_FIXES** | ≥50 | Any | Must fix before merge |
+| **BLOCK_MERGE** | <50 | Any | Block merge until resolved |
+
+**Critical Violations**:
+- Missing TEST or IMPL task for any feature
+- Tests didn't fail initially (Red phase violation)
+- Tests didn't pass after IMPL (Green phase violation)
+- Tests broke during REFACTOR (Refactor phase violation)
+
+## Output Files
+```
+.workflow/active/WFS-{session-id}/
+├── TDD_COMPLIANCE_REPORT.md     # Comprehensive compliance report
+└── .process/
+    ├── test-results.json         # From phases/04-tdd-coverage-analysis.md
+    ├── coverage-report.json      # From phases/04-tdd-coverage-analysis.md
+    └── tdd-cycle-report.md       # From phases/04-tdd-coverage-analysis.md
+```
+
+## Error Handling
+
+### Session Discovery Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| No active session | No WFS-* directories | Provide --session explicitly |
+| Multiple active sessions | Multiple WFS-* directories | Provide --session explicitly |
+| Session not found | Invalid session-id | Check available sessions |
+
+### Validation Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Task files missing | Incomplete planning | Run TDD planning (SKILL.md) first |
+| Invalid JSON | Corrupted task files | Regenerate tasks |
+| Missing summaries | Tasks not executed | Execute tasks before verify |
+
+### Analysis Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Coverage tool missing | No test framework | Configure testing first |
+| Tests fail to run | Code errors | Fix errors before verify |
+| Coverage analysis fails | phases/04-tdd-coverage-analysis.md error | Check analysis output |
+
+## Integration
+
+### Phase Chain
+- **Called After**: Task execution completes (all TDD tasks done)
+- **Calls**: `phases/04-tdd-coverage-analysis.md`
+- **Related Skills**: SKILL.md (orchestrator), `workflow-plan/` (session management)
+
+### When to Use
+- After completing all TDD tasks in a workflow
+- Before merging TDD workflow branch
+- For TDD process quality assessment
+- To identify missing TDD steps
+
+## TDD Compliance Report Structure
+
+```markdown
+# TDD Compliance Report - {Session ID}
+
+**Generated**: {timestamp}
+**Session**: WFS-{sessionId}
+**Workflow Type**: TDD
+
+---
+
+## Executive Summary
+
+### Quality Gate Decision
+
+| Metric | Value | Status |
+|--------|-------|--------|
+| Compliance Score | {score}/100 | {status_emoji} |
+| Chain Completeness | {percentage}% | {status} |
+| Line Coverage | {percentage}% | {status} |
+| Branch Coverage | {percentage}% | {status} |
+| Function Coverage | {percentage}% | {status} |
+
+### Recommendation
+
+**{RECOMMENDATION}**
+
+**Decision Rationale**:
+{brief explanation based on score and violations}
+
+**Quality Gate Criteria**:
+- **APPROVED**: Score ≥90, no critical violations
+- **PROCEED_WITH_CAVEATS**: Score ≥70, no critical violations
+- **REQUIRE_FIXES**: Score ≥50 or critical violations exist
+- **BLOCK_MERGE**: Score <50
+
+---
+
+## Chain Analysis
+
+### Feature 1: {Feature Name}
+**Status**: Complete
+**Chain**: TEST-1.1 → IMPL-1.1 → REFACTOR-1.1
+
+| Phase | Task | Status | Details |
+|-------|------|--------|---------|
+| Red | TEST-1.1 | Pass | Test created and failed with clear message |
+| Green | IMPL-1.1 | Pass | Minimal implementation made test pass |
+| Refactor | REFACTOR-1.1 | Pass | Code improved, tests remained green |
+
+### Feature 2: {Feature Name}
+**Status**: Incomplete
+**Chain**: TEST-2.1 → IMPL-2.1 (Missing REFACTOR-2.1)
+
+| Phase | Task | Status | Details |
+|-------|------|--------|---------|
+| Red | TEST-2.1 | Pass | Test created and failed |
+| Green | IMPL-2.1 | Warning | Implementation seems over-engineered |
+| Refactor | REFACTOR-2.1 | Missing | Task not completed |
+
+**Issues**:
+- REFACTOR-2.1 task not completed (-10 points)
+- IMPL-2.1 implementation exceeded minimal scope (-10 points)
+
+### Chain Validation Summary
+
+| Metric | Value |
+|--------|-------|
+| Total Features | {count} |
+| Complete Chains | {count} ({percent}%) |
+| Incomplete Chains | {count} |
+| Missing TEST | {count} |
+| Missing IMPL | {count} |
+| Missing REFACTOR | {count} |
+| Dependency Errors | {count} |
+| Meta Field Errors | {count} |
+
+---
+
+## Test Coverage Analysis
+
+### Coverage Metrics
+
+| Metric | Coverage | Target | Status |
+|--------|----------|--------|--------|
+| Line Coverage | {percentage}% | ≥80% | {status} |
+| Branch Coverage | {percentage}% | ≥70% | {status} |
+| Function Coverage | {percentage}% | ≥80% | {status} |
+
+### Coverage Gaps
+
+| File | Lines | Issue | Priority |
+|------|-------|-------|----------|
+| src/auth/service.ts | 45-52 | Uncovered error handling | HIGH |
+| src/utils/parser.ts | 78-85 | Uncovered edge case | MEDIUM |
+
+---
+
+## TDD Cycle Validation
+
+### Red Phase (Write Failing Test)
+- {N}/{total} features had failing tests initially ({percent}%)
+- Compliant features: {list}
+- Non-compliant features: {list}
+
+**Violations**:
+- Feature 3: No evidence of initial test failure (-10 points)
+
+### Green Phase (Make Test Pass)
+- {N}/{total} implementations made tests pass ({percent}%)
+- Compliant features: {list}
+- Non-compliant features: {list}
+
+**Violations**:
+- Feature 2: Implementation over-engineered (-10 points)
+
+### Refactor Phase (Improve Quality)
+- {N}/{total} features completed refactoring ({percent}%)
+- Compliant features: {list}
+- Non-compliant features: {list}
+
+**Violations**:
+- Feature 2, 4: Refactoring step skipped (-20 points total)
+
+---
+
+## Best Practices Assessment
+
+### Strengths
+- Clear test descriptions
+- Good test coverage
+- Consistent naming conventions
+- Well-structured code
+
+### Areas for Improvement
+- Some implementations over-engineered in Green phase
+- Missing refactoring steps
+- Test failure messages could be more descriptive
+
+---
+
+## Detailed Findings by Severity
+
+### Critical Issues ({count})
+{List of critical issues with impact and remediation}
+
+### High Priority Issues ({count})
+{List of high priority issues with impact and remediation}
+
+### Medium Priority Issues ({count})
+{List of medium priority issues with impact and remediation}
+
+### Low Priority Issues ({count})
+{List of low priority issues with impact and remediation}
+
+---
+
+## Recommendations
+
+### Required Fixes (Before Merge)
+1. Complete missing REFACTOR tasks (Features 2, 4)
+2. Verify initial test failures for Feature 3
+3. Fix tests that broke during refactoring
+
+### Recommended Improvements
+1. Simplify over-engineered implementations
+2. Add edge case tests for Features 1, 3
+3. Improve test failure message clarity
+4. Increase branch coverage to >85%
+
+### Optional Enhancements
+1. Add more descriptive test names
+2. Consider parameterized tests for similar scenarios
+3. Document TDD process learnings
+
+---
+
+## Metrics Summary
+
+| Metric | Value |
+|--------|-------|
+| Total Features | {count} |
+| Complete Chains | {count} ({percent}%) |
+| Compliance Score | {score}/100 |
+| Critical Issues | {count} |
+| High Issues | {count} |
+| Medium Issues | {count} |
+| Low Issues | {count} |
+| Line Coverage | {percent}% |
+| Branch Coverage | {percent}% |
+| Function Coverage | {percent}% |
+
+---
+
+**Report End**
+```
+
+---
+
+## Post-Phase Update
+
+After TDD Verify completes:
+- **Output Created**: `TDD_COMPLIANCE_REPORT.md` in session directory
+- **Data Produced**: Compliance score, quality gate recommendation, chain validation, coverage metrics
+- **Next Action**: Based on quality gate - APPROVED (merge), REQUIRE_FIXES (iterate), BLOCK_MERGE (rework)
+- **TodoWrite**: Mark "TDD Verify: completed" with quality gate result
--- a/.claude/skills/workflow-tdd-plan/phases/04-tdd-coverage-analysis.md
+++ b/.claude/skills/workflow-tdd-plan/phases/04-tdd-coverage-analysis.md
@@ -0,0 +1,287 @@
+# Phase 4: TDD Coverage Analysis
+
+## Overview
+Analyze test coverage and verify Red-Green-Refactor cycle execution for TDD workflow validation.
+
+## Core Responsibilities
+- Extract test files from TEST tasks
+- Run test suite with coverage
+- Parse coverage metrics
+- Verify TDD cycle execution (Red -> Green -> Refactor)
+- Generate coverage and cycle reports
+
+## Execution Process
+
+```
+Input Parsing:
+   ├─ Parse flags: --session
+   └─ Validation: session_id REQUIRED
+
+Phase 1: Extract Test Tasks
+   └─ Find TEST-*.json files and extract focus_paths
+
+Phase 2: Run Test Suite
+   └─ Decision (test framework):
+      ├─ Node.js → npm test --coverage --json
+      ├─ Python → pytest --cov --json-report
+      └─ Other → [test_command] --coverage --json
+
+Phase 3: Parse Coverage Data
+   ├─ Extract line coverage percentage
+   ├─ Extract branch coverage percentage
+   ├─ Extract function coverage percentage
+   └─ Identify uncovered lines/branches
+
+Phase 4: Verify TDD Cycle
+   └─ FOR each TDD chain (TEST-N.M → IMPL-N.M → REFACTOR-N.M):
+      ├─ Red Phase: Verify tests created and failed initially
+      ├─ Green Phase: Verify tests now pass
+      └─ Refactor Phase: Verify code quality improved
+
+Phase 5: Generate Analysis Report
+   └─ Create tdd-cycle-report.md with coverage metrics and cycle verification
+```
+
+## Execution Lifecycle
+
+### Phase 1: Extract Test Tasks
+```bash
+find .workflow/active/{session_id}/.task/ -name 'TEST-*.json' -exec jq -r '.context.focus_paths[]' {} \;
+```
+
+**Output**: List of test directories/files from all TEST tasks
+
+### Phase 2: Run Test Suite
+```bash
+# Node.js/JavaScript
+npm test -- --coverage --json > .workflow/active/{session_id}/.process/test-results.json
+
+# Python
+pytest --cov --json-report > .workflow/active/{session_id}/.process/test-results.json
+
+# Other frameworks (detect from project)
+[test_command] --coverage --json-output .workflow/active/{session_id}/.process/test-results.json
+```
+
+**Output**: test-results.json with coverage data
+
+### Phase 3: Parse Coverage Data
+```bash
+jq '.coverage' .workflow/active/{session_id}/.process/test-results.json > .workflow/active/{session_id}/.process/coverage-report.json
+```
+
+**Extract**:
+- Line coverage percentage
+- Branch coverage percentage
+- Function coverage percentage
+- Uncovered lines/branches
+
+### Phase 4: Verify TDD Cycle
+
+For each TDD chain (TEST-N.M -> IMPL-N.M -> REFACTOR-N.M):
+
+**1. Red Phase Verification**
+```bash
+# Check TEST task summary
+cat .workflow/active/{session_id}/.summaries/TEST-N.M-summary.md
+```
+
+Verify:
+- Tests were created
+- Tests failed initially
+- Failure messages were clear
+
+**2. Green Phase Verification**
+```bash
+# Check IMPL task summary
+cat .workflow/active/{session_id}/.summaries/IMPL-N.M-summary.md
+```
+
+Verify:
+- Implementation was completed
+- Tests now pass
+- Implementation was minimal
+
+**3. Refactor Phase Verification**
+```bash
+# Check REFACTOR task summary
+cat .workflow/active/{session_id}/.summaries/REFACTOR-N.M-summary.md
+```
+
+Verify:
+- Refactoring was completed
+- Tests still pass
+- Code quality improved
+
+### Phase 5: Generate Analysis Report
+
+Create `.workflow/active/{session_id}/.process/tdd-cycle-report.md`:
+
+```markdown
+# TDD Cycle Analysis - {Session ID}
+
+## Coverage Metrics
+- **Line Coverage**: {percentage}%
+- **Branch Coverage**: {percentage}%
+- **Function Coverage**: {percentage}%
+
+## Coverage Details
+### Covered
+- {covered_lines} lines
+- {covered_branches} branches
+- {covered_functions} functions
+
+### Uncovered
+- Lines: {uncovered_line_numbers}
+- Branches: {uncovered_branch_locations}
+
+## TDD Cycle Verification
+
+### Feature 1: {Feature Name}
+**Chain**: TEST-1.1 -> IMPL-1.1 -> REFACTOR-1.1
+
+- [PASS] **Red Phase**: Tests created and failed initially
+- [PASS] **Green Phase**: Implementation made tests pass
+- [PASS] **Refactor Phase**: Refactoring maintained green tests
+
+### Feature 2: {Feature Name}
+**Chain**: TEST-2.1 -> IMPL-2.1 -> REFACTOR-2.1
+
+- [PASS] **Red Phase**: Tests created and failed initially
+- [WARN] **Green Phase**: Tests pass but implementation seems over-engineered
+- [PASS] **Refactor Phase**: Refactoring maintained green tests
+
+[Repeat for all features]
+
+## TDD Compliance Summary
+- **Total Chains**: {N}
+- **Complete Cycles**: {N}
+- **Incomplete Cycles**: {0}
+- **Compliance Score**: {score}/100
+
+## Gaps Identified
+- Feature 3: Missing initial test failure verification
+- Feature 5: No refactoring step completed
+
+## Recommendations
+- Complete missing refactoring steps
+- Add edge case tests for Feature 2
+- Verify test failure messages are descriptive
+```
+
+## Output Files
+```
+.workflow/active/{session-id}/
+└── .process/
+    ├── test-results.json         # Raw test execution results
+    ├── coverage-report.json      # Parsed coverage data
+    └── tdd-cycle-report.md       # TDD cycle analysis
+```
+
+## Test Framework Detection
+
+Auto-detect test framework from project:
+
+```bash
+# Check for test frameworks
+if [ -f "package.json" ] && grep -q "jest\|mocha\|vitest" package.json; then
+    TEST_CMD="npm test -- --coverage --json"
+elif [ -f "pytest.ini" ] || [ -f "setup.py" ]; then
+    TEST_CMD="pytest --cov --json-report"
+elif [ -f "Cargo.toml" ]; then
+    TEST_CMD="cargo test -- --test-threads=1 --nocapture"
+elif [ -f "go.mod" ]; then
+    TEST_CMD="go test -coverprofile=coverage.out -json ./..."
+else
+    TEST_CMD="echo 'No supported test framework found'"
+fi
+```
+
+## TDD Cycle Verification Algorithm
+
+```
+For each feature N:
+  1. Load TEST-N.M-summary.md
+     IF summary missing:
+       Mark: "Red phase incomplete"
+       SKIP to next feature
+
+     CHECK: Contains "test" AND "fail"
+     IF NOT found:
+       Mark: "Red phase verification failed"
+     ELSE:
+       Mark: "Red phase [PASS]"
+
+  2. Load IMPL-N.M-summary.md
+     IF summary missing:
+       Mark: "Green phase incomplete"
+       SKIP to next feature
+
+     CHECK: Contains "pass" OR "green"
+     IF NOT found:
+       Mark: "Green phase verification failed"
+     ELSE:
+       Mark: "Green phase [PASS]"
+
+  3. Load REFACTOR-N.M-summary.md
+     IF summary missing:
+       Mark: "Refactor phase incomplete"
+       CONTINUE (refactor is optional)
+
+     CHECK: Contains "refactor" AND "pass"
+     IF NOT found:
+       Mark: "Refactor phase verification failed"
+     ELSE:
+       Mark: "Refactor phase [PASS]"
+
+  4. Calculate chain score:
+     - Red + Green + Refactor all [PASS] = 100%
+     - Red + Green [PASS], Refactor missing = 80%
+     - Red [PASS], Green missing = 40%
+     - All missing = 0%
+```
+
+## Coverage Metrics Calculation
+
+```bash
+# Parse coverage from test-results.json
+line_coverage=$(jq '.coverage.lineCoverage' test-results.json)
+branch_coverage=$(jq '.coverage.branchCoverage' test-results.json)
+function_coverage=$(jq '.coverage.functionCoverage' test-results.json)
+
+# Calculate overall score
+overall_score=$(echo "($line_coverage + $branch_coverage + $function_coverage) / 3" | bc)
+```
+
+## Error Handling
+
+### Test Execution Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Test framework not found | No test config | Configure test framework first |
+| Tests fail to run | Syntax errors | Fix code before analysis |
+| Coverage not available | Missing coverage tool | Install coverage plugin |
+
+### Cycle Verification Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Summary missing | Task not executed | Execute tasks before analysis |
+| Invalid summary format | Corrupted file | Re-run task to regenerate |
+| No test evidence | Tests not committed | Ensure tests are committed |
+
+## Integration
+
+### Phase Chain
+- **Called By**: `phases/03-tdd-verify.md` (Coverage & Cycle Analysis step)
+- **Calls**: Test framework commands (npm test, pytest, etc.)
+- **Followed By**: Compliance report generation in `phases/03-tdd-verify.md`
+
+---
+
+## Post-Phase Update
+
+After TDD Coverage Analysis completes:
+- **Output Created**: `test-results.json`, `coverage-report.json`, `tdd-cycle-report.md` in `.process/`
+- **Data Produced**: Coverage metrics (line/branch/function), TDD cycle verification results per feature
+- **Next Action**: Return data to `phases/03-tdd-verify.md` for compliance report aggregation
+- **TodoWrite**: Mark "Coverage & Cycle Analysis: completed"