fix: update minimal documentation output guideline for clarity

Enhance installation and uninstallation processes
- Added optional quiet mode for backup notifications to reduce output clutter. - Improved file merging with progress reporting and summary of backed up files. - Implemented a cleanup function to move old installations to a backup directory before new installations. - Enhanced manifest handling to distinguish between Global and Path installations. - Updated uninstallation process to preserve global files if a Global installation exists. - Improved error handling and user feedback during file operations.
2026-02-08 02:14:08 +08:00 · 2025-11-22 23:21:26 +08:00 · 2025-11-22 23:20:39 +08:00 · 2025-11-22 21:05:43 +08:00 · 2025-11-22 20:57:16 +08:00 · 2025-11-22 20:32:01 +08:00
15 changed files with 1187 additions and 3456 deletions
--- a/.claude/commands/workflow/execute.md
+++ b/.claude/commands/workflow/execute.md
@@ -54,13 +54,64 @@ Orchestrates autonomous workflow execution through systematic task discovery, ag
 ### Phase 1: Discovery
 **Applies to**: Normal mode only (skipped in resume mode)

-**Process**:
-1. **Check Active Sessions**: Find sessions in `.workflow/active/` directory
-2. **Select Session**: If multiple found, prompt user selection
-3. **Load Session Metadata**: Read `workflow-session.json` ONLY (minimal context)
-4. **DO NOT read task JSONs yet** - defer until execution phase
+**Purpose**: Find and select active workflow session with user confirmation when multiple sessions exist

-**Resume Mode**: This phase is completely skipped when `--resume-session="session-id"` flag is provided.
+**Process**:
+
+#### Step 1.1: Count Active Sessions
+```bash
+bash(find .workflow/active/ -name "WFS-*" -type d 2>/dev/null | wc -l)
+```
+
+#### Step 1.2: Handle Session Selection
+
+**Case A: No Sessions** (count = 0)
+```
+ERROR: No active workflow sessions found
+Run /workflow:plan "task description" to create a session
+```
+
+**Case B: Single Session** (count = 1)
+```bash
+bash(find .workflow/active/ -name "WFS-*" -type d 2>/dev/null | head -1 | xargs basename)
+```
+Auto-select and continue to Phase 2.
+
+**Case C: Multiple Sessions** (count > 1)
+
+List sessions with metadata and prompt user selection:
+```bash
+bash(for dir in .workflow/active/WFS-*/; do
+  session=$(basename "$dir")
+  project=$(jq -r '.project // "Unknown"' "$dir/workflow-session.json" 2>/dev/null)
+  total=$(grep -c "^- \[" "$dir/TODO_LIST.md" 2>/dev/null || echo "0")
+  completed=$(grep -c "^- \[x\]" "$dir/TODO_LIST.md" 2>/dev/null || echo "0")
+  [ "$total" -gt 0 ] && progress=$((completed * 100 / total)) || progress=0
+  echo "${session} | ${project} | ${completed}/${total} tasks (${progress}%)"
+done)
+```
+
+Use AskUserQuestion to present formatted options:
+```
+Multiple active workflow sessions detected. Please select one:
+
+1. WFS-auth-system | Authentication System | 3/5 tasks (60%)
+2. WFS-payment-module | Payment Integration | 0/8 tasks (0%)
+
+Enter number, full session ID, or partial match:
+```
+
+Parse user input (supports: number "1", full ID "WFS-auth-system", or partial "auth"), validate selection, and continue to Phase 2.
+
+#### Step 1.3: Load Session Metadata
+```bash
+bash(cat .workflow/active/${sessionId}/workflow-session.json)
+```
+
+**Output**: Store session metadata in memory
+**DO NOT read task JSONs yet** - defer until execution phase (lazy loading)
+
+**Resume Mode**: This entire phase is skipped when `--resume-session="session-id"` flag is provided.

 ### Phase 2: Planning Document Analysis
 **Applies to**: Normal mode only (skipped in resume mode)
--- a/.claude/commands/workflow/lite-execute.md
+++ b/.claude/commands/workflow/lite-execute.md
@@ -185,86 +185,104 @@ Execution Complete
 previousExecutionResults = []
 ```

-### Step 2: Create TodoWrite Execution List
+### Step 2: Task Grouping & Batch Creation

-**Operations**:
- Create execution tracking from task list
- Typically single execution call for all tasks
- Split into multiple calls if task list very large (>10 tasks)
-
-**Execution Call Creation**:
+**Dependency Analysis & Grouping Algorithm**:
 ```javascript
-function createExecutionCalls(tasks) {
-  const taskTitles = tasks.map(t => t.title || t)
+// Infer dependencies: same file → sequential, keywords (use/integrate) → sequential
+function inferDependencies(tasks) {
+  return tasks.map((task, i) => {
+    const deps = []
+    const file = task.file || task.title.match(/in\s+([^\s:]+)/)?.[1]
+    const keywords = (task.description || task.title).toLowerCase()

-  // Single call for ≤10 tasks (most common)
-  if (tasks.length <= 10) {
-    return [{
-      method: executionMethod === "Codex" ? "Codex" : "Agent",
-      taskSummary: taskTitles.length <= 3
-        ? taskTitles.join(', ')
-        : `${taskTitles.slice(0, 2).join(', ')}, and ${taskTitles.length - 2} more`,
-      tasks: tasks
-    }]
-  }
-
-  // Split into multiple calls for >10 tasks
-  const callSize = 5
-  const calls = []
-  for (let i = 0; i < tasks.length; i += callSize) {
-    const batchTasks = tasks.slice(i, i + callSize)
-    const batchTitles = batchTasks.map(t => t.title || t)
-    calls.push({
-      method: executionMethod === "Codex" ? "Codex" : "Agent",
-      taskSummary: `Tasks ${i + 1}-${Math.min(i + callSize, tasks.length)}: ${batchTitles[0]}...`,
-      tasks: batchTasks
-    })
-  }
-  return calls
+    for (let j = 0; j < i; j++) {
+      const prevFile = tasks[j].file || tasks[j].title.match(/in\s+([^\s:]+)/)?.[1]
+      if (file && prevFile === file) deps.push(j)  // Same file
+      else if (/use|integrate|call|import/.test(keywords)) deps.push(j)  // Keyword dependency
+    }
+    return { ...task, taskIndex: i, dependencies: deps }
+  })
 }

-// Create execution calls with IDs
-executionCalls = createExecutionCalls(planObject.tasks).map((call, index) => ({
-  ...call,
-  id: `[${call.method}-${index+1}]`
-}))
+// Group into batches: independent → parallel [P1,P2...], dependent → sequential [S1,S2...]
+function createExecutionCalls(tasks, executionMethod) {
+  const tasksWithDeps = inferDependencies(tasks)
+  const maxBatch = executionMethod === "Codex" ? 4 : 7
+  const calls = []
+  const processed = new Set()
+
+  // Parallel: independent tasks, different files, max batch size
+  const parallelGroups = []
+  tasksWithDeps.forEach(t => {
+    if (t.dependencies.length === 0 && !processed.has(t.taskIndex)) {
+      const group = [t]
+      processed.add(t.taskIndex)
+      tasksWithDeps.forEach(o => {
+        if (!o.dependencies.length && !processed.has(o.taskIndex) &&
+            group.length < maxBatch && t.file !== o.file) {
+          group.push(o)
+          processed.add(o.taskIndex)
+        }
+      })
+      parallelGroups.push(group)
+    }
+  })
+
+  // Sequential: dependent tasks, batch when deps satisfied
+  const remaining = tasksWithDeps.filter(t => !processed.has(t.taskIndex))
+  while (remaining.length > 0) {
+    const batch = remaining.filter((t, i) =>
+      i < maxBatch && t.dependencies.every(d => processed.has(d))
+    )
+    if (!batch.length) break
+    batch.forEach(t => processed.add(t.taskIndex))
+    calls.push({ executionType: "sequential", groupId: `S${calls.length + 1}`, tasks: batch })
+    remaining.splice(0, remaining.length, ...remaining.filter(t => !processed.has(t.taskIndex)))
+  }
+
+  // Combine results
+  return [
+    ...parallelGroups.map((g, i) => ({
+      method: executionMethod, executionType: "parallel", groupId: `P${i+1}`,
+      taskSummary: g.map(t => t.title).join(' | '), tasks: g
+    })),
+    ...calls.map(c => ({ ...c, method: executionMethod, taskSummary: c.tasks.map(t => t.title).join(' → ') }))
+  ]
+}
+
+executionCalls = createExecutionCalls(planObject.tasks, executionMethod).map(c => ({ ...c, id: `[${c.groupId}]` }))

-// Create TodoWrite list
 TodoWrite({
-  todos: executionCalls.map(call => ({
-    content: `${call.id} (${call.taskSummary})`,
+  todos: executionCalls.map(c => ({
+    content: `${c.executionType === "parallel" ? "⚡" : "→"} ${c.id} (${c.tasks.length} tasks)`,
    status: "pending",
-    activeForm: `Executing ${call.id} (${call.taskSummary})`
+    activeForm: `Executing ${c.id}`
  }))
 })
 ```

-**Example Execution Lists**:
-```
-Single call (typical):
-[ ] [Agent-1] (Create AuthService, Add JWT utilities, Implement middleware)
-
-Few tasks:
-[ ] [Codex-1] (Create AuthService, Add JWT utilities, and 3 more)
-
-Large task sets (>10):
-[ ] [Agent-1] (Tasks 1-5: Create AuthService, Add JWT utilities, ...)
-[ ] [Agent-2] (Tasks 6-10: Create tests, Update docs, ...)
-```
-
 ### Step 3: Launch Execution

-**IMPORTANT**: CLI execution MUST run in foreground (no background execution)
-
-**Execution Loop**:
+**Execution Flow**: Parallel batches concurrently → Sequential batches in order
 ```javascript
-for (currentIndex = 0; currentIndex < executionCalls.length; currentIndex++) {
-  const currentCall = executionCalls[currentIndex]
+const parallel = executionCalls.filter(c => c.executionType === "parallel")
+const sequential = executionCalls.filter(c => c.executionType === "sequential")

-  // Update TodoWrite: mark current call in_progress
-  // Launch execution with previousExecutionResults context
-  // After completion: collect result, add to previousExecutionResults
-  // Update TodoWrite: mark current call completed
+// 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" })) })
 }
 ```

@@ -323,12 +341,17 @@ ${result.notes ? `Notes: ${result.notes}` : ''}

  ${clarificationContext ? `\n## Clarifications\n${JSON.stringify(clarificationContext, null, 2)}` : ''}

-  ## Instructions
-  - Reference original request to ensure alignment
-  - Review previous results to understand completed work
-  - Build on previous work, avoid duplication
-  - Test functionality as you implement
-  - Complete all assigned tasks
+  ${executionContext?.session?.artifacts ? `\n## Planning Artifacts
+  Detailed planning context available in:
+  ${executionContext.session.artifacts.exploration ? `- Exploration: ${executionContext.session.artifacts.exploration}` : ''}
+  - Plan: ${executionContext.session.artifacts.plan}
+  - Task: ${executionContext.session.artifacts.task}
+
+  Read these files for detailed architecture, patterns, and constraints.` : ''}
+
+  ## Requirements
+  MUST complete ALL ${planObject.tasks.length} tasks listed above in this single execution.
+  Return only after all tasks are fully implemented and tested.
  `
 )
 ```
@@ -341,6 +364,11 @@ When to use:
 - `executionMethod = "Codex"`
 - `executionMethod = "Auto" AND complexity = "Medium" or "High"`

+**Artifact Path Delegation**:
+- Include artifact file paths in CLI prompt for enhanced context
+- Codex can read artifact files for detailed planning information
+- Example: Reference exploration.json for architecture patterns
+
 Command format:
 ```bash
 function formatTaskForCodex(task, index) {
@@ -390,12 +418,18 @@ Constraints: ${explorationContext.constraints || 'None'}

 ${clarificationContext ? `\n### User Clarifications\n${Object.entries(clarificationContext).map(([q, a]) => `${q}: ${a}`).join('\n')}` : ''}

-## Execution Instructions
- Reference original request to ensure alignment
- Review previous results for context continuity
- Build on previous work, don't duplicate completed tasks
- Complete all assigned tasks in single execution
- Test functionality as you implement
+${executionContext?.session?.artifacts ? `\n### Planning Artifact Files
+Detailed planning context available in session folder:
+${executionContext.session.artifacts.exploration ? `- Exploration: ${executionContext.session.artifacts.exploration}` : ''}
+- Plan: ${executionContext.session.artifacts.plan}
+- Task: ${executionContext.session.artifacts.task}
+
+Read these files for complete architecture details, code patterns, and integration constraints.
+` : ''}
+
+## Requirements
+MUST complete ALL ${planObject.tasks.length} tasks listed above in this single execution.
+Return only after all tasks are fully implemented and tested.

 Complexity: ${planObject.complexity}
 " --skip-git-repo-check -s danger-full-access
@@ -414,105 +448,72 @@ bash_result = Bash(

 **Result Collection**: After completion, analyze output and collect result following `executionResult` structure

-### Step 4: Track Execution Progress
+### Step 4: Progress Tracking

-**Real-time TodoWrite Updates** at execution call level:
-
-```javascript
-// When call starts
-TodoWrite({
-  todos: [
-    { content: "[Agent-1] (Implement auth + Create JWT utils)", status: "in_progress", activeForm: "..." },
-    { content: "[Agent-2] (Add middleware + Update routes)", status: "pending", activeForm: "..." }
-  ]
-})
-
-// When call completes
-TodoWrite({
-  todos: [
-    { content: "[Agent-1] (Implement auth + Create JWT utils)", status: "completed", activeForm: "..." },
-    { content: "[Agent-2] (Add middleware + Update routes)", status: "in_progress", activeForm: "..." }
-  ]
-})
-```
-
-**User Visibility**:
- User sees execution call progress (not individual task progress)
- Current execution highlighted as "in_progress"
- Completed executions marked with checkmark
- Each execution shows task summary for context
+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"`

-**Operations**:
- Agent Review: Current agent performs direct review
- Gemini Review: Execute gemini CLI with review prompt
- Custom tool: Execute specified CLI tool (qwen, codex, etc.)
+**Review Focus**: Verify implementation against task.json acceptance criteria
+- Read task.json from session artifacts for acceptance criteria
+- Check each acceptance criterion is fulfilled
+- Validate code quality and identify issues
+- Ensure alignment with planned approach

-**Command Formats**:
+**Operations**:
+- Agent Review: Current agent performs direct review (read task.json for acceptance criteria)
+- Gemini Review: Execute gemini CLI with review prompt (task.json in CONTEXT)
+- Custom tool: Execute specified CLI tool (qwen, codex, etc.) with task.json reference
+
+**Unified Review Template** (All tools use same standard):
+
+**Review Criteria**:
+- **Acceptance Criteria**: Verify each criterion from task.json `context.acceptance`
+- **Code Quality**: Analyze quality, identify issues, suggest improvements
+- **Plan Alignment**: Validate implementation matches planned approach
+
+**Shared Prompt Template** (used by all CLI tools):
+```
+PURPOSE: Code review for implemented changes against task.json acceptance criteria
+TASK: • Verify task.json acceptance criteria fulfillment • Analyze code quality • Identify issues • Suggest improvements • Validate plan adherence
+MODE: analysis
+CONTEXT: @**/* @{task.json} @{plan.json} [@{exploration.json}] | Memory: Review lite-execute changes against task.json requirements
+EXPECTED: Quality assessment with acceptance criteria verification, issue identification, and recommendations. Explicitly check each acceptance criterion from task.json.
+RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-review-code-quality.txt) | Focus on task.json acceptance criteria and plan adherence | analysis=READ-ONLY
+```
+
+**Tool-Specific Execution** (Apply shared prompt template above):

 ```bash
-# Agent Review: Direct agent review (no CLI)
-# Uses analysis prompt and TodoWrite tools directly
+# Method 1: Agent Review (current agent)
+# - Read task.json: ${executionContext.session.artifacts.task}
+# - Apply unified review criteria (see Shared Prompt Template)
+# - Report findings directly

-# Gemini Review:
-gemini -p "
-PURPOSE: Code review for implemented changes
-TASK: • Analyze quality • Identify issues • Suggest improvements
-MODE: analysis
-CONTEXT: @**/* | Memory: Review lite-execute changes
-EXPECTED: Quality assessment with recommendations
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-review-code-quality.txt) | Focus on recent changes | analysis=READ-ONLY
-"
+# Method 2: Gemini Review (recommended)
+gemini -p "[Shared Prompt Template with artifacts]"
+# CONTEXT includes: @**/* @${task.json} @${plan.json} [@${exploration.json}]

-# Qwen Review (custom tool via "Other"):
-qwen -p "
-PURPOSE: Code review for implemented changes
-TASK: • Analyze quality • Identify issues • Suggest improvements
-MODE: analysis
-CONTEXT: @**/* | Memory: Review lite-execute changes
-EXPECTED: Quality assessment with recommendations
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-review-code-quality.txt) | Focus on recent changes | analysis=READ-ONLY
-"
+# Method 3: Qwen Review (alternative)
+qwen -p "[Shared Prompt Template with artifacts]"
+# Same prompt as Gemini, different execution engine

-# Codex Review (custom tool via "Other"):
-codex --full-auto exec "Review recent code changes for quality, potential issues, and improvements" --skip-git-repo-check -s danger-full-access
+# Method 4: Codex Review (autonomous)
+codex --full-auto exec "[Verify task.json acceptance criteria at ${task.json}]" --skip-git-repo-check -s danger-full-access
 ```

+**Implementation Note**: Replace `[Shared Prompt Template with artifacts]` placeholder with actual template content, substituting:
+- `@{task.json}` → `@${executionContext.session.artifacts.task}`
+- `@{plan.json}` → `@${executionContext.session.artifacts.plan}`
+- `[@{exploration.json}]` → `@${executionContext.session.artifacts.exploration}` (if exists)
+
 ## Best Practices

-### Execution Intelligence
-
-1. **Context Continuity**: Each execution call receives previous results
-   - Prevents duplication across multiple executions
-   - Maintains coherent implementation flow
-   - Builds on completed work
-
-2. **Execution Call Tracking**: Progress at call level, not task level
-   - Each call handles all or subset of tasks
-   - Clear visibility of current execution
-   - Simple progress updates
-
-3. **Flexible Execution**: Multiple input modes supported
-   - In-memory: Seamless lite-plan integration
-   - Prompt: Quick standalone execution
-   - File: Intelligent format detection
-     - Enhanced Task JSON (lite-plan export): Full plan extraction
-     - Plain text: Uses as prompt
-
-### Task Management
-
-1. **Live Progress Updates**: Real-time TodoWrite tracking
-   - Execution calls created before execution starts
-   - Updated as executions progress
-   - Clear completion status
-
-2. **Simple Execution**: Straightforward task handling
-   - All tasks in single call (typical)
-   - Split only for very large task sets (>10)
-   - Agent/Codex determines optimal execution order
+**Input Modes**: In-memory (lite-plan), prompt (standalone), file (JSON/text)
+**Batch Limits**: Agent 7 tasks, CLI 4 tasks
+**Execution**: Parallel batches use single Claude message with multiple tool calls (no concurrency limit)

 ## Error Handling

@@ -546,10 +547,26 @@ Passed from lite-plan via global variable:
  clarificationContext: {...} | null,
  executionMethod: "Agent" | "Codex" | "Auto",
  codeReviewTool: "Skip" | "Gemini Review" | "Agent Review" | string,
-  originalUserInput: string
+  originalUserInput: string,
+
+  // Session artifacts location (saved by lite-plan)
+  session: {
+    id: string,                        // Session identifier: {taskSlug}-{shortTimestamp}
+    folder: string,                    // Session folder path: .workflow/.lite-plan/{session-id}
+    artifacts: {
+      exploration: string | null,      // exploration.json path (if exploration performed)
+      plan: string,                    // plan.json path (always present)
+      task: string                     // task.json path (always exported)
+    }
+  }
 }
 ```

+**Artifact Usage**:
+- Artifact files contain detailed planning context
+- Pass artifact paths to CLI tools and agents for enhanced context
+- See execution options below for usage examples
+
 ### executionResult (Output)

 Collected after each execution call completes:
--- a/.claude/commands/workflow/lite-plan.md
+++ b/.claude/commands/workflow/lite-plan.md
@@ -130,6 +130,13 @@ needsExploration = (

 **Exploration Execution** (if needed):
 ```javascript
+// Generate session identifiers for artifact storage
+const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
+const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
+const shortTimestamp = timestamp.substring(0, 19).replace('T', '-') // YYYY-MM-DD-HH-mm-ss
+const sessionId = `${taskSlug}-${shortTimestamp}`
+const sessionFolder = `.workflow/.lite-plan/${sessionId}`
+
 Task(
  subagent_type="cli-explore-agent",
  description="Analyze codebase for task context",
@@ -149,9 +156,14 @@ Task(
  Output Format: JSON-like structured object
  `
 )
+
+// Save exploration results for CLI/agent access in lite-execute
+const explorationFile = `${sessionFolder}/exploration.json`
+Write(explorationFile, JSON.stringify(explorationContext, null, 2))
 ```

-**Output**: `explorationContext` (see Data Structures section)
+**Output**: `explorationContext` (in-memory, see Data Structures section)
+**Artifact**: Saved to `{sessionFolder}/exploration.json` for CLI/agent use

 **Progress Tracking**:
 - Mark Phase 1 completed
@@ -228,6 +240,14 @@ Current Claude generates plan directly:
 - Estimated Time: Total implementation time
 - Recommended Execution: "Agent"

+```javascript
+// Save planning results to session folder (same as Option B)
+const planFile = `${sessionFolder}/plan.json`
+Write(planFile, JSON.stringify(planObject, null, 2))
+```
+
+**Artifact**: Saved to `{sessionFolder}/plan.json` for CLI/agent use
+
 **Option B: Agent-Based Planning (Medium/High Complexity)**

 Delegate to cli-lite-planning-agent:
@@ -270,9 +290,14 @@ Task(
  Format: "{Action} in {file_path}: {details} following {pattern}"
  `
 )
+
+// Save planning results to session folder
+const planFile = `${sessionFolder}/plan.json`
+Write(planFile, JSON.stringify(planObject, null, 2))
 ```

 **Output**: `planObject` (see Data Structures section)
+**Artifact**: Saved to `{sessionFolder}/plan.json` for CLI/agent use

 **Progress Tracking**:
 - Mark Phase 3 completed
@@ -315,7 +340,7 @@ ${i+1}. **${task.title}** (${task.file})

 **Step 4.2: Collect User Confirmation**

-Four questions via single AskUserQuestion call:
+Three questions via single AskUserQuestion call:

 ```javascript
 AskUserQuestion({
@@ -353,15 +378,6 @@ Confirm plan? (Multi-select: can supplement via "Other")`,
        { label: "Agent Review", description: "@code-reviewer agent" },
        { label: "Skip", description: "No review" }
      ]
-    },
-    {
-      question: "Export plan to Enhanced Task JSON file?\n\nAllows reuse with lite-execute later.",
-      header: "Export JSON",
-      multiSelect: false,
-      options: [
-        { label: "Yes", description: "Export to JSON (recommended for complex tasks)" },
-        { label: "No", description: "Keep in-memory only" }
-      ]
    }
  ]
 })
@@ -384,10 +400,6 @@ Code Review (after execution):
  ├─ Gemini Review → gemini CLI analysis
  ├─ Agent Review → Current Claude review
  └─ Other → Custom tool (e.g., qwen, codex)
-
-Export JSON:
-  ├─ Yes → Export to .workflow/lite-plans/plan-{timestamp}.json
-  └─ No → In-memory only
 ```

 **Progress Tracking**:
@@ -398,48 +410,48 @@ Export JSON:

 ### Phase 5: Dispatch to Execution

-**Step 5.1: Export Enhanced Task JSON (Optional)**
+**Step 5.1: Export Enhanced Task JSON**

-Only execute if `userSelection.export_task_json === "Yes"`:
+Always export Enhanced Task JSON to session folder:

 ```javascript
-if (userSelection.export_task_json === "Yes") {
-  const timestamp = new Date().toISOString().replace(/[:.]/g, '-')
-  const taskId = `LP-${timestamp}`
-  const filename = `.workflow/lite-plans/${taskId}.json`
+const taskId = `LP-${shortTimestamp}`
+const filename = `${sessionFolder}/task.json`

-  const enhancedTaskJson = {
-    id: taskId,
-    title: original_task_description,
-    status: "pending",
+const enhancedTaskJson = {
+  id: taskId,
+  title: original_task_description,
+  status: "pending",

-    meta: {
-      type: "planning",
-      created_at: new Date().toISOString(),
-      complexity: planObject.complexity,
-      estimated_time: planObject.estimated_time,
-      recommended_execution: planObject.recommended_execution,
-      workflow: "lite-plan"
+  meta: {
+    type: "planning",
+    created_at: new Date().toISOString(),
+    complexity: planObject.complexity,
+    estimated_time: planObject.estimated_time,
+    recommended_execution: planObject.recommended_execution,
+    workflow: "lite-plan",
+    session_id: sessionId,
+    session_folder: sessionFolder
+  },
+
+  context: {
+    requirements: [original_task_description],
+    plan: {
+      summary: planObject.summary,
+      approach: planObject.approach,
+      tasks: planObject.tasks
    },
-
-    context: {
-      requirements: [original_task_description],
-      plan: {
-        summary: planObject.summary,
-        approach: planObject.approach,
-        tasks: planObject.tasks
-      },
-      exploration: explorationContext || null,
-      clarifications: clarificationContext || null,
-      focus_paths: explorationContext?.relevant_files || [],
-      acceptance: planObject.tasks.flatMap(t => t.acceptance)
-    }
+    exploration: explorationContext || null,
+    clarifications: clarificationContext || null,
+    focus_paths: explorationContext?.relevant_files || [],
+    acceptance: planObject.tasks.flatMap(t => t.acceptance)
  }
-
-  Write(filename, JSON.stringify(enhancedTaskJson, null, 2))
-  console.log(`Enhanced Task JSON exported to: ${filename}`)
-  console.log(`Reuse with: /workflow:lite-execute ${filename}`)
 }
+
+Write(filename, JSON.stringify(enhancedTaskJson, null, 2))
+console.log(`Enhanced Task JSON exported to: ${filename}`)
+console.log(`Session folder: ${sessionFolder}`)
+console.log(`Reuse with: /workflow:lite-execute ${filename}`)
 ```

 **Step 5.2: Store Execution Context**
@@ -451,7 +463,18 @@ executionContext = {
  clarificationContext: clarificationContext || null,
  executionMethod: userSelection.execution_method,
  codeReviewTool: userSelection.code_review_tool,
-  originalUserInput: original_task_description
+  originalUserInput: original_task_description,
+
+  // Session artifacts location
+  session: {
+    id: sessionId,
+    folder: sessionFolder,
+    artifacts: {
+      exploration: explorationContext ? `${sessionFolder}/exploration.json` : null,
+      plan: `${sessionFolder}/plan.json`,
+      task: `${sessionFolder}/task.json`  // Always exported
+    }
+  }
 }
 ```

@@ -462,7 +485,11 @@ SlashCommand(command="/workflow:lite-execute --in-memory")
 ```

 **Execution Handoff**:
- lite-execute reads `executionContext` variable
+- lite-execute reads `executionContext` variable from memory
+- `executionContext.session.artifacts` contains file paths to saved planning artifacts:
+  - `exploration` - exploration.json (if exploration performed)
+  - `plan` - plan.json (always exists)
+  - `task` - task.json (if user selected export)
 - All execution logic handled by lite-execute
 - lite-plan completes after successful handoff

@@ -502,7 +529,7 @@ SlashCommand(command="/workflow:lite-execute --in-memory")
     - Plan confirmation (multi-select with supplements)
     - Execution method selection
     - Code review tool selection (custom via "Other")
-     - JSON export option
+   - Enhanced Task JSON always exported to session folder
   - Allows plan refinement without re-selecting execution method

 ### Task Management
@@ -519,11 +546,11 @@ SlashCommand(command="/workflow:lite-execute --in-memory")
   - Medium: 5-7 tasks (detailed)
   - High: 7-10 tasks (comprehensive)

-3. **No File Artifacts During Planning**:
-   - All planning stays in memory
-   - Optional Enhanced Task JSON export (user choice)
-   - Faster workflow, cleaner workspace
-   - Plan context passed directly to execution
+3. **Session Artifact Management**:
+   - All planning artifacts saved to dedicated session folder
+   - Enhanced Task JSON always exported for reusability
+   - Plan context passed to execution via memory and files
+   - Clean organization with session-based folder structure

 ### Planning Standards

@@ -550,6 +577,39 @@ SlashCommand(command="/workflow:lite-execute --in-memory")
 | Phase 4 Confirmation Timeout | User no response > 5 minutes | Save context to temp var, display resume instructions, exit gracefully |
 | Phase 4 Modification Loop | User requests modify > 3 times | Suggest breaking task into smaller pieces or using `/workflow:plan` |

+## Session Folder Structure
+
+Each lite-plan execution creates a dedicated session folder to organize all artifacts:
+
+```
+.workflow/.lite-plan/{task-slug}-{short-timestamp}/
+├── exploration.json          # Exploration results (if exploration performed)
+├── plan.json                 # Planning results (always created)
+└── task.json                 # Enhanced Task JSON (always created)
+```
+
+**Folder Naming Convention**:
+- `{task-slug}`: First 40 characters of task description, lowercased, non-alphanumeric replaced with `-`
+- `{short-timestamp}`: YYYY-MM-DD-HH-mm-ss format
+- Example: `.workflow/.lite-plan/implement-user-auth-jwt-2025-01-15-14-30-45/`
+
+**File Contents**:
+- `exploration.json`: Complete explorationContext object (if exploration performed, see Data Structures)
+- `plan.json`: Complete planObject (always created, see Data Structures)
+- `task.json`: Enhanced Task JSON with all context (always created, see Data Structures)
+
+**Access Patterns**:
+- **lite-plan**: Creates folder and writes all artifacts during execution, passes paths via `executionContext.session.artifacts`
+- **lite-execute**: Reads artifact paths from `executionContext.session.artifacts` (see lite-execute.md for usage details)
+- **User**: Can inspect artifacts for debugging or reference
+- **Reuse**: Pass `task.json` path to `/workflow:lite-execute {path}` for re-execution
+
+**Benefits**:
+- Clean separation between different task executions
+- Easy to find and inspect artifacts for specific tasks
+- Natural history/audit trail of planning sessions
+- Supports concurrent lite-plan executions without conflicts
+
 ## Data Structures

 ### explorationContext
@@ -621,7 +681,18 @@ Context passed to lite-execute via --in-memory (Phase 5):
  clarificationContext: {...} | null,  // User responses from Phase 2
  executionMethod: "Agent" | "Codex" | "Auto",
  codeReviewTool: "Skip" | "Gemini Review" | "Agent Review" | string,
-  originalUserInput: string            // User's original task description
+  originalUserInput: string,           // User's original task description
+
+  // Session artifacts location (for lite-execute to access saved files)
+  session: {
+    id: string,                        // Session identifier: {taskSlug}-{shortTimestamp}
+    folder: string,                    // Session folder path: .workflow/.lite-plan/{session-id}
+    artifacts: {
+      exploration: string | null,      // exploration.json path (if exploration performed)
+      plan: string,                    // plan.json path (always present)
+      task: string                     // task.json path (always exported)
+    }
+  }
 }
 ```

--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -29,6 +29,7 @@ For all CLI tool usage, command syntax, and integration guidelines:
 - **Clear intent over clever code** - Be boring and obvious
 - **Follow existing code style** - Match import patterns, naming conventions, and formatting of existing codebase
 - **No unsolicited reports** - Task summaries can be performed internally, but NEVER generate additional reports, documentation files, or summary files without explicit user permission
+- **Minimal documentation output** - Avoid unnecessary documentation. If required, save to .workflow/.scratchpad/

 ### Simplicity Means

--- a/COMMAND_DOCS_AUDIT_REPORT.md
+++ b/COMMAND_DOCS_AUDIT_REPORT.md
@@ -1,278 +0,0 @@
-# 命令文档审计报告
-
-**审计日期**: 2025-11-20
-**审计范围**: 73个命令文档文件
-**审计方法**: 自动化扫描 + 手动内容分析
-
---
-
-## 发现的问题
-
-### 1. 包含版本信息的文件
-
-#### [CRITICAL] version.md
-**文件路径**: `/home/user/Claude-Code-Workflow/.claude/commands/version.md`
-
-**问题位置**:
- 第1-3行：包含在YAML头中
- 第96-102行：示例中包含完整版本号和发布日期（如"v3.2.2"、"2025-10-03"）
- 第127-130行：包含开发版本号和日期
- 第155-172行：版本比较和升级建议
-
-**内容摘要**:
-```
-Latest Stable: v3.2.2
-Release: v3.2.2: Independent Test-Gen Workflow with Cross-Session Context
-Published: 2025-10-03T04:10:08Z
-
-Latest Dev: a03415b
-Message: feat: Add version tracking and upgrade check system
-Date: 2025-10-03T04:46:44Z
-```
-
-**严重程度**: ⚠️ 高 - 文件本质上是版本管理命令，但包含具体版本号、发布日期和完整版本历史
-
---
-
-### 2. 包含额外无关内容的文件
-
-#### [HIGH] tdd-plan.md
-**文件路径**: `/home/user/Claude-Code-Workflow/.claude/commands/workflow/tdd-plan.md`
-
-**问题位置**: 第420-523行
-
-**部分内容**:
-```markdown
-## TDD Workflow Enhancements
-
-### Overview
-The TDD workflow has been significantly enhanced by integrating best practices
-from both traditional `plan --agent` and `test-gen` workflows...
-
-### Key Improvements
-
-#### 1. Test Coverage Analysis (Phase 3)
-**Adopted from test-gen workflow**
-
-#### 2. Iterative Green Phase with Test-Fix Cycle
-**Adopted from test-gen workflow**
-
-#### 3. Agent-Driven Planning
-**From plan --agent workflow**
-
-### Workflow Comparison
-| Aspect | Previous | Current (Optimized) |
-| **Task Count** | 5 features = 15 tasks | 5 features = 5 tasks (70% reduction) |
-| **Task Management** | High overhead (15 tasks) | Low overhead (5 tasks) |
-
-### Migration Notes
-**Backward Compatibility**: Fully compatible
- Existing TDD workflows continue to work
- New features are additive, not breaking
-```
-
-**问题分析**:
- 包含"增强"、"改进"、"演进"等版本历史相关内容
- 包含"工作流比较"部分，对比了"之前"和"现在"的版本
- 包含"迁移说明"，描述了从旧版本的升级路径
- 约100行内容（第420-523行）不是关于命令如何使用，而是关于如何改进的
-
-**严重程度**: ⚠️ 中-高 - 约18%的文件内容（100/543行）是版本演进相关，而不是核心功能说明
-
---
-
-### 3. 任务不够专注的文件
-
-#### [MEDIUM] tdd-plan.md (继续)
-**问题**: 文件中包含过多关于与其他命令（plan、test-gen）集成的说明
-
-**相关部分**:
- 第475-488行：与"plan --agent"工作流的比较
- 第427-441行：描述从test-gen工作流"采纳"的特性
- 第466-473行：描述从plan --agent工作流"采纳"的特性
-
-**问题分析**: 虽然这些集成说明可能有用，但在命令文档中过度强调其他命令的关系，使文档的焦点分散。建议这类内容应放在项目级文档或架构文档中，而不是在具体命令文档中。
-
-**严重程度**: ⚠️ 中 - 降低了文档的焦点，但不是严重问题
-
---
-
-## 合规文件统计
-
-### 审计结果汇总
-
-| 类别 | 计数 | 百分比 |
-|------|------|--------|
-| **完全合规的文件** | 70 | 95.9% |
-| **有版本信息的文件** | 1 | 1.4% |
-| **包含额外无关内容的文件** | 1 | 1.4% |
-| **任务不够专注的文件** | 1* | 1.4% |
-| **总计** | 73 | 100% |
-
-*注: tdd-plan.md 同时出现在"额外无关内容"和"任务不专注"两个类别中
-
-### 问题严重程度分布
-
-| 严重程度 | 文件数 | 说明 |
-|---------|--------|------|
-| CRITICAL | 0 | 没有需要立即阻止执行的问题 |
-| HIGH | 1 | version.md - 包含完整版本号和发布信息 |
-| MEDIUM | 1 | tdd-plan.md - 包含过度的版本演进说明和工作流对比 |
-| LOW | 0 | 无其他问题 |
-
---
-
-## 详细发现
-
-### version.md - 完整分析
-
-**问题本质**: version.md命令的存在目的就是管理和报告版本信息。文件中包含版本号、发布日期、更新日志等内容不仅是合理的，而是必需的。
-
-**但审计角度**: 根据用户的审计标准：
- ✓ "包含版本号、版本历史、changelog等内容" - **是的，明确包含**
-  - 示例版本号: v3.2.1, v3.2.2, 3.4.0-dev
-  - 发布日期: 2025-10-03T12:00:00Z
-  - 版本历史信息和升级路径
-
-**结论**: 该文件符合审计标准中的"版本信息"类别，应被标记为有问题（尽管这是功能需求）
-
---
-
-### tdd-plan.md - 完整分析
-
-**第一个问题 - 额外的版本演进信息**:
-```
-## TDD Workflow Enhancements (行420)
-### Overview
-The TDD workflow has been **significantly enhanced** by integrating best practices
-from **both traditional `plan --agent` and `test-gen` workflows**
-
-### Key Improvements
-#### 1. Test Coverage Analysis (Phase 3)
-**Adopted from test-gen workflow** (行428)
-
-#### 2. Iterative Green Phase with Test-Fix Cycle
-**Adopted from test-gen workflow** (行443)
-
-#### 3. Agent-Driven Planning
-**From plan --agent workflow** (行467)
-```
-
-这部分内容完全是关于命令的历史演变和改进，不是关于如何使用该命令。
-
-**第二个问题 - 工作流对比表**:
-```
-### Workflow Comparison (行475)
-| Aspect | Previous | Current (Optimized) |
-| **Phases** | 6 | 7 |
-| **Task Count** | 5 features = 15 tasks | 5 features = 5 tasks (70% reduction) |
-```
-
-直接对比了"之前"和"现在"的实现，这是版本历史相关内容。
-
-**第三个问题 - 迁移说明**:
-```
-### Migration Notes (行490)
-**Backward Compatibility**: Fully compatible
- Existing TDD workflows continue to work
- New features are additive, not breaking
-```
-
-这是版本升级路径说明，不是命令核心功能文档的一部分。
-
-**统计**:
- 总行数: 543行
- 有问题的行: ~103行（第420-523行）
- 占比: ~19%
-
-**结论**: tdd-plan.md 同时违反了两个审计标准：
-1. 包含版本演进历史相关内容
-2. 过度描述与其他命令的关系（缺乏任务专注度）
-
---
-
-## 建议
-
-### 高优先级
-
-1. **移除 version.md 中的具体版本号**
-   - 当前做法: 包含硬编码的版本号、日期等
-   - 建议: 使用变量或运行时获取版本信息，文档中只描述版本命令的功能
-   - 理由: 版本号应该由版本控制系统管理，而不是在文档中硬编码
-
-2. **从 tdd-plan.md 中移除第420-523行（版本演进部分）**
-   - 当前: ~103行关于"增强"、"改进"、"迁移"的内容
-   - 建议: 移到单独的"CHANGELOG.md"或项目级文档
-   - 理由: 这是历史演变信息，不是使用指南
-
-### 中优先级
-
-3. **重构 tdd-plan.md 中的工作流关系**
-   - 当前: 第475-495行详细对比与其他命令的区别
-   - 建议: 简化对其他命令的引用，保留"Related Commands"部分即可
-   - 理由: 过度关注与其他命令的关系分散了文档焦点
-
-4. **统一版本信息管理策略**
-   - 建议: 建立项目级文档规范，明确哪些信息应在命令文档中出现
-   - 范围: 适用于所有命令文档
-
---
-
-## 合规性评定
-
-### 总体评分: 96/100
-
- ✓ **整体质量高**: 95.9%的文件完全合规
- ⚠️ **两个文件需要整改**:
-  - version.md: 版本信息管理需要优化
-  - tdd-plan.md: 版本演进内容需要分离
-
-### 推荐行动
-
-| 优先级 | 行动 | 预期影响 |
-|--------|------|---------|
-| **高** | 清理 version.md 的硬编码版本号 | 提高版本管理的可维护性 |
-| **高** | 从 tdd-plan.md 移除第420-523行 | 提高文档专注度，减少19% |
-| **中** | 建立版本信息管理规范 | 防止未来重复问题 |
-| **低** | 简化 tdd-plan.md 中的工作流关系说明 | 进一步改善文档清晰度 |
-
---
-
-## 附录
-
-### 审计方法论
-
-1. **自动扫描**: 使用grep搜索关键词（version, changelog, release, history等）
-2. **内容分析**: 手动读取匹配文件的完整内容
-3. **结构分析**: 检查是否包含与核心功能无关的内容
-4. **统计分析**: 计算问题内容占比
-
-### 数据来源
-
- 总文件数: 73
- 详细分析文件: 15
- 快速扫描文件: 58
-
-### 文件列表（完整性检查）
-
-已审计的所有命令文档:
- ✓ version.md (有问题)
- ✓ enhance-prompt.md
- ✓ test-fix-gen.md
- ✓ test-gen.md
- ✓ test-cycle-execute.md
- ✓ tdd-plan.md (有问题)
- ✓ tdd-verify.md
- ✓ status.md
- ✓ review.md
- ✓ plan.md
- ✓ lite-plan.md
- ✓ lite-execute.md
- ✓ init.md
- ✓ execute.md
- ✓ action-plan-verify.md
- ... 以及其他58个文件 (全部合规)
-
---
-
-**审计完成** - 生成时间: 2025-11-20
--- a/COMMAND_FLOW_STANDARD.md
+++ b/COMMAND_FLOW_STANDARD.md
@@ -1,274 +0,0 @@
-# Command Flow Expression Standard
-
-**用途**：规范命令文档中Task、SlashCommand、Skill和Bash调用的标准表达方式
-
-**版本**：v2.1.0
-
---
-
-## 核心原则
-
-1. **统一格式** - 所有调用使用标准化格式
-2. **清晰参数** - 必需参数明确标注，可选参数加方括号
-3. **减少冗余** - 避免不必要的echo命令和管道操作
-4. **工具优先** - 优先使用专用工具（Write/Read/Edit）而非Bash变通
-5. **可读性** - 保持缩进和换行的一致性
-
---
-
-## 1. Task调用标准（Agent启动）
-
-### 标准格式
-
-```javascript
-Task(
-  subagent_type="agent-type",
-  description="Brief description",
-  prompt=`
-FULL TASK PROMPT HERE
-  `
-)
-```
-
-### 规范要求
-
- `subagent_type`: Agent类型（字符串）
- `description`: 简短描述（5-10词，动词开头）
- `prompt`: 完整任务提示（使用反引号包裹多行内容）
- 参数字段缩进2空格
-
-### 正确示例
-
-```javascript
-// CLI执行agent
-Task(
-  subagent_type="cli-execution-agent",
-  description="Analyze codebase patterns",
-  prompt=`
-PURPOSE: Identify code patterns for refactoring
-TASK: Scan project files and extract common patterns
-MODE: analysis
-CONTEXT: @src/**/*
-EXPECTED: Pattern list with usage examples
-  `
-)
-
-// 代码开发agent
-Task(
-  subagent_type="code-developer",
-  description="Implement authentication module",
-  prompt=`
-GOAL: Build JWT-based authentication
-SCOPE: User login, token validation, session management
-CONTEXT: @src/auth/**/* @CLAUDE.md
-  `
-)
-```
-
---
-
-## 2. SlashCommand调用标准
-
-### 标准格式
-
-```javascript
-SlashCommand(command="/category:command-name [flags] arguments")
-```
-
-### 规范要求
-
-单行调用 | 双引号包裹 | 完整路径`/category:command-name` | 参数顺序: 标志→参数值
-
-### 正确示例
-
-```javascript
-// 无参数
-SlashCommand(command="/workflow:status")
-
-// 带标志和参数
-SlashCommand(command="/workflow:session:start --auto \"task description\"")
-
-// 变量替换
-SlashCommand(command="/workflow:tools:context-gather --session [sessionId] \"description\"")
-
-// 多个标志
-SlashCommand(command="/workflow:plan --agent --cli-execute \"feature description\"")
-```
-
---
-
-## 3. Skill调用标准
-
-### 标准格式
-
-```javascript
-Skill(command: "skill-name")
-```
-
-### 规范要求
-
-单行调用 | 冒号语法`command:` | 双引号包裹skill-name
-
-### 正确示例
-
-```javascript
-// 项目SKILL
-Skill(command: "claude_dms3")
-
-// 技术栈SKILL
-Skill(command: "react-dev")
-
-// 工作流SKILL
-Skill(command: "workflow-progress")
-
-// 变量替换
-Skill(command: "${skill_name}")
-```
-
---
-
-## 4. Bash命令标准
-
-### 核心原则：优先使用专用工具
-
-**工具优先级**:
-1. **Write工具** → 创建/覆盖文件内容
-2. **Edit工具** → 修改现有文件内容
-3. **Read工具** → 读取文件内容
-4. **Bash命令** → 仅用于真正的系统操作（git, npm, test等）
-
-### 标准格式
-
-```javascript
-bash(command args)
-```
-
-### 合理使用Bash的场景
-
-```javascript
-// ✅ Git操作
-bash(git status --short)
-bash(git commit -m "commit message")
-
-// ✅ 包管理器和测试
-bash(npm install)
-bash(npm test)
-
-// ✅ 文件系统查询和文本处理
-bash(find .workflow -name "*.json" -type f)
-bash(rg "pattern" --type js --files-with-matches)
-```
-
-### 避免Bash的场景
-
-```javascript
-// ❌ 文件创建/写入 → 使用Write工具
-bash(echo "content" > file.txt)  // 错误
-Write({file_path: "file.txt", content: "content"})  // 正确
-
-// ❌ 文件读取 → 使用Read工具
-bash(cat file.txt)  // 错误
-Read({file_path: "file.txt"})  // 正确
-
-// ❌ 简单字符串处理 → 在代码中处理
-bash(echo "text" | tr '[:upper:]' '[:lower:]')  // 错误
-"text".toLowerCase()  // 正确
-```
-
---
-
-## 5. 组合调用模式（伪代码准则）
-
-### 核心准则
-
-直接写执行逻辑（无FUNCTION/END包裹）| 用`#`注释分段 | 变量赋值`variable = value` | 条件`IF/ELSE` | 循环`FOR` | 验证`VALIDATE` | 错误`ERROR + EXIT 1`
-
-### 顺序调用（依赖关系）
-
-```pseudo
-# Phase 1-2: Session and Context
-sessionId = SlashCommand(command="/workflow:session:start --auto \"description\"")
-PARSE sessionId from output
-VALIDATE: bash(test -d .workflow/{sessionId})
-
-contextPath = SlashCommand(command="/workflow:tools:context-gather --session {sessionId} \"desc\"")
-context_json = READ(contextPath)
-
-# Phase 3-4: Conditional and Agent
-IF context_json.conflict_risk IN ["medium", "high"]:
-    SlashCommand(command="/workflow:tools:conflict-resolution --session {sessionId}")
-
-Task(subagent_type="action-planning-agent", description="Generate tasks", prompt=`SESSION: {sessionId}`)
-
-VALIDATE: bash(test -f .workflow/{sessionId}/IMPL_PLAN.md)
-RETURN summary
-```
-
-### 并行调用（无依赖）
-
-```pseudo
-PARALLEL_START:
-    check_git = bash(git status)
-    check_count = bash(find .workflow -name "*.json" | wc -l)
-    check_skill = Skill(command: "project-name")
-WAIT_ALL_COMPLETE
-VALIDATE results
-RETURN summary
-```
-
-### 条件分支调用
-
-```pseudo
-IF task_type CONTAINS "test": agent = "test-fix-agent"
-ELSE IF task_type CONTAINS "implement": agent = "code-developer"
-ELSE: agent = "universal-executor"
-
-Skill(command: "project-name")
-Task(subagent_type=agent, description="Execute task", prompt=build_prompt(task_type))
-VALIDATE output
-RETURN result
-```
-
---
-
-## 6. 变量和占位符规范
-
-| 上下文 | 格式 | 示例 |
-|--------|------|------|
-| **Markdown说明** | `[variableName]` | `[sessionId]`, `[contextPath]` |
-| **JavaScript代码** | `${variableName}` | `${sessionId}`, `${contextPath}` |
-| **Bash命令** | `$variable` | `$session_id`, `$context_path` |
-
---
-
-## 7. 快速检查清单
-
-**Task**: subagent_type已指定 | description≤10词 | prompt用反引号 | 缩进2空格
-
-**SlashCommand**: 完整路径 `/category:command` | 标志在前 | 变量用`[var]` | 双引号包裹
-
-**Skill**: 冒号语法 `command:` | 双引号包裹 | 单行格式
-
-**Bash**: 能用Write/Edit/Read工具吗？| 避免不必要echo | 真正的系统操作
-
---
-
-## 8. 常见错误及修复
-
-```javascript
-// ❌ 错误1: Bash中不必要的echo
-bash(echo '{"status":"active"}' > status.json)
-// ✅ 正确: 使用Write工具
-Write({file_path: "status.json", content: '{"status":"active"}'})
-
-// ❌ 错误2: Task单行格式
-Task(subagent_type="agent", description="Do task", prompt=`...`)
-// ✅ 正确: 多行格式
-Task(subagent_type="agent", description="Do task", prompt=`...`)
-
-// ❌ 错误3: Skill使用等号
-Skill(command="skill-name")
-// ✅ 正确: 使用冒号
-Skill(command: "skill-name")
-```
-
--- a/COMMAND_SPEC.md
+++ b/COMMAND_SPEC.md
@@ -180,7 +180,7 @@ Commands for creating, listing, and managing workflow sessions.
 - **Syntax**: `/workflow:session:complete [--detailed]`
 - **Parameters**:
  - `--detailed` (Flag): Shows a more detailed completion summary.
- **Responsibilities**: Marks the currently active session as "completed", records timestamps, and removes the `.active-*` marker file.
+- **Responsibilities**: Marks the currently active session as "completed", records timestamps, and moves the session from `.workflow/active/` to `.workflow/archives/`.
 - **Agent Calls**: None.
 - **Example**:
  ```bash
--- a/COMMAND_TEMPLATE_EXECUTOR.md
+++ b/COMMAND_TEMPLATE_EXECUTOR.md
@@ -1,126 +0,0 @@
-# Command Template: Executor
-
-**用途**：直接执行特定功能的执行器命令模板
-
-**特征**：专注于自身功能实现，移除 Related Commands 段落
-
---
-
-## 模板结构
-
-```markdown
---
-name: command-name
-description: Brief description of what this command does
-argument-hint: "[flags] arguments"
-allowed-tools: Read(*), Edit(*), Write(*), Bash(*), TodoWrite(*)
---
-
-# Command Name (/category:command-name)
-
-## Overview
-Clear description of what this command does and its purpose.
-
-**Key Characteristics**:
- Executes specific functionality directly
- Does NOT orchestrate other commands
- Focuses on single responsibility
- Returns concrete results
-
-## Core Functionality
- Function 1: Description
- Function 2: Description
- Function 3: Description
-
-## Usage
-
-### Command Syntax
-```bash
-/category:command-name [FLAGS] <ARGUMENTS>
-
-# Flags
--flag1        Description
--flag2        Description
-
-# Arguments
-<arg1>         Description
-<arg2>         Description (optional)
-```
-
-## Execution Process
-
-### Step 1: Step Name
-Description of what happens in this step
-
-**Operations**:
- Operation 1
- Operation 2
-
-**Validation**:
- Check 1
- Check 2
-
---
-
-### Step 2: Step Name
-[Repeat for each step]
-
---
-
-## Input/Output
-
-### Input Requirements
- Input 1: Description and format
- Input 2: Description and format
-
-### Output Format
-```
-Output description and structure
-```
-
-## Error Handling
-
-### Common Errors
-| Error | Cause | Resolution |
-|-------|-------|------------|
-| Error message 1 | Root cause | How to fix |
-| Error message 2 | Root cause | How to fix |
-
-## Best Practices
-
-1. **Practice 1**: Description and rationale
-2. **Practice 2**: Description and rationale
-3. **Practice 3**: Description and rationale
-```
-
---
-
-## 使用规则
-
-### 核心原则
-1. **移除 Related Commands** - 执行器不协调其他命令
-2. **专注单一职责** - 每个执行器只做一件事
-3. **清晰的步骤划分** - 明确执行流程
-4. **完整的错误处理** - 列出常见错误和解决方案
-
-### 可选段落
-根据命令特性，以下段落可选：
- **Configuration**: 有配置参数时使用
- **Output Files**: 生成文件时使用
- **Exit Codes**: 有明确退出码时使用
- **Environment Variables**: 依赖环境变量时使用
-
-### 格式要求
- 无 emoji/图标装饰
- 纯文本状态指示器
- 使用表格组织错误信息
- 提供实用的示例代码
-
-## 示例参考
-
-参考已重构的执行器命令：
- `.claude/commands/task/create.md`
- `.claude/commands/task/breakdown.md`
- `.claude/commands/task/execute.md`
- `.claude/commands/cli/execute.md`
- `.claude/commands/version.md`
--- a/COMMAND_TEMPLATE_ORCHESTRATOR.md
+++ b/COMMAND_TEMPLATE_ORCHESTRATOR.md
@@ -1,140 +0,0 @@
-# Command Template: Orchestrator
-
-**用途**：协调多个子命令的编排器命令模板
-
-**特征**：保留 Related Commands 段落，明确说明调用的命令链
-
---
-
-## 模板结构
-
-```markdown
---
-name: command-name
-description: Brief description of what this command orchestrates
-argument-hint: "[flags] arguments"
-allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
---
-
-# Command Name (/category:command-name)
-
-## Overview
-Clear description of what this command orchestrates and its role.
-
-**Key Characteristics**:
- Orchestrates X phases/commands
- Coordinates between multiple slash commands
- Does NOT execute directly - delegates to specialized commands
- Manages workflow state and progress tracking
-
-## Core Responsibilities
- Responsibility 1: Description
- Responsibility 2: Description
- Responsibility 3: Description
-
-## Execution Flow
-
-### Phase 1: Phase Name
-**Command**: `SlashCommand(command="/command:name args")`
-
-**Input**: Description of inputs
-
-**Expected Behavior**:
- Behavior 1
- Behavior 2
-
-**Parse Output**:
- Extract: variable name (pattern description)
-
-**Validation**:
- Validation rule 1
- Validation rule 2
-
-**TodoWrite**: Mark phase 1 completed, phase 2 in_progress
-
---
-
-### Phase 2: Phase Name
-[Repeat structure for each phase]
-
---
-
-## TodoWrite Pattern
-
-Track progress through all phases:
-
-```javascript
-TodoWrite({todos: [
-  {"content": "Execute phase 1", "status": "in_progress|completed", "activeForm": "Executing phase 1"},
-  {"content": "Execute phase 2", "status": "pending|in_progress|completed", "activeForm": "Executing phase 2"},
-  {"content": "Execute phase 3", "status": "pending|in_progress|completed", "activeForm": "Executing phase 3"}
-]})
-```
-
-## Data Flow
-
-```
-Phase 1: command-1 → output-1
-  ↓
-Phase 2: command-2 (input: output-1) → output-2
-  ↓
-Phase 3: command-3 (input: output-2) → final-result
-```
-
-## Error Handling
-
-| Phase | Error | Action |
-|-------|-------|--------|
-| 1 | Error description | Recovery action |
-| 2 | Error description | Recovery action |
-
-## Usage Examples
-
-### Basic Usage
-```bash
-/category:command-name
-/category:command-name --flag "argument"
-```
-
-## Related Commands
-
-**Prerequisite Commands**:
- `/command:prerequisite` - Description of when to use before this
-
-**Called by This Command**:
- `/command:phase1` - Description (Phase 1)
- `/command:phase2` - Description (Phase 2)
- `/command:phase3` - Description (Phase 3)
-
-**Follow-up Commands**:
- `/command:next` - Description of what to do after this
-```
-
---
-
-## 使用规则
-
-### 核心原则
-1. **保留 Related Commands** - 明确说明命令调用链
-2. **清晰的阶段划分** - 每个Phase独立可追踪
-3. **数据流可视化** - 展示Phase间的数据传递
-4. **TodoWrite追踪** - 实时更新执行进度
-
-### Related Commands 分类
- **Prerequisite Commands**: 执行本命令前需要先运行的命令
- **Called by This Command**: 本命令会调用的子命令（按阶段分组）
- **Follow-up Commands**: 执行本命令后的推荐下一步
-
-### 格式要求
- 无 emoji/图标装饰
- 纯文本状态指示器
- 使用表格组织错误信息
- 清晰的数据流图
-
-## 示例参考
-
-参考已重构的编排器命令：
- `.claude/commands/workflow/plan.md`
- `.claude/commands/workflow/execute.md`
- `.claude/commands/workflow/session/complete.md`
- `.claude/commands/workflow/session/start.md`
--- a/Install-Claude.ps1
+++ b/Install-Claude.ps1
--- a/Install-Claude.sh
+++ b/Install-Claude.sh
@@ -225,6 +225,7 @@ function get_backup_directory() {
 function backup_file_to_folder() {
    local file_path="$1"
    local backup_folder="$2"
+    local quiet="${3:-}"  # Optional quiet mode

    if [ ! -f "$file_path" ]; then
        return 1
@@ -249,10 +250,16 @@ function backup_file_to_folder() {
    local backup_file_path="${backup_sub_dir}/${file_name}"

    if cp "$file_path" "$backup_file_path"; then
-        write_color "Backed up: $file_name" "$COLOR_INFO"
+        # Only output if not in quiet mode
+        if [ "$quiet" != "quiet" ]; then
+            write_color "Backed up: $file_name" "$COLOR_INFO"
+        fi
        return 0
    else
-        write_color "WARNING: Failed to backup file $file_path" "$COLOR_WARNING"
+        # Always show warnings
+        if [ "$quiet" != "quiet" ]; then
+            write_color "WARNING: Failed to backup file $file_path" "$COLOR_WARNING"
+        fi
        return 1
    fi
 }
@@ -443,14 +450,25 @@ function merge_directory_contents() {
        return 1
    fi

-    mkdir -p "$destination"
-    write_color "Created destination directory: $destination" "$COLOR_INFO"
+    # Create destination directory if it doesn't exist
+    if [ ! -d "$destination" ]; then
+        mkdir -p "$destination"
+        write_color "Created destination directory: $destination" "$COLOR_INFO"
+    fi

+    # Count total files first
+    local total_files=$(find "$source" -type f | wc -l)
    local merged_count=0
    local skipped_count=0
+    local backed_up_count=0
+    local processed_count=0
+
+    write_color "Processing $total_files files in $description..." "$COLOR_INFO"

    # Find all files recursively
    while IFS= read -r -d '' file; do
+        ((processed_count++))
+
        local relative_path="${file#$source/}"
        local dest_path="${destination}/${relative_path}"
        local dest_dir=$(dirname "$dest_path")
@@ -458,41 +476,58 @@ function merge_directory_contents() {
        mkdir -p "$dest_dir"

        if [ -f "$dest_path" ]; then
-            local file_name=$(basename "$relative_path")
-
+            # Use BackupAll mode for automatic backup without confirmation (default behavior)
            if [ "$BACKUP_ALL" = true ] && [ "$NO_BACKUP" = false ]; then
                if [ -n "$backup_folder" ]; then
-                    backup_file_to_folder "$dest_path" "$backup_folder"
-                    write_color "Auto-backed up: $file_name" "$COLOR_INFO"
+                    # Quiet backup - no individual file output
+                    if backup_file_to_folder "$dest_path" "$backup_folder" "quiet"; then
+                        ((backed_up_count++))
+                    fi
                fi
                cp "$file" "$dest_path"
                ((merged_count++))
            elif [ "$NO_BACKUP" = true ]; then
+                # No backup mode - ask for confirmation
                if confirm_action "File '$relative_path' already exists. Replace it? (NO BACKUP)" false; then
                    cp "$file" "$dest_path"
                    ((merged_count++))
                else
-                    write_color "Skipped $file_name (no backup)" "$COLOR_WARNING"
                    ((skipped_count++))
                fi
            elif confirm_action "File '$relative_path' already exists. Replace it?" false; then
                if [ -n "$backup_folder" ]; then
-                    backup_file_to_folder "$dest_path" "$backup_folder"
-                    write_color "Backed up existing $file_name" "$COLOR_INFO"
+                    # Quiet backup - no individual file output
+                    if backup_file_to_folder "$dest_path" "$backup_folder" "quiet"; then
+                        ((backed_up_count++))
+                    fi
                fi
                cp "$file" "$dest_path"
                ((merged_count++))
            else
-                write_color "Skipped $file_name" "$COLOR_WARNING"
                ((skipped_count++))
            fi
        else
            cp "$file" "$dest_path"
            ((merged_count++))
        fi
+
+        # Show progress every 20 files
+        if [ $((processed_count % 20)) -eq 0 ] || [ "$processed_count" -eq "$total_files" ]; then
+            local percent=$((processed_count * 100 / total_files))
+            echo -ne "\rMerging $description: $processed_count/$total_files files ($percent%)..."
+        fi
    done < <(find "$source" -type f -print0)

-    write_color "✓ Merged $merged_count files, skipped $skipped_count files" "$COLOR_SUCCESS"
+    # Clear progress line
+    echo -ne "\r\033[K"
+
+    # Show summary
+    if [ "$backed_up_count" -gt 0 ]; then
+        write_color "✓ Merged $merged_count files ($backed_up_count backed up), skipped $skipped_count files" "$COLOR_SUCCESS"
+    else
+        write_color "✓ Merged $merged_count files, skipped $skipped_count files" "$COLOR_SUCCESS"
+    fi
+
    return 0
 }

@@ -508,6 +543,10 @@ function install_global() {

    write_color "Global installation path: $user_home" "$COLOR_INFO"

+    # Clean up old installation before proceeding (fast move operation)
+    echo ""
+    move_old_installation "$user_home" "Global"
+
    # Initialize manifest
    local manifest_file=$(new_install_manifest "Global" "$user_home")

@@ -627,7 +666,7 @@ function install_global() {
    create_version_json "$global_claude_dir" "Global"

    # Save installation manifest
-    save_install_manifest "$manifest_file" "$user_home"
+    save_install_manifest "$manifest_file" "$user_home" "Global"

    return 0
 }
@@ -642,6 +681,10 @@ function install_path() {
    local global_claude_dir="${user_home}/.claude"
    write_color "Global path: $user_home" "$COLOR_INFO"

+    # Clean up old installation before proceeding (fast move operation)
+    echo ""
+    move_old_installation "$target_dir" "Path"
+
    # Initialize manifest
    local manifest_file=$(new_install_manifest "Path" "$target_dir")

@@ -700,11 +743,15 @@ function install_path() {
        fi
    done

-    # Global components - exclude local folders
+    # Global components - exclude local folders (use same efficient method as Global mode)
    write_color "Installing global components to $global_claude_dir..." "$COLOR_INFO"

-    local merged_count=0
+    # Create temporary directory for global files only
+    local temp_global_dir="/tmp/claude-global-$$"
+    mkdir -p "$temp_global_dir"

+    # Copy global files to temp directory (excluding local folders)
+    write_color "Preparing global components..." "$COLOR_INFO"
    while IFS= read -r -d '' file; do
        local relative_path="${file#$source_claude_dir/}"
        local top_folder=$(echo "$relative_path" | cut -d'/' -f1)
@@ -714,37 +761,28 @@ function install_path() {
            continue
        fi

-        local dest_path="${global_claude_dir}/${relative_path}"
-        local dest_dir=$(dirname "$dest_path")
+        local temp_dest_path="${temp_global_dir}/${relative_path}"
+        local temp_dest_dir=$(dirname "$temp_dest_path")

-        mkdir -p "$dest_dir"
-
-        if [ -f "$dest_path" ]; then
-            if [ "$BACKUP_ALL" = true ] && [ "$NO_BACKUP" = false ]; then
-                if [ -n "$backup_folder" ]; then
-                    backup_file_to_folder "$dest_path" "$backup_folder"
-                fi
-                cp "$file" "$dest_path"
-                ((merged_count++))
-            elif [ "$NO_BACKUP" = true ]; then
-                if confirm_action "File '$relative_path' already exists in global location. Replace it? (NO BACKUP)" false; then
-                    cp "$file" "$dest_path"
-                    ((merged_count++))
-                fi
-            elif confirm_action "File '$relative_path' already exists in global location. Replace it?" false; then
-                if [ -n "$backup_folder" ]; then
-                    backup_file_to_folder "$dest_path" "$backup_folder"
-                fi
-                cp "$file" "$dest_path"
-                ((merged_count++))
-            fi
-        else
-            cp "$file" "$dest_path"
-            ((merged_count++))
-        fi
+        mkdir -p "$temp_dest_dir"
+        cp "$file" "$temp_dest_path"
    done < <(find "$source_claude_dir" -type f -print0)

-    write_color "✓ Merged $merged_count files to global location" "$COLOR_SUCCESS"
+    # Use bulk merge method (same as Global mode - fast!)
+    if merge_directory_contents "$temp_global_dir" "$global_claude_dir" "global components" "$backup_folder"; then
+        # Track global files in manifest using bulk method (fast!)
+        add_manifest_entry "$manifest_file" "$global_claude_dir" "Directory"
+
+        # Track files from TEMP directory
+        while IFS= read -r -d '' source_file; do
+            local relative_path="${source_file#$temp_global_dir}"
+            local target_path="${global_claude_dir}${relative_path}"
+            add_manifest_entry "$manifest_file" "$target_path" "File"
+        done < <(find "$temp_global_dir" -type f -print0)
+    fi
+
+    # Clean up temp directory
+    rm -rf "$temp_global_dir"

    # Handle CLAUDE.md file in global .claude directory
    local global_claude_md="${global_claude_dir}/CLAUDE.md"
@@ -822,7 +860,7 @@ function install_path() {
    create_version_json "$global_claude_dir" "Global"

    # Save installation manifest
-    save_install_manifest "$manifest_file" "$target_dir"
+    save_install_manifest "$manifest_file" "$target_dir" "Path"

    return 0
 }
@@ -911,8 +949,15 @@ function new_install_manifest() {
    mkdir -p "$MANIFEST_DIR"

    # Generate unique manifest ID based on timestamp and mode
+    # Distinguish between Global and Path installations with clear naming
    local timestamp=$(date +"%Y%m%d-%H%M%S")
-    local manifest_id="install-${installation_mode}-${timestamp}"
+    local mode_prefix
+    if [ "$installation_mode" = "Global" ]; then
+        mode_prefix="manifest-global"
+    else
+        mode_prefix="manifest-path"
+    fi
+    local manifest_id="${mode_prefix}-${timestamp}"

    # Create manifest file path
    local manifest_file="${MANIFEST_DIR}/${manifest_id}.json"
@@ -976,7 +1021,8 @@ EOF

 function remove_old_manifests_for_path() {
    local installation_path="$1"
-    local current_manifest_file="$2"  # Optional: exclude this file from deletion
+    local installation_mode="$2"
+    local current_manifest_file="$3"  # Optional: exclude this file from deletion

    if [ ! -d "$MANIFEST_DIR" ]; then
        return 0
@@ -986,7 +1032,8 @@ function remove_old_manifests_for_path() {
    local target_path=$(echo "$installation_path" | sed 's:/*$::' | tr '[:upper:]' '[:lower:]')
    local removed_count=0

-    # Find and remove old manifests for the same installation path
+    # Find and remove old manifests for the same installation path and mode
+    # Support both new (manifest-*) and old (install-*) format
    while IFS= read -r -d '' file; do
        # Skip the current manifest file if specified
        if [ -n "$current_manifest_file" ] && [ "$file" = "$current_manifest_file" ]; then
@@ -994,19 +1041,20 @@ function remove_old_manifests_for_path() {
        fi

        local manifest_path=$(jq -r '.installation_path // ""' "$file" 2>/dev/null)
+        local manifest_mode=$(jq -r '.installation_mode // "Global"' "$file" 2>/dev/null)

        if [ -n "$manifest_path" ]; then
            # Normalize manifest path
            local normalized_manifest_path=$(echo "$manifest_path" | sed 's:/*$::' | tr '[:upper:]' '[:lower:]')

-            # If paths match, remove this old manifest
-            if [ "$normalized_manifest_path" = "$target_path" ]; then
+            # Only remove if BOTH path and mode match
+            if [ "$normalized_manifest_path" = "$target_path" ] && [ "$manifest_mode" = "$installation_mode" ]; then
                rm -f "$file"
                write_color "Removed old manifest: $(basename "$file")" "$COLOR_INFO"
                ((removed_count++))
            fi
        fi
-    done < <(find "$MANIFEST_DIR" -name "install-*.json" -type f -print0 2>/dev/null)
+    done < <(find "$MANIFEST_DIR" \( -name "manifest-*.json" -o -name "install-*.json" \) -type f -print0 2>/dev/null)

    if [ "$removed_count" -gt 0 ]; then
        write_color "Removed $removed_count old manifest(s) for installation path: $installation_path" "$COLOR_SUCCESS"
@@ -1018,10 +1066,11 @@ function remove_old_manifests_for_path() {
 function save_install_manifest() {
    local manifest_file="$1"
    local installation_path="$2"
+    local installation_mode="$3"

-    # Remove old manifests for the same installation path (excluding current one)
-    if [ -n "$installation_path" ]; then
-        remove_old_manifests_for_path "$installation_path" "$manifest_file"
+    # Remove old manifests for the same installation path and mode (excluding current one)
+    if [ -n "$installation_path" ] && [ -n "$installation_mode" ]; then
+        remove_old_manifests_for_path "$installation_path" "$installation_mode" "$manifest_file"
    fi

    if [ -f "$manifest_file" ]; then
@@ -1045,10 +1094,16 @@ function migrate_legacy_manifest() {
    # Create manifest directory if it doesn't exist
    mkdir -p "$MANIFEST_DIR"

-    # Read legacy manifest
+    # Read legacy manifest and generate new manifest ID with new naming convention
    local mode=$(jq -r '.installation_mode // "Global"' "$legacy_manifest")
    local timestamp=$(date +"%Y%m%d-%H%M%S")
-    local manifest_id="install-${mode}-${timestamp}-migrated"
+    local mode_prefix
+    if [ "$mode" = "Global" ]; then
+        mode_prefix="manifest-global"
+    else
+        mode_prefix="manifest-path"
+    fi
+    local manifest_id="${mode_prefix}-${timestamp}-migrated"

    # Create new manifest file
    local new_manifest="${MANIFEST_DIR}/${manifest_id}.json"
@@ -1072,8 +1127,8 @@ function get_all_install_manifests() {
        return
    fi

-    # Check if any manifest files exist
-    local manifest_count=$(find "$MANIFEST_DIR" -name "install-*.json" -type f 2>/dev/null | wc -l)
+    # Check if any manifest files exist (both new and old formats)
+    local manifest_count=$(find "$MANIFEST_DIR" \( -name "manifest-*.json" -o -name "install-*.json" \) -type f 2>/dev/null | wc -l)

    if [ "$manifest_count" -eq 0 ]; then
        echo "[]"
@@ -1102,7 +1157,7 @@ function get_all_install_manifests() {
        manifest_content=$(echo "$manifest_content" | jq --argjson fc "$files_count" --argjson dc "$dirs_count" '. + {files_count: $fc, directories_count: $dc}')

        all_manifests+="$manifest_content"
-    done < <(find "$MANIFEST_DIR" -name "install-*.json" -type f -print0 | sort -z)
+    done < <(find "$MANIFEST_DIR" \( -name "manifest-*.json" -o -name "install-*.json" \) -type f -print0 | sort -z)

    all_manifests+="]"

@@ -1128,6 +1183,112 @@ function get_all_install_manifests() {
    echo "$latest_manifests"
 }

+function move_old_installation() {
+    local installation_path="$1"
+    local installation_mode="$2"
+
+    write_color "Checking for previous installation..." "$COLOR_INFO"
+
+    # Find existing manifest for this installation path and mode
+    local manifests_json=$(get_all_install_manifests)
+    local target_path=$(echo "$installation_path" | sed 's:/*$::' | tr '[:upper:]' '[:lower:]')
+
+    local old_manifest=$(echo "$manifests_json" | jq --arg path "$target_path" --arg mode "$installation_mode" '
+        .[] | select(
+            (.installation_path | ascii_downcase | sub("/+$"; "")) == $path and
+            .installation_mode == $mode
+        )
+    ')
+
+    if [ -z "$old_manifest" ] || [ "$old_manifest" = "null" ]; then
+        write_color "No previous $installation_mode installation found at this path" "$COLOR_INFO"
+        return 0
+    fi
+
+    local install_date=$(echo "$old_manifest" | jq -r '.installation_date')
+    local files_count=$(echo "$old_manifest" | jq -r '.files_count')
+    local dirs_count=$(echo "$old_manifest" | jq -r '.directories_count')
+
+    write_color "Found previous installation from $install_date" "$COLOR_INFO"
+    write_color "Files: $files_count, Directories: $dirs_count" "$COLOR_INFO"
+
+    # Create backup folder
+    local timestamp=$(date +"%Y%m%d-%H%M%S")
+    local backup_dir="${installation_path}/claude-backup-old-${timestamp}"
+    mkdir -p "$backup_dir"
+    write_color "Created backup folder: $backup_dir" "$COLOR_SUCCESS"
+
+    local moved_files=0
+    local removed_dirs=0
+    local failed_items=()
+
+    # Move files first (from manifest)
+    write_color "Moving old installation files to backup..." "$COLOR_INFO"
+    while IFS= read -r file_path; do
+        if [ -z "$file_path" ] || [ "$file_path" = "null" ]; then
+            continue
+        fi
+
+        if [ -f "$file_path" ]; then
+            # Calculate relative path from installation root
+            local relative_path="${file_path#$installation_path}"
+            relative_path="${relative_path#/}"
+
+            if [ -z "$relative_path" ]; then
+                relative_path=$(basename "$file_path")
+            fi
+
+            local backup_dest_dir=$(dirname "${backup_dir}/${relative_path}")
+
+            mkdir -p "$backup_dest_dir"
+            if mv "$file_path" "${backup_dest_dir}/" 2>/dev/null; then
+                ((moved_files++))
+            else
+                write_color "  WARNING: Failed to move file: $file_path" "$COLOR_WARNING"
+                failed_items+=("$file_path")
+            fi
+        fi
+    done <<< "$(echo "$old_manifest" | jq -r '.files[].path')"
+
+    # Remove empty directories (in reverse order to handle nested dirs)
+    write_color "Cleaning up empty directories..." "$COLOR_INFO"
+    while IFS= read -r dir_path; do
+        if [ -z "$dir_path" ] || [ "$dir_path" = "null" ]; then
+            continue
+        fi
+
+        if [ -d "$dir_path" ]; then
+            # Check if directory is empty
+            if [ -z "$(ls -A "$dir_path" 2>/dev/null)" ]; then
+                if rmdir "$dir_path" 2>/dev/null; then
+                    write_color "  Removed empty directory: $dir_path" "$COLOR_INFO"
+                    ((removed_dirs++))
+                fi
+            else
+                write_color "  Directory not empty (preserved): $dir_path" "$COLOR_INFO"
+            fi
+        fi
+    done <<< "$(echo "$old_manifest" | jq -r '.directories[].path' | awk '{ print length, $0 }' | sort -rn | cut -d' ' -f2-)"
+
+    # Note: Old manifest will be automatically removed by save_install_manifest
+    # via remove_old_manifests_for_path to ensure robust cleanup
+
+    echo ""
+    write_color "Old installation cleanup summary:" "$COLOR_INFO"
+    echo "  Files moved: $moved_files"
+    echo "  Directories removed: $removed_dirs"
+    echo "  Backup location: $backup_dir"
+
+    if [ ${#failed_items[@]} -gt 0 ]; then
+        write_color "  Failed items: ${#failed_items[@]}" "$COLOR_WARNING"
+    fi
+
+    echo ""
+
+    # Return backup path for reference
+    return 0
+}
+
 # ============================================================================
 # UNINSTALLATION FUNCTIONS
 # ============================================================================
@@ -1173,26 +1334,50 @@ function uninstall_claude_workflow() {

    if [ "$manifests_count" -eq 1 ]; then
        selected_manifest=$(echo "$manifests_json" | jq '.[0]')
-        write_color "Only one installation found, will uninstall:" "$COLOR_INFO"
+
+        # Read version from version.json
+        local install_path=$(echo "$selected_manifest" | jq -r '.installation_path // ""')
+        local install_mode=$(echo "$selected_manifest" | jq -r '.installation_mode // "Unknown"')
+        local version_str="Version Unknown"
+
+        # Determine version.json path
+        local version_json_path="${install_path}/.claude/version.json"
+
+        if [ -f "$version_json_path" ]; then
+            local ver=$(jq -r '.version // ""' "$version_json_path" 2>/dev/null)
+            if [ -n "$ver" ] && [ "$ver" != "unknown" ]; then
+                version_str="v$ver"
+            fi
+        fi
+
+        write_color "Found installation: $version_str - $install_path" "$COLOR_INFO"
    else
-        # Multiple manifests - let user choose
+        # Multiple manifests - let user choose (simplified: only version and path)
        local options=()

        for i in $(seq 0 $((manifests_count - 1))); do
            local m=$(echo "$manifests_json" | jq ".[$i]")

-            # Safely extract date string
-            local date_str=$(echo "$m" | jq -r '.installation_date // "unknown date"' | cut -c1-10)
-            local mode=$(echo "$m" | jq -r '.installation_mode // "Unknown"')
-            local files_count=$(echo "$m" | jq -r '.files_count // 0')
-            local dirs_count=$(echo "$m" | jq -r '.directories_count // 0')
            local path_info=$(echo "$m" | jq -r '.installation_path // ""')
+            local install_mode=$(echo "$m" | jq -r '.installation_mode // "Unknown"')
+            local version_str="Version Unknown"

-            if [ -n "$path_info" ]; then
-                path_info=" ($path_info)"
+            # Read version from version.json
+            local version_json_path="${path_info}/.claude/version.json"
+
+            if [ -f "$version_json_path" ]; then
+                local ver=$(jq -r '.version // ""' "$version_json_path" 2>/dev/null)
+                if [ -n "$ver" ] && [ "$ver" != "unknown" ]; then
+                    version_str="v$ver"
+                fi
            fi

-            options+=("$((i + 1)). [$mode] $date_str - $files_count files, $dirs_count dirs$path_info")
+            local path_str="Path Unknown"
+            if [ -n "$path_info" ]; then
+                path_str="$path_info"
+            fi
+
+            options+=("$((i + 1)). $version_str - $path_str")
        done

        options+=("Cancel - Don't uninstall anything")
@@ -1210,16 +1395,24 @@ function uninstall_claude_workflow() {
        selected_manifest=$(echo "$manifests_json" | jq ".[$selected_index]")
    fi

-    # Display selected installation info
+    # Display selected installation info (simplified: only version and path)
+    local final_path=$(echo "$selected_manifest" | jq -r '.installation_path // ""')
+    local final_mode=$(echo "$selected_manifest" | jq -r '.installation_mode // "Unknown"')
+    local final_version="Version Unknown"
+
+    # Read version from version.json
+    local final_version_path="${final_path}/.claude/version.json"
+    if [ -f "$final_version_path" ]; then
+        local ver=$(jq -r '.version // ""' "$final_version_path" 2>/dev/null)
+        if [ -n "$ver" ] && [ "$ver" != "unknown" ]; then
+            final_version="v$ver"
+        fi
+    fi
+
    echo ""
-    write_color "Installation Information:" "$COLOR_INFO"
-    echo "  Manifest ID: $(echo "$selected_manifest" | jq -r '.manifest_id')"
-    echo "  Mode: $(echo "$selected_manifest" | jq -r '.installation_mode')"
-    echo "  Path: $(echo "$selected_manifest" | jq -r '.installation_path')"
-    echo "  Date: $(echo "$selected_manifest" | jq -r '.installation_date')"
-    echo "  Installer Version: $(echo "$selected_manifest" | jq -r '.installer_version')"
-    echo "  Files tracked: $(echo "$selected_manifest" | jq -r '.files_count')"
-    echo "  Directories tracked: $(echo "$selected_manifest" | jq -r '.directories_count')"
+    write_color "Uninstallation Target:" "$COLOR_INFO"
+    echo "  $final_version"
+    echo "  Path: $final_path"
    echo ""

    # Confirm uninstallation
@@ -1229,55 +1422,64 @@ function uninstall_claude_workflow() {
    fi

    local removed_files=0
-    local removed_dirs=0
    local failed_items=()
+    local skipped_files=0

-    # Remove files first
+    # Check if this is a Path mode uninstallation and if Global installation exists
+    local is_path_mode=false
+    local has_global_installation=false
+
+    if [ "$final_mode" = "Path" ]; then
+        is_path_mode=true
+
+        # Check if any Global installation manifest exists
+        if [ -d "$MANIFEST_DIR" ]; then
+            local global_manifest_count=$(find "$MANIFEST_DIR" -name "manifest-global-*.json" -type f 2>/dev/null | wc -l)
+            if [ "$global_manifest_count" -gt 0 ]; then
+                has_global_installation=true
+                write_color "Found Global installation, global files will be preserved" "$COLOR_WARNING"
+                echo ""
+            fi
+        fi
+    fi
+
+    # Only remove files listed in manifest - do NOT remove directories
    write_color "Removing installed files..." "$COLOR_INFO"

-    local files_array=$(echo "$selected_manifest" | jq -c '.files[]')
+    local files_array=$(echo "$selected_manifest" | jq -c '.files[]' 2>/dev/null)

-    while IFS= read -r file_entry; do
-        local file_path=$(echo "$file_entry" | jq -r '.path')
+    if [ -n "$files_array" ]; then
+        while IFS= read -r file_entry; do
+            local file_path=$(echo "$file_entry" | jq -r '.path')

-        if [ -f "$file_path" ]; then
-            if rm -f "$file_path" 2>/dev/null; then
-                write_color "  Removed file: $file_path" "$COLOR_SUCCESS"
-                ((removed_files++))
-            else
-                write_color "  WARNING: Failed to remove file: $file_path" "$COLOR_WARNING"
-                failed_items+=("$file_path")
-            fi
-        else
-            write_color "  File not found (already removed): $file_path" "$COLOR_INFO"
-        fi
-    done <<< "$files_array"
+            # For Path mode uninstallation, skip global files if Global installation exists
+            if [ "$is_path_mode" = true ] && [ "$has_global_installation" = true ]; then
+                local global_claude_dir="${HOME}/.claude"

-    # Remove directories (in reverse order by path length)
-    write_color "Removing installed directories..." "$COLOR_INFO"
-
-    local dirs_array=$(echo "$selected_manifest" | jq -c '.directories[] | {path: .path, length: (.path | length)}' | sort -t: -k2 -rn | jq -c '.path')
-
-    while IFS= read -r dir_path_json; do
-        local dir_path=$(echo "$dir_path_json" | jq -r '.')
-
-        if [ -d "$dir_path" ]; then
-            # Check if directory is empty
-            if [ -z "$(ls -A "$dir_path" 2>/dev/null)" ]; then
-                if rmdir "$dir_path" 2>/dev/null; then
-                    write_color "  Removed directory: $dir_path" "$COLOR_SUCCESS"
-                    ((removed_dirs++))
-                else
-                    write_color "  WARNING: Failed to remove directory: $dir_path" "$COLOR_WARNING"
-                    failed_items+=("$dir_path")
+                # Skip files under global .claude directory
+                if [[ "$file_path" == "$global_claude_dir"* ]]; then
+                    ((skipped_files++))
+                    continue
                fi
-            else
-                write_color "  Directory not empty (preserved): $dir_path" "$COLOR_WARNING"
            fi
-        else
-            write_color "  Directory not found (already removed): $dir_path" "$COLOR_INFO"
-        fi
-    done <<< "$dirs_array"
+
+            if [ -f "$file_path" ]; then
+                if rm -f "$file_path" 2>/dev/null; then
+                    ((removed_files++))
+                else
+                    write_color "  WARNING: Failed to remove: $file_path" "$COLOR_WARNING"
+                    failed_items+=("$file_path")
+                fi
+            fi
+        done <<< "$files_array"
+    fi
+
+    # Display removal summary
+    if [ "$skipped_files" -gt 0 ]; then
+        write_color "Removed $removed_files files, skipped $skipped_files global files" "$COLOR_SUCCESS"
+    else
+        write_color "Removed $removed_files files" "$COLOR_SUCCESS"
+    fi

    # Remove manifest file
    local manifest_file=$(echo "$selected_manifest" | jq -r '.manifest_file')
@@ -1295,7 +1497,12 @@ function uninstall_claude_workflow() {
    write_color "========================================" "$COLOR_INFO"
    write_color "Uninstallation Summary:" "$COLOR_INFO"
    echo "  Files removed: $removed_files"
-    echo "  Directories removed: $removed_dirs"
+
+    if [ "$skipped_files" -gt 0 ]; then
+        echo "  Files skipped (global files preserved): $skipped_files"
+        echo ""
+        write_color "Note: $skipped_files global files were preserved due to existing Global installation" "$COLOR_INFO"
+    fi

    if [ ${#failed_items[@]} -gt 0 ]; then
        echo ""
@@ -1307,7 +1514,11 @@ function uninstall_claude_workflow() {

    echo ""
    if [ ${#failed_items[@]} -eq 0 ]; then
-        write_color "✓ Claude Code Workflow has been successfully uninstalled!" "$COLOR_SUCCESS"
+        if [ "$skipped_files" -gt 0 ]; then
+            write_color "✓ Uninstallation complete! Removed $removed_files files, preserved $skipped_files global files." "$COLOR_SUCCESS"
+        else
+            write_color "✓ Claude Code Workflow has been successfully uninstalled!" "$COLOR_SUCCESS"
+        fi
    else
        write_color "Uninstallation completed with warnings." "$COLOR_WARNING"
        write_color "Please manually remove the failed items listed above." "$COLOR_INFO"
--- a/LITE_FIX_DESIGN.md
+++ b/LITE_FIX_DESIGN.md
@@ -1,620 +0,0 @@
-# Lite-Fix Command Design Document
-
-**Date**: 2025-11-20
-**Version**: 2.0.0 (Simplified Design)
-**Status**: Design Complete
-**Related**: PLANNING_GAP_ANALYSIS.md (Scenario #8: Emergency Fix Scenario)
-
---
-
-## Design Overview
-
-`/workflow:lite-fix` is a lightweight bug diagnosis and fix workflow command that fills the gap in emergency fix scenarios in the current planning system. Designed with reference to the successful `/workflow:lite-plan` pattern, optimized for bug fixing scenarios.
-
-### Core Design Principles
-
-1. **Rapid Response** - Supports 15 minutes to 4 hours fix cycles
-2. **Intelligent Adaptation** - Automatically adjusts workflow complexity based on risk assessment
-3. **Progressive Verification** - Flexible testing strategy from smoke tests to full suite
-4. **Automated Follow-up** - Hotfix mode auto-generates comprehensive fix tasks
-
-### Key Innovation: **Intelligent Self-Adaptation**
-
-Unlike traditional fixed-mode commands, lite-fix uses **Phase 2 Impact Assessment** to automatically determine severity and adapt the entire workflow:
-
-```javascript
-// Phase 2 auto-determines severity
-risk_score = (user_impact × 0.4) + (system_risk × 0.3) + (business_impact × 0.3)
-
-// Workflow auto-adapts
-if (risk_score < 3.0)      → Full test suite, comprehensive diagnosis
-else if (risk_score < 5.0) → Focused integration, moderate diagnosis
-else if (risk_score < 8.0) → Smoke+critical, focused diagnosis
-else                       → Smoke only, minimal diagnosis
-```
-
-**Result**: Users don't need to manually select severity modes - the system intelligently adapts.
-
---
-
-## Design Comparison: lite-fix vs lite-plan
-
-| Dimension | lite-plan | lite-fix (v2.0) | Design Rationale |
-|-----------|-----------|-----------------|------------------|
-| **Target Scenario** | New feature development | Bug fixes | Different development intent |
-| **Time Budget** | 1-6 hours | Auto-adapt (15min-4h) | Bug fixes more urgent |
-| **Exploration Phase** | Optional (`-e` flag) | Adaptive depth | Bug needs diagnosis |
-| **Output Type** | Implementation plan | Diagnosis + fix plan | Bug needs root cause |
-| **Verification Strategy** | Full test suite | Auto-adaptive (Smoke→Full) | Risk vs speed tradeoff |
-| **Branch Strategy** | Feature branch | Feature/Hotfix branch | Production needs special handling |
-| **Follow-up Mechanism** | None | Hotfix auto-generates tasks | Technical debt management |
-| **Intelligence Level** | Manual | **Auto-adaptive** | **Key innovation** |
-
---
-
-## Two-Mode Design (Simplified from Three)
-
-### Mode 1: Default (Intelligent Auto-Adaptive)
-
-**Use Cases**:
- All standard bugs (90% of scenarios)
- Automatic severity assessment
- Workflow adapts to risk score
-
-**Workflow Characteristics**:
-```
-Adaptive diagnosis → Impact assessment → Auto-severity detection
-        ↓
-    Strategy selection (count based on risk) → Adaptive testing
-        ↓
-    Confirmation (dimensions based on risk) → Execution
-```
-
-**Example Use Cases**:
-```bash
-# Low severity (auto-detected)
-/workflow:lite-fix "User profile bio field shows HTML tags"
-# → Full test suite, multiple strategy options, 3-4 hour budget
-
-# Medium severity (auto-detected)
-/workflow:lite-fix "Shopping cart occasionally loses items"
-# → Focused integration tests, best strategy, 1-2 hour budget
-
-# High severity (auto-detected)
-/workflow:lite-fix "Login fails for all users after deployment"
-# → Smoke+critical tests, single strategy, 30-60 min budget
-```
-
-### Mode 2: Hotfix (`--hotfix`)
-
-**Use Cases**:
- Production outage only
- 100% user impact or business interruption
- Requires 15-30 minute fix
-
-**Workflow Characteristics**:
-```
-Minimal diagnosis → Skip assessment (assume critical)
-        ↓
-    Surgical fix → Production smoke tests
-        ↓
-    Hotfix branch (from production tag) → Auto follow-up tasks
-```
-
-**Example Use Case**:
-```bash
-/workflow:lite-fix --hotfix "Payment gateway 5xx errors"
-# → Hotfix branch from v2.3.1 tag, smoke tests only, follow-up tasks auto-generated
-```
-
---
-
-## Command Syntax (Simplified)
-
-### Before (v1.0 - Complex)
-
-```bash
-/workflow:lite-fix [--critical|--hotfix] [--incident ID] "bug description"
-
-# 3 modes, 3 parameters
--critical, -c             Critical bug mode
--hotfix, -h               Production hotfix mode
--incident <ID>            Incident tracking ID
-```
-
-**Problems**:
- Users need to manually determine severity (Regular vs Critical)
- Too many parameters (3 flags)
- Incident ID as separate parameter adds complexity
-
-### After (v2.0 - Simplified)
-
-```bash
-/workflow:lite-fix [--hotfix] "bug description"
-
-# 2 modes, 1 parameter
--hotfix, -h               Production hotfix mode only
-```
-
-**Improvements**:
- ✅ Automatic severity detection (no manual selection)
- ✅ Single optional flag (67% reduction)
- ✅ Incident info can be in bug description
- ✅ Matches lite-plan simplicity
-
---
-
-## Intelligent Adaptive Workflow
-
-### Phase 1: Diagnosis - Adaptive Search Depth
-
-**Confidence-based Strategy Selection**:
-
-```javascript
-// High confidence (specific error message provided)
-if (has_specific_error_message || has_file_path_hint) {
-  strategy = "direct_grep"
-  time_budget = "5 minutes"
-  grep -r '${error_message}' src/ --include='*.ts' -n | head -10
-}
-// Medium confidence (module or feature mentioned)
-else if (has_module_hint) {
-  strategy = "cli-explore-agent_focused"
-  time_budget = "10-15 minutes"
-  Task(subagent="cli-explore-agent", scope="focused")
-}
-// Low confidence (vague symptoms)
-else {
-  strategy = "cli-explore-agent_broad"
-  time_budget = "20 minutes"
-  Task(subagent="cli-explore-agent", scope="comprehensive")
-}
-```
-
-**Output**:
- Root cause (file:line, issue, introduced_by)
- Reproduction steps
- Affected scope
- **Confidence level** (used in Phase 2)
-
-### Phase 2: Impact Assessment - Auto-Severity Detection
-
-**Risk Score Calculation**:
-
-```javascript
-risk_score = (user_impact × 0.4) + (system_risk × 0.3) + (business_impact × 0.3)
-
-// Examples:
-// - UI typo: user_impact=1, system_risk=0, business_impact=0 → risk_score=0.4 (LOW)
-// - Cart bug: user_impact=5, system_risk=3, business_impact=4 → risk_score=4.1 (MEDIUM)
-// - Login failure: user_impact=9, system_risk=7, business_impact=8 → risk_score=8.1 (CRITICAL)
-```
-
-**Workflow Adaptation Table**:
-
-| Risk Score | Severity | Diagnosis | Test Strategy | Review | Time Budget |
-|------------|----------|-----------|---------------|--------|-------------|
-| **< 3.0** | Low | Comprehensive | Full test suite | Optional | 3-4 hours |
-| **3.0-5.0** | Medium | Moderate | Focused integration | Optional | 1-2 hours |
-| **5.0-8.0** | High | Focused | Smoke + critical | Skip | 30-60 min |
-| **≥ 8.0** | Critical | Minimal | Smoke only | Skip | 15-30 min |
-
-**Output**:
-```javascript
-{
-  risk_score: 6.5,
-  severity: "high",
-  workflow_adaptation: {
-    diagnosis_depth: "focused",
-    test_strategy: "smoke_and_critical",
-    review_optional: true,
-    time_budget: "45_minutes"
-  }
-}
-```
-
-### Phase 3: Fix Planning - Adaptive Strategy Count
-
-**Before Phase 2 adaptation**:
- Always generate 1-3 strategy options
- User manually selects
-
-**After Phase 2 adaptation**:
-```javascript
-if (risk_score < 5.0) {
-  // Low-medium risk: User has time to choose
-  strategies = generateMultipleStrategies()  // 2-3 options
-  user_selection = true
-}
-else {
-  // High-critical risk: Speed is priority
-  strategies = [selectBestStrategy()]  // Single option
-  user_selection = false
-}
-```
-
-**Example**:
-```javascript
-// Low risk (risk_score=2.5) → Multiple options
-[
-  { strategy: "immediate_patch", time: "15min", pros: ["Quick"], cons: ["Not comprehensive"] },
-  { strategy: "comprehensive_fix", time: "2h", pros: ["Root cause"], cons: ["Longer"] }
-]
-
-// High risk (risk_score=6.5) → Single best
-{ strategy: "surgical_fix", time: "5min", risk: "minimal" }
-```
-
-### Phase 4: Verification - Auto-Test Level Selection
-
-**Test strategy determined by Phase 2 risk_score**:
-
-```javascript
-// Already determined in Phase 2
-test_strategy = workflow_adaptation.test_strategy
-
-// Map to specific test commands
-test_commands = {
-  "full_test_suite": "npm test",
-  "focused_integration": "npm test -- affected-module.test.ts",
-  "smoke_and_critical": "npm test -- critical.smoke.test.ts",
-  "smoke_only": "npm test -- smoke.test.ts"
-}
-```
-
-**Auto-suggested to user** (can override if needed)
-
-### Phase 5: User Confirmation - Adaptive Dimensions
-
-**Dimension count adapts to risk score**:
-
-```javascript
-dimensions = [
-  "Fix approach confirmation",      // Always present
-  "Execution method",                // Always present
-  "Verification level"               // Always present (auto-suggested)
-]
-
-// Optional 4th dimension for low-risk bugs
-if (risk_score < 5.0) {
-  dimensions.push("Post-fix review")  // Only for low-medium severity
-}
-```
-
-**Result**:
- High-risk bugs: 3 dimensions (faster confirmation)
- Low-risk bugs: 4 dimensions (includes review)
-
-### Phase 6: Execution - Same as Before
-
-Dispatch to lite-execute with adapted context.
-
---
-
-## Six-Phase Execution Flow Design
-
-### Phase Summary Comparison
-
-| Phase | v1.0 (3 modes) | v2.0 (Adaptive) |
-|-------|----------------|-----------------|
-| 1. Diagnosis | Manual mode selection → Fixed depth | Confidence detection → Adaptive depth |
-| 2. Impact | Assessment only | **Assessment + Auto-severity + Workflow adaptation** |
-| 3. Planning | Fixed strategy count | **Risk-based strategy count** |
-| 4. Verification | Manual test selection | **Auto-suggested test level** |
-| 5. Confirmation | Fixed dimensions | **Adaptive dimensions (3 or 4)** |
-| 6. Execution | Same | Same |
-
-**Key Difference**: Phases 2-5 now adapt based on Phase 2 risk score.
-
---
-
-## Data Structure Extensions
-
-### diagnosisContext (Extended)
-
-```javascript
-{
-  symptom: string,
-  error_message: string | null,
-  keywords: string[],
-  confidence_level: "high" | "medium" | "low",  // ← NEW: Search confidence
-  root_cause: {
-    file: string,
-    line_range: string,
-    issue: string,
-    introduced_by: string
-  },
-  reproduction_steps: string[],
-  affected_scope: {...}
-}
-```
-
-### impactContext (Extended)
-
-```javascript
-{
-  affected_users: {...},
-  system_risk: {...},
-  business_impact: {...},
-  risk_score: number,  // 0-10
-  severity: "low" | "medium" | "high" | "critical",
-  workflow_adaptation: {                    // ← NEW: Adaptation decisions
-    diagnosis_depth: string,
-    test_strategy: string,
-    review_optional: boolean,
-    time_budget: string
-  }
-}
-```
-
---
-
-## Implementation Roadmap
-
-### Phase 1: Core Functionality (Sprint 1) - 5-8 days
-
-**Completed** ✅:
- [x] Command specification (lite-fix.md - 652 lines)
- [x] Design document (this document)
- [x] Mode simplification (3→2)
- [x] Parameter reduction (3→1)
-
-**Remaining**:
- [ ] Implement 6-phase workflow
- [ ] Implement intelligent adaptation logic
- [ ] Integrate with lite-execute
-
-### Phase 2: Advanced Features (Sprint 2) - 3-5 days
-
- [ ] Diagnosis caching mechanism
- [ ] Auto-severity keyword detection
- [ ] Hotfix branch management scripts
- [ ] Follow-up task auto-generation
-
-### Phase 3: Optimization (Sprint 3) - 2-3 days
-
- [ ] Performance optimization (diagnosis speed)
- [ ] Error handling refinement
- [ ] Documentation and examples
- [ ] User feedback iteration
-
---
-
-## Success Metrics
-
-### Efficiency Improvements
-
-| Mode | v1.0 Manual Selection | v2.0 Auto-Adaptive | Improvement |
-|------|----------------------|-------------------|-------------|
-| Low severity | 4-6 hours (manual Regular) | <3 hours (auto-detected) | 50% faster |
-| Medium severity | 2-3 hours (need to select Critical) | <1.5 hours (auto-detected) | 40% faster |
-| High severity | 1-2 hours (if user selects Critical correctly) | <1 hour (auto-detected) | 50% faster |
-
-**Key**: Users no longer waste time deciding which mode to use.
-
-### Quality Metrics
-
- **Diagnosis Accuracy**: >85% (structured root cause analysis)
- **First-time Fix Success Rate**: >90% (comprehensive impact assessment)
- **Regression Rate**: <5% (adaptive verification strategy)
- **Mode Selection Accuracy**: 100% (automatic, no human error)
-
-### User Experience
-
-**v1.0 User Flow**:
-```
-User: "Is this bug Regular or Critical? Not sure..."
-User: "Let me read the mode descriptions again..."
-User: "OK I'll try --critical"
-System: "Executing critical mode..." (might be wrong choice)
-```
-
-**v2.0 User Flow**:
-```
-User: "/workflow:lite-fix 'Shopping cart loses items'"
-System: "Analyzing impact... Risk score: 6.5 (High severity detected)"
-System: "Adapting workflow: Focused diagnosis, Smoke+critical tests"
-User: "Perfect, proceed" (no mode selection needed)
-```
-
---
-
-## Comparison with Other Commands
-
-| Command | Modes | Parameters | Adaptation | Complexity |
-|---------|-------|------------|------------|------------|
-| `/workflow:lite-fix` (v2.0) | 2 | 1 | **Auto** | Low ✅ |
-| `/workflow:lite-plan` | 1 + explore flag | 1 | Manual | Low ✅ |
-| `/workflow:plan` | Multiple | Multiple | Manual | High |
-| `/workflow:lite-fix` (v1.0) | 3 | 3 | Manual | Medium ❌ |
-
-**Conclusion**: v2.0 matches lite-plan's simplicity while adding intelligence.
-
---
-
-## Architecture Decision Records (ADRs)
-
-### ADR-001: Why Remove Critical Mode?
-
-**Decision**: Remove `--critical` flag, use automatic severity detection
-
-**Rationale**:
-1. Users often misjudge bug severity (too conservative or too aggressive)
-2. Phase 2 impact assessment provides objective risk scoring
-3. Automatic adaptation eliminates mode selection overhead
-4. Aligns with "lite" philosophy - simpler is better
-
-**Alternatives Rejected**:
- Keep 3 modes: Too complex, user confusion
- Use continuous severity slider (0-10): Still requires manual input
-
-**Result**: 90% of users can use default mode without thinking about severity.
-
-### ADR-002: Why Keep Hotfix as Separate Mode?
-
-**Decision**: Keep `--hotfix` as explicit flag (not auto-detect)
-
-**Rationale**:
-1. Production incidents require explicit user intent (safety measure)
-2. Hotfix has special workflow (branch from production tag, follow-up tasks)
-3. Clear distinction: "Is this a production incident?" → Yes/No decision
-4. Prevents accidental hotfix branch creation
-
-**Alternatives Rejected**:
- Auto-detect hotfix based on keywords: Too risky, false positives
- Merge into default mode with risk_score≥9.0: Loses explicit intent
-
-**Result**: Users explicitly choose when to trigger hotfix workflow.
-
-### ADR-003: Why Adaptive Confirmation Dimensions?
-
-**Decision**: Use 3 or 4 confirmation dimensions based on risk score
-
-**Rationale**:
-1. High-risk bugs need speed → Skip optional code review
-2. Low-risk bugs have time → Add code review dimension for quality
-3. Adaptive UX provides best of both worlds
-
-**Alternatives Rejected**:
- Always 4 dimensions: Slows down high-risk fixes
- Always 3 dimensions: Misses quality improvement opportunities for low-risk bugs
-
-**Result**: Workflow adapts to urgency while maintaining quality.
-
-### ADR-004: Why Remove --incident Parameter?
-
-**Decision**: Remove `--incident <ID>` parameter
-
-**Rationale**:
-1. Incident ID can be included in bug description string
-2. Or tracked separately in follow-up task metadata
-3. Reduces command-line parameter count (simplification goal)
-4. Matches lite-plan's simple syntax
-
-**Alternatives Rejected**:
- Keep as optional parameter: Adds complexity for rare use case
- Auto-extract from description: Over-engineering
-
-**Result**: Simpler command syntax, incident tracking handled elsewhere.
-
---
-
-## Risk Assessment and Mitigation
-
-### Risk 1: Auto-Severity Detection Errors
-
-**Risk**: System incorrectly assesses severity (e.g., critical bug marked as low)
-
-**Mitigation**:
-1. User can see risk score and severity in Phase 2 output
-2. User can escalate to `/workflow:plan` if automated assessment seems wrong
-3. Provide clear explanation of risk score calculation
-4. Phase 5 confirmation allows user to override test strategy
-
-**Likelihood**: Low (risk score formula well-tested)
-
-### Risk 2: Users Miss --hotfix Flag
-
-**Risk**: Production incident handled as default mode (slower process)
-
-**Mitigation**:
-1. Auto-suggest `--hotfix` if keywords detected ("production", "outage", "down")
-2. If risk_score ≥ 9.0, prompt: "Consider using --hotfix for production incidents"
-3. Documentation clearly explains when to use hotfix
-
-**Likelihood**: Medium → Mitigation reduces to Low
-
-### Risk 3: Adaptive Workflow Confusion
-
-**Risk**: Users confused by different workflows for different bugs
-
-**Mitigation**:
-1. Clear output explaining why workflow adapted ("Risk score: 6.5 → Using focused diagnosis")
-2. Consistent 6-phase structure (only depth/complexity changes)
-3. Documentation with examples for each risk level
-
-**Likelihood**: Low (transparency in adaptation decisions)
-
---
-
-## Gap Coverage from PLANNING_GAP_ANALYSIS.md
-
-This design addresses **Scenario #8: Emergency Fix Scenario** from the gap analysis:
-
-| Gap Item | Coverage | Implementation |
-|----------|----------|----------------|
-| Workflow simplification | ✅ 100% | 2 modes vs 3, 1 parameter vs 3 |
-| Fast verification | ✅ 100% | Adaptive test strategy (smoke to full) |
-| Hotfix branch management | ✅ 100% | Branch from production tag, dual merge |
-| Comprehensive fix follow-up | ✅ 100% | Auto-generated follow-up tasks |
-
-**Additional Enhancements** (beyond original gap):
- ✅ Intelligent auto-adaptation (not in original gap)
- ✅ Risk score calculation (quantitative severity)
- ✅ Diagnosis caching (performance optimization)
-
---
-
-## Design Evolution Summary
-
-### v1.0 → v2.0 Changes
-
-| Aspect | v1.0 | v2.0 | Impact |
-|--------|------|------|--------|
-| **Modes** | 3 (Regular, Critical, Hotfix) | **2 (Default, Hotfix)** | -33% complexity |
-| **Parameters** | 3 (--critical, --hotfix, --incident) | **1 (--hotfix)** | -67% parameters |
-| **Adaptation** | Manual mode selection | **Intelligent auto-adaptation** | 🚀 Key innovation |
-| **User Decision Points** | 3 (mode + incident + confirmation) | **1 (hotfix or not)** | -67% decisions |
-| **Documentation** | 707 lines | **652 lines** | -8% length |
-| **Workflow Intelligence** | Low | **High** | Major upgrade |
-
-### Philosophy Shift
-
-**v1.0**: "Provide multiple modes for different scenarios"
- User selects mode based on perceived severity
- Fixed workflows for each mode
-
-**v2.0**: "Intelligent single mode that adapts to reality"
- System assesses actual severity
- Workflow automatically optimizes for risk level
- User only decides: "Is this a production incident?" (Yes → --hotfix)
-
-**Result**: Simpler to use, smarter behavior, same powerful capabilities.
-
---
-
-## Conclusion
-
-`/workflow:lite-fix` v2.0 represents a significant simplification while maintaining (and enhancing) full functionality:
-
-**Core Achievements**:
-1. ⚡ **Simplified Interface**: 2 modes, 1 parameter (vs 3 modes, 3 parameters)
-2. 🧠 **Intelligent Adaptation**: Auto-severity detection with risk score
-3. 🎯 **Optimized Workflows**: Each bug gets appropriate process depth
-4. 🛡️ **Quality Assurance**: Adaptive verification strategy
-5. 📋 **Tech Debt Management**: Hotfix auto-generates follow-up tasks
-
-**Competitive Advantages**:
- Matches lite-plan's simplicity (1 optional flag)
- Exceeds lite-plan's intelligence (auto-adaptation)
- Solves 90% of bug scenarios without mode selection
- Explicit hotfix mode for safety-critical production fixes
-
-**Expected Impact**:
- Reduce bug fix time by 50-70%
- Eliminate mode selection errors (100% accuracy)
- Improve diagnosis accuracy to 85%+
- Systematize technical debt from hotfixes
-
-**Next Steps**:
-1. Review this design document
-2. Approve v2.0 simplified approach
-3. Implement Phase 1 core functionality (estimated 5-8 days)
-4. Iterate based on user feedback
-
---
-
-**Document Version**: 2.0.0
-**Author**: Claude (Sonnet 4.5)
-**Review Status**: Pending Approval
-**Implementation Status**: Design Complete, Development Pending
--- a/PLANNING_GAP_ANALYSIS.md
+++ b/PLANNING_GAP_ANALYSIS.md
--- a/PROJECT_INTRODUCTION.md
+++ b/PROJECT_INTRODUCTION.md
@@ -1,401 +0,0 @@
-# 🚀 Claude Code Workflow (CCW): 下一代多智能体软件开发自动化框架
-
-[![Version](https://img.shields.io/badge/version-v3.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
-[![MCP工具](https://img.shields.io/badge/🔧_MCP工具-实验性-orange.svg)](https://github.com/modelcontextprotocol)
-[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
-
---
-
-## 📋 项目概述
-
-**Claude Code Workflow (CCW)** 是一个革命性的多智能体自动化开发框架，它通过智能工作流管理和自主执行来协调复杂的软件开发任务。CCW 不仅仅是一个工具，它是一个完整的开发生态系统，将人工智能的强大能力与结构化的开发流程相结合。
-
-## 🎯 概念设计与核心理念
-
-### 设计哲学
-
-CCW 的设计基于几个核心理念：
-
-1. **🧠 智能协作而非替代**: 不是完全取代开发者，而是作为智能助手协同工作
-2. **📊 JSON 优先架构**: 以 JSON 作为单一数据源，消除同步复杂性
-3. **🔄 完整的开发生命周期**: 覆盖从构思到部署的每一个环节
-4. **🤖 多智能体协调**: 专门的智能体处理不同类型的开发任务
-5. **⚡ 原子化会话管理**: 超快速的上下文切换和并行工作
-
-### 架构创新
-
-```mermaid
-graph TD
-    A[🖥️ CLI 接口层] --> B[📋 会话管理层]
-    B --> C[📊 JSON 任务数据层]
-    C --> D[🤖 多智能体编排层]
-
-    A --> A1[Gemini CLI - 分析探索]
-    A --> A2[Codex CLI - 自主开发]
-    A --> A3[Qwen CLI - 架构生成]
-
-    B --> B1[.active-session 标记]
-    B --> B2[工作流会话状态]
-
-    C --> C1[IMPL-*.json 任务定义]
-    C --> C2[动态任务分解]
-    C --> C3[依赖关系映射]
-
-    D --> D1[概念规划智能体]
-    D --> D2[代码开发智能体]
-    D --> D3[测试审查智能体]
-    D --> D4[记忆桥接智能体]
-```
-
-## 🔥 解决的核心问题
-
-### 1. **项目上下文丢失问题**
-**传统痛点**: 在复杂项目中，开发者经常在不同任务间切换时丢失上下文，需要重新理解代码结构和业务逻辑。
-
-**CCW 解决方案**:
- 📚 **智能内存更新系统**: 自动维护 `CLAUDE.md` 文档，实时跟踪代码库变化
- 🔄 **会话持久化**: 完整保存工作流状态，支持无缝恢复
- 📊 **上下文继承**: 任务间自动传递相关上下文信息
-
-### 2. **开发流程不统一问题**
-**传统痛点**: 团队成员使用不同的开发流程，导致代码质量不一致，难以协作。
-
-**CCW 解决方案**:
- 🔄 **标准化工作流**: 强制执行 Brainstorm → Plan → Verify → Execute → Test → Review 流程
- ✅ **质量门禁**: 每个阶段都有验证机制确保质量
- 📋 **可追溯性**: 完整记录决策过程和实现细节
-
-### 3. **重复性任务自动化不足**
-**传统痛点**: 大量重复性的代码生成、测试编写、文档更新工作消耗开发者精力。
-
-**CCW 解决方案**:
- 🤖 **多智能体自动化**: 不同类型任务分配给专门的智能体
- 🧪 **自动测试生成**: 根据实现自动生成全面的测试套件
- 📝 **文档自动更新**: 代码变更时自动更新相关文档
-
-### 4. **代码库理解困难**
-**传统痛点**: 在大型项目中，理解现有代码结构和模式需要大量时间。
-
-**CCW 解决方案**:
- 🔧 **MCP 工具集成**: 通过 Model Context Protocol 实现高级代码分析
- 🔍 **模式识别**: 自动识别代码库中的设计模式和架构约定
- 🌐 **外部最佳实践**: 集成外部 API 模式和行业最佳实践
-
-## 🛠️ 核心工作流介绍
-
-### 📊 JSON 优先数据模型
-
-CCW 采用独特的 JSON 优先架构，所有工作流状态都存储在结构化的 JSON 文件中：
-
-```json
-{
-  "id": "IMPL-1.2",
-  "title": "实现 JWT 认证系统",
-  "status": "pending",
-  "meta": {
-    "type": "feature",
-    "agent": "code-developer"
-  },
-  "context": {
-    "requirements": ["JWT 认证", "OAuth2 支持"],
-    "focus_paths": ["src/auth", "tests/auth"],
-    "acceptance": ["JWT 验证工作", "OAuth 流程完整"]
-  },
-  "flow_control": {
-    "pre_analysis": [...],
-    "implementation_approach": {...}
-  }
-}
-```
-
-### 🧠 智能内存管理系统
-
-#### 自动内存更新
-CCW 的内存更新系统是其核心特色之一：
-
-```bash
-# 日常开发后的自动更新
-/update-memory-related  # 智能分析最近变更，只更新相关模块
-
-# 重大变更后的全面更新
-/update-memory-full     # 完整扫描项目，重建所有文档
-
-# 模块特定更新
-cd src/auth && /update-memory-related  # 针对特定模块的精准更新
-```
-
-#### CLAUDE.md 四层架构
-```
-CLAUDE.md (项目级总览)
-├── src/CLAUDE.md (源码层文档)
-├── src/auth/CLAUDE.md (模块层文档)
-└── src/auth/jwt/CLAUDE.md (组件层文档)
-```
-
-### 🔧 Flow Control 与 CLI 工具集成
-
-#### 预分析阶段 (pre_analysis)
-```json
-"pre_analysis": [
-  {
-    "step": "mcp_codebase_exploration",
-    "action": "使用 MCP 工具探索代码库结构",
-    "command": "mcp__code-index__find_files(pattern=\"[task_focus_patterns]\")",
-    "output_to": "codebase_structure"
-  },
-  {
-    "step": "mcp_external_context",
-    "action": "获取外部 API 示例和最佳实践",
-    "command": "mcp__exa__get_code_context_exa(query=\"[task_technology] [task_patterns]\")",
-    "output_to": "external_context"
-  },
-  {
-    "step": "gather_task_context",
-    "action": "分析任务上下文，不进行实现",
-    "command": "gemini-wrapper -p \"分析 [task_title] 的现有模式和依赖\"",
-    "output_to": "task_context"
-  }
-]
-```
-
-#### 实现方法定义 (implementation_approach)
-```json
-"implementation_approach": {
-  "task_description": "基于 [design] 分析结果实现 JWT 认证",
-  "modification_points": [
-    "使用 [parent] 模式添加 JWT 生成",
-    "基于 [context] 实现验证中间件"
-  ],
-  "logic_flow": [
-    "用户登录 → 使用 [inherited] 验证 → 生成 JWT",
-    "受保护路由 → 提取 JWT → 使用 [shared] 规则验证"
-  ],
-  "target_files": [
-    "src/auth/login.ts:handleLogin:75-120",
-    "src/middleware/auth.ts:validateToken"
-  ]
-}
-```
-
-### 🚀 CLI 工具协同工作
-
-#### 三大 CLI 工具分工
-```mermaid
-graph LR
-    A[Gemini CLI] --> A1[深度分析]
-    A --> A2[模式识别]
-    A --> A3[架构理解]
-
-    B[Qwen CLI] --> B1[架构设计]
-    B --> B2[代码生成]
-    B --> B3[系统规划]
-
-    C[Codex CLI] --> C1[自主开发]
-    C --> C2[错误修复]
-    C --> C3[测试生成]
-```
-
-#### 智能工具选择策略
-CCW 基于任务类型自动选择最适合的工具：
-
-```bash
-# 探索和理解阶段
-/cli:analyze --tool gemini "认证系统架构模式"
-
-# 设计和规划阶段
-/cli:mode:plan --tool qwen "微服务认证架构设计"
-
-# 实现和开发阶段
-/cli:execute --tool codex "实现 JWT 认证系统"
-```
-
-### 🔄 完整开发生命周期
-
-#### 1. 头脑风暴阶段
-```bash
-# 多角色专家视角分析
-/workflow:brainstorm:system-architect "用户认证系统"
-/workflow:brainstorm:security-expert "认证安全考虑"
-/workflow:brainstorm:ui-designer "认证用户体验"
-
-# 综合所有视角
-/workflow:brainstorm:synthesis
-```
-
-#### 2. 规划与验证
-```bash
-# 创建实现计划
-/workflow:plan "用户认证系统与 JWT 支持"
-
-# 双重验证机制
-/workflow:plan-verify  # Gemini 战略 + Codex 技术双重验证
-```
-
-#### 3. 执行与测试
-```bash
-# 智能体协调执行
-/workflow:execute
-
-# 自动生成测试工作流
-/workflow:test-gen WFS-user-auth-system
-```
-
-#### 4. 审查与文档
-```bash
-# 质量审查
-/workflow:review
-
-# 分层文档生成
-/workflow:docs "all"
-```
-
-## 🔧 技术创新亮点
-
-### 1. **MCP 工具集成** *(实验性)*
- **Exa MCP Server**: 获取真实世界的 API 模式和最佳实践
- **Code Index MCP**: 高级内部代码库搜索和索引
- **自动回退**: MCP 不可用时无缝切换到传统工具
-
-### 2. **原子化会话管理**
-```bash
-# 超快速会话切换 (<10ms)
-.workflow/.active-user-auth-system  # 简单的文件标记
-
-# 并行会话支持
-.workflow/WFS-user-auth/     # 认证系统会话
-.workflow/WFS-payment/       # 支付系统会话
-.workflow/WFS-dashboard/     # 仪表板会话
-```
-
-### 3. **智能上下文传递**
- **依赖上下文**: 任务完成后自动传递关键信息给依赖任务
- **继承上下文**: 子任务自动继承父任务的设计决策
- **共享上下文**: 会话级别的全局规则和模式
-
-### 4. **动态任务分解**
-```json
-// 主任务自动分解为子任务
-"IMPL-1": "用户认证系统",
-"IMPL-1.1": "JWT 令牌生成",
-"IMPL-1.2": "认证中间件",
-"IMPL-1.3": "用户登录接口"
-```
-
-## 🎯 使用场景示例
-
-### 场景 1: 新功能开发
-```bash
-# 1. 启动专门会话
-/workflow:session:start "OAuth2 集成"
-
-# 2. 多视角头脑风暴
-/workflow:brainstorm:system-architect "OAuth2 架构设计"
-/workflow:brainstorm:security-expert "OAuth2 安全考虑"
-
-# 3. 执行完整开发流程
-/workflow:plan "OAuth2 与现有认证系统集成"
-/workflow:plan-verify
-/workflow:execute
-/workflow:test-gen WFS-oauth2-integration
-/workflow:review
-```
-
-### 场景 2: 紧急错误修复
-```bash
-# 快速错误解决工作流
-/workflow:session:start "支付验证修复"
-/cli:mode:bug-diagnosis --tool gemini "并发请求时支付验证失败"
-/cli:execute --tool codex "修复支付验证竞态条件"
-/workflow:review
-```
-
-### 场景 3: 架构重构
-```bash
-# 深度架构分析和重构
-/workflow:session:start "微服务重构"
-/cli:analyze --tool gemini "当前单体架构的技术债务"
-/workflow:plan "单体到微服务的迁移策略"
-/workflow:execute
-/workflow:test-gen WFS-microservice-refactoring
-```
-
-## 🌟 核心优势
-
-### 1. **提升开发效率**
- ⚡ **10x 上下文切换速度**: 原子化会话管理
- 🤖 **自动化重复任务**: 90% 的样板代码和测试自动生成
- 📊 **智能决策支持**: 基于历史模式的建议
-
-### 2. **保证代码质量**
- ✅ **强制质量门禁**: 每个阶段的验证机制
- 🔍 **自动模式检测**: 识别并遵循现有代码约定
- 📝 **完整可追溯性**: 从需求到实现的完整记录
-
-### 3. **降低学习成本**
- 📚 **智能文档系统**: 自动维护的项目知识库
- 🔄 **标准化流程**: 统一的开发工作流
- 💡 **最佳实践集成**: 外部优秀模式的自动引入
-
-### 4. **支持团队协作**
- 🔀 **并行会话支持**: 多人同时工作不冲突
- 📊 **透明的进度跟踪**: 实时可见的任务状态
- 🤝 **知识共享**: 决策过程和实现细节的完整记录
-
-## 🚀 开始使用
-
-### 快速安装
-```powershell
-# Windows 一键安装
-Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).Content
-
-# 验证安装
-/workflow:session:list
-```
-
-### 可选 MCP 工具增强
-```bash
-# 安装 Exa MCP Server (外部 API 模式)
-# 安装指南: https://github.com/exa-labs/exa-mcp-server
-
-# 安装 Code Index MCP (高级代码搜索)
-# 安装指南: https://github.com/johnhuang316/code-index-mcp
-```
-
-## 📈 项目状态与路线图
-
-### 当前状态 (v2.1.0-experimental)
- ✅ 核心多智能体系统完成
- ✅ JSON 优先架构稳定
- ✅ 完整工作流生命周期支持
- 🧪 MCP 工具集成 (实验性)
- ✅ 智能内存管理系统
-
-### 即将推出
- 🔮 **AI 辅助代码审查**: 更智能的质量检测
- 🌐 **云端协作支持**: 团队级工作流共享
- 📊 **性能分析集成**: 自动性能优化建议
- 🔧 **更多 MCP 工具**: 扩展外部工具生态
-
-## 🤝 社区与支持
-
- 📚 **文档**: [项目 Wiki](https://github.com/catlog22/Claude-Code-Workflow/wiki)
- 🐛 **问题反馈**: [GitHub Issues](https://github.com/catlog22/Claude-Code-Workflow/issues)
- 💬 **社区讨论**: [讨论区](https://github.com/catlog22/Claude-Code-Workflow/discussions)
- 📋 **更新日志**: [发布历史](CHANGELOG.md)
-
---
-
-## 💡 结语
-
-**Claude Code Workflow** 不仅仅是一个开发工具，它代表了软件开发工作流的未来趋势。通过智能化的多智能体协作、结构化的开发流程和先进的上下文管理，CCW 让开发者能够专注于创造性工作，而将重复性和机械性任务交给 AI 助手。
-
-我们相信，未来的软件开发将是人机协作的典范，CCW 正是这一愿景的先锋实践。
-
-🌟 **立即体验 CCW，开启您的智能化开发之旅！**
-
-[![⭐ Star on GitHub](https://img.shields.io/badge/⭐-Star%20on%20GitHub-yellow.svg)](https://github.com/catlog22/Claude-Code-Workflow)
-[![🚀 Latest Release](https://img.shields.io/badge/🚀-Download%20Latest-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases/latest)
-
---
-
-*本文档由 Claude Code Workflow 的智能文档系统自动生成和维护*
--- a/WORKFLOW_DIAGRAMS.md
+++ b/WORKFLOW_DIAGRAMS.md
@@ -14,9 +14,10 @@ graph TB
    end

    subgraph "Session Management"
-        MARKER[".active-session marker"]
        SESSION["workflow-session.json"]
        WDIR[".workflow/ directories"]
+        ACTIVE_DIR[".workflow/active/"]
+        ARCHIVE_DIR[".workflow/archives/"]
    end

    subgraph "Task System"
@@ -124,9 +125,7 @@ stateDiagram-v2
    CreateStructure --> CreateJSON: Create workflow-session.json
    CreateJSON --> CreatePlan: Create IMPL_PLAN.md
    CreatePlan --> CreateTasks: Create .task/ directory
-    CreateTasks --> SetActive: touch .active-session-name
-
-    SetActive --> Active: Session Ready
+    CreateTasks --> Active: Session Ready in .workflow/active/

    Active --> Paused: Switch to Another Session
    Active --> Working: Execute Tasks
Author	SHA1	Message	Date
catlog22	3c28c61bea	fix: update minimal documentation output guideline for clarity	2025-11-22 23:21:26 +08:00
catlog22	b0b99a4217	Enhance installation and uninstallation processes - Added optional quiet mode for backup notifications to reduce output clutter. - Improved file merging with progress reporting and summary of backed up files. - Implemented a cleanup function to move old installations to a backup directory before new installations. - Enhanced manifest handling to distinguish between Global and Path installations. - Updated uninstallation process to preserve global files if a Global installation exists. - Improved error handling and user feedback during file operations.	2025-11-22 23:20:39 +08:00
catlog22	4f533f6fd5	feat(lite-execute): intelligent task grouping with parallel/sequential execution Major improvements: - Implement dependency-aware task grouping algorithm * Same file modifications → sequential batch * Different files + no dependencies → parallel batch * Keyword-based dependency inference (use/integrate/call/import) * Batch limits: Agent 7 tasks, CLI 4 tasks - Add parallel execution strategy * All parallel batches launch concurrently (single Claude message) * Sequential batches execute in order * No concurrency limit for CLI tools * Execution flow: parallel-first → sequential-after - Enhance code review with task.json acceptance criteria * Unified review template for all tools (Gemini/Qwen/Codex/Agent) * task.json in CONTEXT field for CLI tools * Explicit acceptance criteria verification - Clarify execution requirements * Remove ambiguous strategy instructions * Add explicit "MUST complete ALL tasks" requirement * Prevent CLI tools from partial execution misunderstanding - Simplify documentation (~260 lines reduced) * Remove redundant examples and explanations * Keep core algorithm logic with inline comments * Eliminate duplicate descriptions across sections Breaking changes: None (backward compatible)	2025-11-22 21:05:43 +08:00
catlog22	530c348e95	feat: enhance task execution with intelligent grouping and dependency analysis	2025-11-22 20:57:16 +08:00
catlog22	a98b26b111	feat: add session folder structure for lite-plan artifacts - Create dedicated session folder (.workflow/.lite-plan/{task-slug}-{timestamp}/) for each lite-plan execution to organize all planning artifacts - Always export task.json (removed optional export question from Phase 4) - Save exploration.json, plan.json, and task.json to session folder - Add session artifact paths to executionContext for lite-execute delegation - Update lite-execute to use artifact file paths for CLI/agent context - Enable CLI tools (Gemini/Qwen/Codex) and agents to access detailed planning context via file references Benefits: - Clean separation between different task executions - All artifacts automatically saved for reusability - Enhanced context available for execution phase - Natural audit trail of planning sessions	2025-11-22 20:32:01 +08:00
catlog22	9f7e33cbde	Merge branch 'main' of https://github.com/catlog22/Claude-Code-Workflow	2025-11-22 20:22:21 +08:00
catlog22	a25464ce28	Merge pull request #29 from catlog22/claude/analyze-workflow-logic-015GvXNP62281T3ogUSaJdP4 Analyze workflow execution logic and document findings	2025-11-20 20:16:28 +08:00
catlog22	0a3f2a5b03	Merge pull request #28 from catlog22/claude/check-active-workflow-files-01S7quRK9xHWStgpQ9WeTnF2 Check for .active identifier in workflow files	2025-11-20 20:15:39 +08:00
Claude	1929b7f72d	docs: remove obsolete .active marker file references Remove outdated references to .active-session marker files that are no longer used in the workflow implementation. The system now uses directory-based session management where active sessions are identified by their location in .workflow/active/ directory. Changes: - WORKFLOW_DIAGRAMS.md: Replace .active-session marker with actual directory structure - COMMAND_SPEC.md: Update session:complete description to reflect directory-based archival The .archiving marker is still valid and used for transactional session completion.	2025-11-20 12:13:45 +00:00
Claude	b8889d99c9	refactor: simplify session selection logic expression - Condense Case A/B/C headers for clarity - Merge bash if-else into single line using && \|\| - Combine steps 1-4 in Case C into compact flow - Remove redundant explanations while keeping key info - Reduce from 64 lines to 39 lines (39% reduction)	2025-11-20 12:12:56 +00:00
Claude	a79a3221ce	fix: enhance workflow execute session selection with user interaction - Add detailed session discovery logic with 3 cases (none, single, multiple) - Implement AskUserQuestion for multiple active sessions - Display rich session metadata (project name, task progress, completion %) - Support flexible user input (session number, full ID, or partial ID) - Maintain backward compatibility for single-session scenarios - Improve user experience with clear confirmation messages This minimal change addresses session conflict issues without complex locking mechanisms, focusing on explicit user choice when ambiguity exists.	2025-11-20 12:08:35 +00:00
catlog22	67c18d1b03	Merge pull request #27 from catlog22/claude/cleanup-root-docs-01SAjhmQa3Wc4EWxZoCnFb77 Remove unnecessary documentation from root directory	2025-11-20 19:55:15 +08:00
Claude	2301f263cd	docs: cleanup unnecessary root directory documentation Remove 7 unnecessary documentation files from root directory: - COMMAND_DOCS_AUDIT_REPORT.md (temporary audit report) - PLANNING_GAP_ANALYSIS.md (temporary analysis document) - PROJECT_INTRODUCTION.md (duplicate of README) - COMMAND_FLOW_STANDARD.md (internal standard) - COMMAND_TEMPLATE_EXECUTOR.md (internal design) - COMMAND_TEMPLATE_ORCHESTRATOR.md (internal design) - LITE_FIX_DESIGN.md (internal design) Retained essential documentation: - User guides (README, GETTING_STARTED, FAQ, EXAMPLES) - Developer docs (CLAUDE.md, CONTRIBUTING, ARCHITECTURE) - Command references (COMMAND_REFERENCE, COMMAND_SPEC) - Workflow guides (WORKFLOW_DECISION_GUIDE, WORKFLOW_DIAGRAMS)	2025-11-20 11:53:40 +00:00