Fix session management location inference and ccw command usage

This commit addresses multiple issues in session management and command documentation:

Session Management Fixes:
- Add auto-inference of location from type parameter in session.ts
- When --type lite-plan/lite-fix is specified, automatically set location accordingly
- Preserve explicit --location parameter when provided
- Update session-manager.ts to support type-based location inference
- Fix metadata filename selection (session-metadata.json vs workflow-session.json)

Command Documentation Fixes:
- Add missing --mode analysis parameter (3 locations):
  * commands/memory/docs.md
  * commands/workflow/lite-execute.md (2 instances)
- Add missing --mode write parameter (4 locations):
  * commands/workflow/tools/task-generate-agent.md
- Remove non-existent subcommands (3 locations):
  * commands/workflow/session/complete.md (manifest, project)
- Update session command syntax to use simplified format:
  * Changed from 'ccw session manifest read' to 'test -f' checks
  * Changed from 'ccw session project read' to 'test -f' checks

Documentation Updates:
- Update lite-plan.md and lite-fix.md to use --type parameter
- Update session/start.md to document lite-plan and lite-fix types
- Sync all fixes to skills/command-guide/reference directory (84 files)

All ccw command usage across the codebase is now consistent and correct.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.claude/agents/code-developer.md

@@ -34,10 +34,10 @@ You are a code execution specialist focused on implementing high-quality, produc
 - **context-package.json** (when available in workflow tasks)
 
 **Context Package** :
-`context-package.json` provides artifact paths - read using `ccw session`:
+`context-package.json` provides artifact paths - read using Read tool or ccw session:
 ```bash
-# Get context package content from session
-ccw session read ${SESSION_ID} --type context
+# Get context package content from session using Read tool
+Read(.workflow/active/${SESSION_ID}/.process/context-package.json)
 # Returns parsed JSON with brainstorm_artifacts, focus_paths, etc.
 ```
 

.claude/agents/conceptual-planning-agent.md

@@ -109,7 +109,7 @@ This agent processes **simplified inline [FLOW_CONTROL]** format from brainstorm
 
 3. **load_session_metadata**
    - Action: Load session metadata
-   - Command: ccw session read WFS-{session} --type session
+   - Command: Read(.workflow/active/WFS-{session}/workflow-session.json)
    - Output: session_metadata
 ```
 
@@ -155,7 +155,7 @@ When called, you receive:
 - **User Context**: Specific requirements, constraints, and expectations from user discussion
 - **Output Location**: Directory path for generated analysis files
 - **Role Hint** (optional): Suggested role or role selection guidance
-- **context-package.json** (CCW Workflow): Artifact paths catalog - use `ccw session read {session} --type context` to get context package
+- **context-package.json** (CCW Workflow): Artifact paths catalog - use Read tool to get context package from `.workflow/active/{session}/.process/context-package.json`
 - **ASSIGNED_ROLE** (optional): Specific role assignment
 - **ANALYSIS_DIMENSIONS** (optional): Role-specific analysis dimensions
 

.claude/agents/test-fix-agent.md

@@ -83,7 +83,7 @@ When task JSON contains implementation_approach array:
   - L1 (Unit): `*.test.*`, `*.spec.*` in `__tests__/`, `tests/unit/`
   - L2 (Integration): `tests/integration/`, `*.integration.test.*`
   - L3 (E2E): `tests/e2e/`, `*.e2e.test.*`, `cypress/`, `playwright/`
-- **context-package.json** (CCW Workflow): Use `ccw session read {session} --type context` to get context package with artifact paths
+- **context-package.json** (CCW Workflow): Use Read tool to get context package from `.workflow/active/{session}/.process/context-package.json`
 - Identify test commands from project configuration
 
 ```bash

.claude/commands/memory/docs.md

@@ -74,7 +74,7 @@ SlashCommand(command="/workflow:session:start --type docs --new \"{project_name}
 
 ```bash
 # Update workflow-session.json with docs-specific fields
-ccw session update {sessionId} --type session --content '{"target_path":"{target_path}","project_root":"{project_root}","project_name":"{project_name}","mode":"full","tool":"gemini","cli_execute":false}'
+ccw session {sessionId} write workflow-session.json '{"target_path":"{target_path}","project_root":"{project_root}","project_name":"{project_name}","mode":"full","tool":"gemini","cli_execute":false}'
 ```
 
 ### Phase 2: Analyze Structure
@@ -136,7 +136,7 @@ bash(if [ -d .workflow/docs/\${project_name} ]; then find .workflow/docs/\${proj
 
 ```bash
 # Count existing docs from doc-planning-data.json
-ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq '.existing_docs.file_list | length'
+ccw session WFS-docs-{timestamp} read .process/doc-planning-data.json --raw | jq '.existing_docs.file_list | length'
 # Or read entire process file and parse
 ```
 
@@ -191,10 +191,10 @@ Large Projects (single dir >10 docs):
 
 ```bash
 # 1. Get top-level directories from doc-planning-data.json
-ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq -r '.top_level_dirs[]'
+ccw session WFS-docs-{timestamp} read .process/doc-planning-data.json --raw | jq -r '.top_level_dirs[]'
 
 # 2. Get mode from workflow-session.json
-ccw session read WFS-docs-{timestamp} --type session --raw | jq -r '.mode // "full"'
+ccw session WFS-docs-{timestamp} read workflow-session.json --raw | jq -r '.mode // "full"'
 
 # 3. Check for HTTP API
 bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo "NO_API")
@@ -223,7 +223,7 @@ bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo
 
 **Task ID Calculation**:
 ```bash
-group_count=$(ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq '.groups.count')
+group_count=$(ccw session WFS-docs-{timestamp} read .process/doc-planning-data.json --raw | jq '.groups.count')
 readme_id=$((group_count + 1))   # Next ID after groups
 arch_id=$((group_count + 2))
 api_id=$((group_count + 3))
@@ -239,7 +239,7 @@ api_id=$((group_count + 3))
 | **CLI** | true | implementation_approach | write | --mode write | Execute CLI commands, validate output |
 
 **Command Patterns**:
-- Gemini/Qwen: `ccw cli exec "..." --tool gemini --cd dir`
+- Gemini/Qwen: `ccw cli exec "..." --tool gemini --mode analysis --cd dir`
 - CLI Mode: `ccw cli exec "..." --tool gemini --mode write --cd dir`
 - Codex: `ccw cli exec "..." --tool codex --mode write --cd dir`
 
@@ -286,8 +286,8 @@ api_id=$((group_count + 3))
         "step": "load_precomputed_data",
         "action": "Load Phase 2 analysis and extract group directories",
         "commands": [
-          "ccw session read ${session_id} --type process --filename doc-planning-data.json",
-          "ccw session read ${session_id} --type process --filename doc-planning-data.json --raw | jq '.groups.assignments[] | select(.group_id == \"${group_number}\") | .directories'"
+          "ccw session ${session_id} read .process/doc-planning-data.json",
+          "ccw session ${session_id} read .process/doc-planning-data.json --raw | jq '.groups.assignments[] | select(.group_id == \"${group_number}\") | .directories'"
         ],
         "output_to": "phase2_context",
         "note": "Single JSON file contains all Phase 2 analysis results"

.claude/commands/workflow/execute.md

@@ -149,7 +149,7 @@ Parse user input (supports: number "1", full ID "WFS-auth-system", or partial "a
 
 #### Step 1.3: Load Session Metadata
 ```bash
-ccw session read ${sessionId} --type session
+ccw session ${sessionId} read workflow-session.json
 ```
 
 **Output**: Store session metadata in memory

.claude/commands/workflow/lite-execute.md

@@ -591,12 +591,12 @@ ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --
 const reviewId = `${sessionId}-review`
 
 // First review pass with fixed ID
-const reviewResult = Bash(`ccw cli exec "[Review prompt]" --tool gemini --id ${reviewId}`)
+const reviewResult = Bash(`ccw cli exec "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
 
 // If issues found, continue review dialog with fixed ID chain
 if (hasUnresolvedIssues(reviewResult)) {
   // Resume with follow-up questions
-  Bash(`ccw cli exec "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --id ${reviewId}-followup`)
+  Bash(`ccw cli exec "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
 }
 ```
 

.claude/commands/workflow/lite-fix.md

@@ -72,31 +72,62 @@ Phase 5: Dispatch
 ### Phase 1: Intelligent Multi-Angle Diagnosis
 
 **Session Setup** (MANDATORY - follow exactly):
+
+**Option 1: Using CLI Command** (Recommended for simplicity):
+```bash
+# Generate session ID
+bug_slug=$(echo "${bug_description}" | tr '[:upper:]' '[:lower:]' | tr -cs '[:alnum:]' '-' | cut -c1-40)
+date_str=$(date -u '+%Y-%m-%d')
+session_id="${bug_slug}-${date_str}"
+
+# Initialize lite-fix session (location auto-inferred from type)
+ccw session init "${session_id}" \
+  --type lite-fix \
+  --content "{\"description\":\"${bug_description}\",\"severity\":\"${severity}\"}"
+
+
+
+# Get session folder
+session_folder=".workflow/.lite-fix/${session_id}"
+echo "Session initialized: ${session_id} at ${session_folder}"
+```
+
+**Option 2: Using session_manager Tool** (For programmatic access):
 ```javascript
 // Helper: Get UTC+8 (China Standard Time) ISO string
 const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
 
 const bugSlug = bug_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
-const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-11-29
+const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-12-17
+
+const sessionId = `${bugSlug}-${dateStr}`  // e.g., "user-avatar-upload-fails-2025-12-17"
 
-const sessionId = `${bugSlug}-${dateStr}`  // e.g., "user-avatar-upload-fails-2025-11-29"
 
-// Initialize session via session_manager tool
-const initResult = await ccw_tool_exec('session_manager', {
-  operation: 'init',
-  session_id: sessionId,
-  location: 'lite-fix',
-  metadata: {
-    description: bug_description,
-    severity: severity,  // Set after severity assessment
-    created_at: getUtc8ISOString()
-  }
-})
 
 const sessionFolder = initResult.result.path
 console.log(`Session initialized: ${sessionId} at ${sessionFolder}`)
 ```
 
+**Session File Structure**:
+- `session-metadata.json` - Session metadata (created at init, contains description, severity, status)
+- `fix-plan.json` - Actual fix planning content (created later in Phase 3, contains fix tasks, diagnosis results)
+
+**Metadata Field Usage**:
+- `description`: Displayed in dashboard session list (replaces session ID as title)
+- `severity`: Used for fix planning strategy selection (Low/Medium → Direct Claude, High/Critical → Agent)
+- `created_at`: Displayed in dashboard timeline
+- `status`: Updated through workflow (diagnosing → fixing → completed)
+- Custom fields: Any additional fields in metadata are saved and accessible programmatically
+
+**Accessing Session Data**:
+```bash
+# Read session metadata
+ccw session ${session_id} read session-metadata.json
+
+# Read fix plan content (after Phase 3 completion)
+ccw session ${session_id} read fix-plan.json
+```
+
 **Diagnosis Decision Logic**:
 ```javascript
 const hotfixMode = $ARGUMENTS.includes('--hotfix') || $ARGUMENTS.includes('-h')

.claude/commands/workflow/lite-plan.md

@@ -72,31 +72,59 @@ Phase 5: Dispatch
 ### Phase 1: Intelligent Multi-Angle Exploration
 
 **Session Setup** (MANDATORY - follow exactly):
+
+**Option 1: Using CLI Command** (Recommended for simplicity):
+```bash
+# Generate session ID
+task_slug=$(echo "${task_description}" | tr '[:upper:]' '[:lower:]' | tr -cs '[:alnum:]' '-' | cut -c1-40)
+date_str=$(date -u '+%Y-%m-%d')
+session_id="${task_slug}-${date_str}"
+
+# Initialize lite-plan session (location auto-inferred from type)
+ccw session init "${session_id}" \
+  --type lite-plan \
+  --content "{\"description\":\"${task_description}\",\"complexity\":\"${complexity}\"}"
+
+# Get session folder
+session_folder=".workflow/.lite-plan/${session_id}"
+echo "Session initialized: ${session_id} at ${session_folder}"
+```
+
+**Option 2: Using session_manager Tool** (For programmatic access):
 ```javascript
 // Helper: Get UTC+8 (China Standard Time) ISO string
 const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
 
 const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
-const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-11-29
+const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-12-17
+
+const sessionId = `${taskSlug}-${dateStr}`  // e.g., "implement-jwt-refresh-2025-12-17"
 
-const sessionId = `${taskSlug}-${dateStr}`  // e.g., "implement-jwt-refresh-2025-11-29"
 
-// Initialize session via session_manager tool
-const initResult = await ccw_tool_exec('session_manager', {
-  operation: 'init',
-  session_id: sessionId,
-  location: 'lite-plan',
-  metadata: {
-    description: task_description,
-    complexity: complexity,  // Set after complexity assessment
-    created_at: getUtc8ISOString()
-  }
-})
 
 const sessionFolder = initResult.result.path
 console.log(`Session initialized: ${sessionId} at ${sessionFolder}`)
 ```
 
+**Session File Structure**:
+- `session-metadata.json` - Session metadata (created at init, contains description, complexity, status)
+- `plan.json` - Actual planning content (created later in Phase 3, contains tasks, steps, dependencies)
+
+**Metadata Field Usage**:
+- `description`: Displayed in dashboard session list (replaces session ID as title)
+- `complexity`: Used for planning strategy selection (Low → Direct Claude, Medium/High → Agent)
+- `created_at`: Displayed in dashboard timeline
+- Custom fields: Any additional fields in metadata are saved and accessible programmatically
+
+**Accessing Session Data**:
+```bash
+# Read session metadata
+ccw session ${session_id} read session-metadata.json
+
+# Read plan content (after Phase 3 completion)
+ccw session ${session_id} read plan.json
+```
+
 **Exploration Decision Logic**:
 ```javascript
 needsExploration = (

.claude/commands/workflow/review.md

@@ -112,14 +112,18 @@ After bash validation, the model takes control to:
 
 1. **Load Context**: Read completed task summaries and changed files
    ```bash
-   # Load implementation summaries
-   ccw session read ${sessionId} --type summary --raw
+   # Load implementation summaries (iterate through .summaries/ directory)
+   for summary in .workflow/active/${sessionId}/.summaries/*.md; do
+     cat "$summary"
+   done
 
    # Load test results (if available)
-   ccw session read ${sessionId} --type summary --filename "TEST-FIX-*.md" --raw 2>/dev/null
+   for test_summary in .workflow/active/${sessionId}/.summaries/TEST-FIX-*.md 2>/dev/null; do
+     cat "$test_summary"
+   done
 
    # Get session created_at for git log filter
-   created_at=$(ccw session read ${sessionId} --type session --raw | jq -r .created_at)
+   created_at=$(ccw session ${sessionId} read workflow-session.json | jq -r .created_at)
    git log --since="$created_at" --name-only --pretty=format: | sort -u
    ```
 
@@ -170,11 +174,13 @@ After bash validation, the model takes control to:
    - Verify all requirements and acceptance criteria met:
      ```bash
      # Load task requirements and acceptance criteria
-     ccw session read ${sessionId} --type task --raw | jq -r '
-       "Task: " + .id + "\n" +
-       "Requirements: " + (.context.requirements | join(", ")) + "\n" +
-       "Acceptance: " + (.context.acceptance | join(", "))
-     '
+     for task_file in .workflow/active/${sessionId}/.task/*.json; do
+       cat "$task_file" | jq -r '
+         "Task: " + .id + "\n" +
+         "Requirements: " + (.context.requirements | join(", ")) + "\n" +
+         "Acceptance: " + (.context.acceptance | join(", "))
+       '
+     done
 
      # Check implementation summaries against requirements
      ccw cli exec "

.claude/commands/workflow/session/complete.md

@@ -34,7 +34,7 @@ ccw session list --location active
 #### Step 1.2: Check for Existing Archiving Marker (Resume Detection)
 ```bash
 # Check if session is already being archived (marker file exists)
-ccw session read WFS-session-name --type process --filename .archiving 2>/dev/null && echo "RESUMING" || echo "NEW"
+ccw session WFS-session-name read .process/.archiving 2>/dev/null && echo "RESUMING" || echo "NEW"
 ```
 
 **If RESUMING**:
@@ -47,7 +47,7 @@ ccw session read WFS-session-name --type process --filename .archiving 2>/dev/nu
 #### Step 1.3: Create Archiving Marker
 ```bash
 # Mark session as "archiving in progress"
-ccw session write WFS-session-name --type process --filename .archiving --content ''
+ccw session WFS-session-name write .process/.archiving ''
 ```
 **Purpose**:
 - Prevents concurrent operations on this session
@@ -171,8 +171,8 @@ ccw session archive WFS-session-name
 
 #### Step 3.2: Update Manifest
 ```bash
-# Read current manifest using ccw (or create empty array if not exists)
-ccw session read manifest --type manifest --raw 2>/dev/null || echo "[]"
+# Check if manifest exists
+test -f .workflow/archives/manifest.json && echo "EXISTS" || echo "NOT_FOUND"
 ```
 
 **JSON Update Logic**:
@@ -221,8 +221,8 @@ rm .workflow/archives/WFS-session-name/.process/.archiving 2>/dev/null || true
 
 #### Step 4.1: Check Project State Exists
 ```bash
-# Check project state using ccw
-ccw session read project --type project 2>/dev/null && echo "EXISTS" || echo "SKIP"
+# Check if project.json exists
+test -f .workflow/project.json && echo "EXISTS" || echo "SKIP"
 ```
 
 **If SKIP**: Output warning and skip Phase 4
@@ -249,11 +249,6 @@ const featureId = title.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 5
 
 #### Step 4.3: Update project.json
 
-```bash
-# Read current project state using ccw
-ccw session read project --type project --raw
-```
-
 **JSON Update Logic**:
 ```javascript
 // Read existing project.json (created by /workflow:init)

.claude/commands/workflow/session/list.md

@@ -30,7 +30,7 @@ ccw session stats WFS-session
 
 ### Step 3: Read Session Metadata
 ```bash
-ccw session read WFS-session --type session
+ccw session WFS-session read workflow-session.json
 # Returns: session_id, status, project, created_at, etc.
 ```
 
@@ -39,8 +39,8 @@ ccw session read WFS-session --type session
 ### Basic Operations
 - **List all sessions**: `ccw session list`
 - **List active only**: `ccw session list --location active`
-- **Read session data**: `ccw session read WFS-xxx --type session`
-- **Get task stats**: `ccw session stats WFS-xxx`
+- **Read session data**: `ccw session WFS-xxx read workflow-session.json`
+- **Get task stats**: `ccw session WFS-xxx stats`
 
 ## Simple Output Format
 

.claude/commands/workflow/session/resume.md

@@ -23,7 +23,7 @@ ccw session list --location active
 
 ### Step 2: Check Session Status
 ```bash
-ccw session read WFS-session --type session
+ccw session WFS-session read workflow-session.json
 # Check .status field in response
 ```
 
@@ -35,17 +35,15 @@ ccw session list --location active
 
 ### Step 4: Update Session Status to Active
 ```bash
-ccw session status WFS-session active
-# Or with full update:
-ccw session update WFS-session --type session --content '{"status":"active","resumed_at":"2025-12-10T08:00:00Z"}'
+ccw session WFS-session status active
 ```
 
 ## Simple Commands
 
 ### Basic Operations
 - **List sessions**: `ccw session list --location active`
-- **Check status**: `ccw session read WFS-xxx --type session`
-- **Update status**: `ccw session status WFS-xxx active`
+- **Check status**: `ccw session WFS-xxx read workflow-session.json`
+- **Update status**: `ccw session WFS-xxx status active`
 
 ### Resume Result
 ```

.claude/commands/workflow/session/start.md

@@ -30,10 +30,17 @@ The `--type` parameter classifies sessions for CCW dashboard organization:
 | `tdd` | TDD-based development | `/workflow:tdd-plan` |
 | `test` | Test generation/fix sessions | `/workflow:test-fix-gen` |
 | `docs` | Documentation sessions | `/memory:docs` |
+| `lite-plan` | Lightweight planning workflow | `/workflow:lite-plan` |
+| `lite-fix` | Lightweight bug fix workflow | `/workflow:lite-fix` |
+
+**Special Behavior for `lite-plan` and `lite-fix`**:
+- These types automatically infer the storage location (`.workflow/.lite-plan/` or `.workflow/.lite-fix/`)
+- No need to specify `--location` parameter when using these types
+- Alternative: Use `--location lite-plan` or `--location lite-fix` directly
 
 **Validation**: If `--type` is provided with invalid value, return error:
 ```
-ERROR: Invalid session type. Valid types: workflow, review, tdd, test, docs
+ERROR: Invalid session type. Valid types: workflow, review, tdd, test, docs, lite-plan, lite-fix
 ```
 
 ## Step 0: Initialize Project State (First-time Only)
@@ -75,7 +82,7 @@ ccw session list --location active
 
 ### Step 2: Display Session Metadata
 ```bash
-ccw session read WFS-promptmaster-platform --type session
+ccw session WFS-promptmaster-platform read workflow-session.json
 ```
 
 ### Step 4: User Decision
@@ -102,7 +109,7 @@ ccw session list --location active
 # Pattern: WFS-{lowercase-slug-from-description}
 
 # Create session with ccw (creates directories + metadata atomically)
-ccw session init WFS-implement-oauth2-auth --type workflow --content '{"project":"implement OAuth2 auth","status":"planning"}'
+ccw session init WFS-implement-oauth2-auth --type workflow
 ```
 
 **Output**: `SESSION_ID: WFS-implement-oauth2-auth`
@@ -113,7 +120,7 @@ ccw session init WFS-implement-oauth2-auth --type workflow --content '{"project"
 ccw session list --location active
 
 # Read session metadata for relevance check
-ccw session read WFS-promptmaster-platform --type session
+ccw session WFS-promptmaster-platform read workflow-session.json
 
 # If task contains project keywords → Reuse session
 # If task unrelated → Create new session (use Step 2a)
@@ -149,10 +156,41 @@ ccw session list --location active
 
 ### Step 2: Create Session Structure
 ```bash
-# Single command creates directories (.process, .task, .summaries) + metadata
-ccw session init WFS-fix-login-bug --type workflow --content '{"project":"fix login bug","status":"planning"}'
+# Basic init - creates directories + default metadata
+ccw session init WFS-fix-login-bug --type workflow
+
+# Advanced init - with custom metadata
+ccw session init WFS-oauth-implementation --type workflow --content '{"description":"OAuth2 authentication system","priority":"high","complexity":"medium"}'
 ```
 
+**Default Metadata** (auto-generated):
+```json
+{
+  "session_id": "WFS-fix-login-bug",
+  "type": "workflow",
+  "status": "planning",
+  "created_at": "2025-12-17T..."
+}
+```
+
+**Custom Metadata** (merged with defaults):
+```json
+{
+  "session_id": "WFS-oauth-implementation",
+  "type": "workflow",
+  "status": "planning",
+  "created_at": "2025-12-17T...",
+  "description": "OAuth2 authentication system",
+  "priority": "high",
+  "complexity": "medium"
+}
+```
+
+**Field Usage**:
+- `description`: Displayed in dashboard (replaces session_id as title)
+- `status`: Can override default "planning" (e.g., "active", "implementing")
+- Custom fields: Any additional fields are saved and accessible programmatically
+
 **Output**: `SESSION_ID: WFS-fix-login-bug`
 
 ## Execution Guideline

.claude/commands/workflow/tdd-verify.md

@@ -77,18 +77,32 @@ find .workflow/active/ -name "WFS-*" -type d | head -1 | sed 's/.*\///'
 
 ```bash
 # Load all task JSONs
-ccw session read {sessionId} --type task
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file"
+done
 
 # Extract task IDs
-ccw session read {sessionId} --type task --raw | jq -r '.id'
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file" | jq -r '.id'
+done
 
 # Check dependencies - read tasks and filter for IMPL/REFACTOR
-ccw session read {sessionId} --type task --task-id "IMPL-*" --raw | jq -r '.context.depends_on[]?'
-ccw session read {sessionId} --type task --task-id "REFACTOR-*" --raw | jq -r '.context.depends_on[]?'
+for task_file in .workflow/active/{sessionId}/.task/IMPL-*.json; do
+  cat "$task_file" | jq -r '.context.depends_on[]?'
+done
+
+for task_file in .workflow/active/{sessionId}/.task/REFACTOR-*.json; do
+  cat "$task_file" | jq -r '.context.depends_on[]?'
+done
 
 # Check meta fields
-ccw session read {sessionId} --type task --raw | jq -r '.meta.tdd_phase'
-ccw session read {sessionId} --type task --raw | jq -r '.meta.agent'
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file" | jq -r '.meta.tdd_phase'
+done
+
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file" | jq -r '.meta.agent'
+done
 ```
 
 **Validation**:

.claude/commands/workflow/tools/task-generate-agent.md

@@ -307,10 +307,10 @@ Each task JSON MUST include:
 4. **merge_fork**: Task has multiple parents - merges all parent contexts into new conversation
 
 **Execution Command Patterns**:
-- new: `ccw cli exec "[prompt]" --tool [tool] --id [cli_execution_id]`
-- resume: `ccw cli exec "[prompt]" --resume [resume_from] --tool [tool]`
-- fork: `ccw cli exec "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool]`
-- merge_fork: `ccw cli exec "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool]`
+- new: `ccw cli exec "[prompt]" --tool [tool] --mode write --id [cli_execution_id]`
+- resume: `ccw cli exec "[prompt]" --resume [resume_from] --tool [tool] --mode write`
+- fork: `ccw cli exec "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write`
+- merge_fork: `ccw cli exec "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write`
 
 ## QUALITY STANDARDS
 Hard Constraints:

.claude/skills/command-guide/reference/agents/action-planning-agent.md

@@ -203,7 +203,13 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
   "id": "IMPL-N",
   "title": "Descriptive task name",
   "status": "pending|active|completed|blocked",
-  "context_package_path": ".workflow/active/WFS-{session}/.process/context-package.json"
+  "context_package_path": ".workflow/active/WFS-{session}/.process/context-package.json",
+  "cli_execution_id": "WFS-{session}-IMPL-N",
+  "cli_execution": {
+    "strategy": "new|resume|fork|merge_fork",
+    "resume_from": "parent-cli-id",
+    "merge_from": ["id1", "id2"]
+  }
 }
 ```
 
@@ -216,6 +222,50 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
 - `title`: Descriptive task name summarizing the work
 - `status`: Task state - `pending` (not started), `active` (in progress), `completed` (done), `blocked` (waiting on dependencies)
 - `context_package_path`: Path to smart context package containing project structure, dependencies, and brainstorming artifacts catalog
+- `cli_execution_id`: Unique CLI conversation ID (format: `{session_id}-{task_id}`)
+- `cli_execution`: CLI execution strategy based on task dependencies
+  - `strategy`: Execution pattern (`new`, `resume`, `fork`, `merge_fork`)
+  - `resume_from`: Parent task's cli_execution_id (for resume/fork)
+  - `merge_from`: Array of parent cli_execution_ids (for merge_fork)
+
+**CLI Execution Strategy Rules** (MANDATORY - apply to all tasks):
+
+| Dependency Pattern | Strategy | CLI Command Pattern |
+|--------------------|----------|---------------------|
+| No `depends_on` | `new` | `--id {cli_execution_id}` |
+| 1 parent, parent has 1 child | `resume` | `--resume {resume_from}` |
+| 1 parent, parent has N children | `fork` | `--resume {resume_from} --id {cli_execution_id}` |
+| N parents | `merge_fork` | `--resume {merge_from.join(',')} --id {cli_execution_id}` |
+
+**Strategy Selection Algorithm**:
+```javascript
+function computeCliStrategy(task, allTasks) {
+  const deps = task.context?.depends_on || []
+  const childCount = allTasks.filter(t =>
+    t.context?.depends_on?.includes(task.id)
+  ).length
+
+  if (deps.length === 0) {
+    return { strategy: "new" }
+  } else if (deps.length === 1) {
+    const parentTask = allTasks.find(t => t.id === deps[0])
+    const parentChildCount = allTasks.filter(t =>
+      t.context?.depends_on?.includes(deps[0])
+    ).length
+
+    if (parentChildCount === 1) {
+      return { strategy: "resume", resume_from: parentTask.cli_execution_id }
+    } else {
+      return { strategy: "fork", resume_from: parentTask.cli_execution_id }
+    }
+  } else {
+    const mergeFrom = deps.map(depId =>
+      allTasks.find(t => t.id === depId).cli_execution_id
+    )
+    return { strategy: "merge_fork", merge_from: mergeFrom }
+  }
+}
+```
 
 #### Meta Object
 
@@ -225,7 +275,13 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
     "type": "feature|bugfix|refactor|test-gen|test-fix|docs",
     "agent": "@code-developer|@action-planning-agent|@test-fix-agent|@universal-executor",
     "execution_group": "parallel-abc123|null",
-    "module": "frontend|backend|shared|null"
+    "module": "frontend|backend|shared|null",
+    "execution_config": {
+      "method": "agent|hybrid|cli",
+      "cli_tool": "codex|gemini|qwen|auto",
+      "enable_resume": true,
+      "previous_cli_id": "string|null"
+    }
   }
 }
 ```
@@ -235,6 +291,11 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
 - `agent`: Assigned agent for execution
 - `execution_group`: Parallelization group ID (tasks with same ID can run concurrently) or `null` for sequential tasks
 - `module`: Module identifier for multi-module projects (e.g., `frontend`, `backend`, `shared`) or `null` for single-module
+- `execution_config`: CLI execution settings (from userConfig in task-generate-agent)
+  - `method`: Execution method - `agent` (direct), `hybrid` (agent + CLI), `cli` (CLI only)
+  - `cli_tool`: Preferred CLI tool - `codex`, `gemini`, `qwen`, or `auto`
+  - `enable_resume`: Whether to use `--resume` for CLI continuity (default: true)
+  - `previous_cli_id`: Previous task's CLI execution ID for resume (populated at runtime)
 
 **Test Task Extensions** (for type="test-gen" or type="test-fix"):
 
@@ -409,14 +470,14 @@ Generate individual `.task/IMPL-*.json` files with the following structure:
   // Pattern: Gemini CLI deep analysis
   {
     "step": "gemini_analyze_[aspect]",
-    "command": "ccw cli exec 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --cd [path]",
+    "command": "ccw cli exec 'PURPOSE: [goal]\\nTASK: [tasks]\\nMODE: analysis\\nCONTEXT: @[paths]\\nEXPECTED: [output]\\nRULES: $(cat [template]) | [constraints] | analysis=READ-ONLY' --tool gemini --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
   // Pattern: Qwen CLI analysis (fallback/alternative)
   {
     "step": "qwen_analyze_[aspect]",
-    "command": "ccw cli exec '[similar to gemini pattern]' --tool qwen --cd [path]",
+    "command": "ccw cli exec '[similar to gemini pattern]' --tool qwen --mode analysis --cd [path]",
     "output_to": "analysis_result"
   },
 
@@ -457,7 +518,7 @@ The examples above demonstrate **patterns**, not fixed requirements. Agent MUST:
 4. **Command Composition Patterns**:
    - **Single command**: `bash([simple_search])`
    - **Multiple commands**: `["bash([cmd1])", "bash([cmd2])"]`
-   - **CLI analysis**: `ccw cli exec '[prompt]' --tool gemini --cd [path]`
+   - **CLI analysis**: `ccw cli exec '[prompt]' --tool gemini --mode analysis --cd [path]`
    - **MCP integration**: `mcp__[tool]__[function]([params])`
 
 **Key Principle**: Examples show **structure patterns**, not specific implementations. Agent must create task-appropriate steps dynamically.
@@ -479,11 +540,12 @@ The `implementation_approach` supports **two execution modes** based on the pres
    - Specified command executes the step directly
    - Leverages specialized CLI tools (codex/gemini/qwen) for complex reasoning
    - **Use for**: Large-scale features, complex refactoring, or when user explicitly requests CLI tool usage
-   - **Required fields**: Same as default mode **PLUS** `command`
-   - **Command patterns**:
-     - `ccw cli exec '[prompt]' --tool codex --mode auto --cd [path]`
-     - `ccw cli exec '[task]' --tool codex --mode auto` (multi-step with context)
+   - **Required fields**: Same as default mode **PLUS** `command`, `resume_from` (optional)
+   - **Command patterns** (with resume support):
+     - `ccw cli exec '[prompt]' --tool codex --mode write --cd [path]`
+     - `ccw cli exec '[prompt]' --resume ${previousCliId} --tool codex --mode write` (resume from previous)
      - `ccw cli exec '[prompt]' --tool gemini --mode write --cd [path]` (write mode)
+   - **Resume mechanism**: When step depends on previous CLI execution, include `--resume` with previous execution ID
 
 **Semantic CLI Tool Selection**:
 
@@ -559,11 +621,26 @@ Agent determines CLI tool usage per-step based on user semantics and task nature
     "step": 3,
     "title": "Execute implementation using CLI tool",
     "description": "Use Codex/Gemini for complex autonomous execution",
-    "command": "ccw cli exec '[prompt]' --tool codex --mode auto --cd [path]",
+    "command": "ccw cli exec '[prompt]' --tool codex --mode write --cd [path]",
     "modification_points": ["[Same as default mode]"],
     "logic_flow": ["[Same as default mode]"],
     "depends_on": [1, 2],
-    "output": "cli_implementation"
+    "output": "cli_implementation",
+    "cli_output_id": "step3_cli_id"  // Store execution ID for resume
+  },
+
+  // === CLI MODE with Resume: Continue from previous CLI execution ===
+  {
+    "step": 4,
+    "title": "Continue implementation with context",
+    "description": "Resume from previous step with accumulated context",
+    "command": "ccw cli exec '[continuation prompt]' --resume ${step3_cli_id} --tool codex --mode write",
+    "resume_from": "step3_cli_id",  // Reference previous step's CLI ID
+    "modification_points": ["[Continue from step 3]"],
+    "logic_flow": ["[Build on previous output]"],
+    "depends_on": [3],
+    "output": "continued_implementation",
+    "cli_output_id": "step4_cli_id"
   }
 ]
 ```
@@ -759,6 +836,8 @@ Use `analysis_results.complexity` or task count to determine structure:
 - Use provided context package: Extract all information from structured context
 - Respect memory-first rule: Use provided content (already loaded from memory/file)
 - Follow 6-field schema: All task JSONs must have id, title, status, context_package_path, meta, context, flow_control
+- **Assign CLI execution IDs**: Every task MUST have `cli_execution_id` (format: `{session_id}-{task_id}`)
+- **Compute CLI execution strategy**: Based on `depends_on`, set `cli_execution.strategy` (new/resume/fork/merge_fork)
 - Map artifacts: Use artifacts_inventory to populate task.context.artifacts array
 - Add MCP integration: Include MCP tool steps in flow_control.pre_analysis when capabilities available
 - Validate task count: Maximum 12 tasks hard limit, request re-scope if exceeded

.claude/skills/command-guide/reference/agents/cli-execution-agent.md

@@ -134,7 +134,7 @@ RULES: $(cat {selected_template}) | {constraints}
 ```
 analyze|plan → gemini (qwen fallback) + mode=analysis
 execute (simple|medium) → gemini (qwen fallback) + mode=write
-execute (complex) → codex + mode=auto
+execute (complex) → codex + mode=write
 discuss → multi (gemini + codex parallel)
 ```
 
@@ -155,7 +155,7 @@ MODE: analysis
 CONTEXT: @**/*
 EXPECTED: {output}
 RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
-" --tool gemini --cd {dir}
+" --tool gemini --mode analysis --cd {dir}
 
 # Qwen fallback: Replace '--tool gemini' with '--tool qwen'
 ```
@@ -165,14 +165,14 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt)
 ccw cli exec "..." --tool gemini --mode write --cd {dir}
 ```
 
-**Codex (Auto)**:
+**Codex (Write)**:
 ```bash
-ccw cli exec "..." --tool codex --mode auto --cd {dir}
+ccw cli exec "..." --tool codex --mode write --cd {dir}
 ```
 
 **Cross-Directory** (Gemini/Qwen):
 ```bash
-ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --cd src/auth --includeDirs ../shared
+ccw cli exec "CONTEXT: @**/* @../shared/**/*" --tool gemini --mode analysis --cd src/auth --includeDirs ../shared
 ```
 
 **Directory Scope**:

.claude/skills/command-guide/reference/agents/cli-explore-agent.md

@@ -85,7 +85,7 @@ MODE: analysis
 CONTEXT: @**/*
 EXPECTED: {from prompt}
 RULES: {from prompt, if template specified} | analysis=READ-ONLY
-" --tool gemini --cd {dir}
+" --tool gemini --mode analysis --cd {dir} 
 ```
 
 **Fallback Chain**: Gemini → Qwen → Codex → Bash-only

.claude/skills/command-guide/reference/agents/cli-lite-planning-agent.md

@@ -1,140 +1,117 @@
 ---
 name: cli-lite-planning-agent
 description: |
-  Specialized agent for executing CLI planning tools (Gemini/Qwen) to generate detailed implementation plans. Used by lite-plan workflow for Medium/High complexity tasks.
+  Generic planning agent for lite-plan and lite-fix workflows. Generates structured plan JSON based on provided schema reference.
 
   Core capabilities:
-  - Task decomposition (1-10 tasks with IDs: T1, T2...)
-  - Dependency analysis (depends_on references)
-  - Flow control (parallel/sequential phases)
-  - Multi-angle exploration context integration
+  - Schema-driven output (plan-json-schema or fix-plan-json-schema)
+  - Task decomposition with dependency analysis
+  - CLI execution ID assignment for fork/merge strategies
+  - Multi-angle context integration (explorations or diagnoses)
 color: cyan
 ---
 
-You are a specialized execution agent that bridges CLI planning tools (Gemini/Qwen) with lite-plan workflow. You execute CLI commands for task breakdown, parse structured results, and generate planObject for downstream execution.
+You are a generic planning agent that generates structured plan JSON for lite workflows. Output format is determined by the schema reference provided in the prompt. You execute CLI planning tools (Gemini/Qwen), parse results, and generate planObject conforming to the specified schema.
 
-## Output Schema
-
-**Reference**: `~/.claude/workflows/cli-templates/schemas/plan-json-schema.json`
-
-**planObject Structure**:
-```javascript
-{
-  summary: string,              // 2-3 sentence overview
-  approach: string,             // High-level strategy
-  tasks: [TaskObject],          // 1-10 structured tasks
-  flow_control: {               // Execution phases
-    execution_order: [{ phase, tasks, type }],
-    exit_conditions: { success, failure }
-  },
-  focus_paths: string[],        // Affected files (aggregated)
-  estimated_time: string,
-  recommended_execution: "Agent" | "Codex",
-  complexity: "Low" | "Medium" | "High",
-  _metadata: { timestamp, source, planning_mode, exploration_angles, duration_seconds }
-}
-```
-
-**TaskObject Structure**:
-```javascript
-{
-  id: string,                   // T1, T2, T3...
-  title: string,                // Action verb + target
-  file: string,                 // Target file path
-  action: string,               // Create|Update|Implement|Refactor|Add|Delete|Configure|Test|Fix
-  description: string,          // What to implement (1-2 sentences)
-  modification_points: [{       // Precise changes (optional)
-    file: string,
-    target: string,             // function:lineRange
-    change: string
-  }],
-  implementation: string[],     // 2-7 actionable steps
-  reference: {                  // Pattern guidance (optional)
-    pattern: string,
-    files: string[],
-    examples: string
-  },
-  acceptance: string[],         // 1-4 quantified criteria
-  depends_on: string[]          // Task IDs: ["T1", "T2"]
-}
-```
 
 ## Input Context
 
 ```javascript
 {
-  task_description: string,
-  explorationsContext: { [angle]: ExplorationResult } | null,
-  explorationAngles: string[],
+  // Required
+  task_description: string,           // Task or bug description
+  schema_path: string,                // Schema reference path (plan-json-schema or fix-plan-json-schema)
+  session: { id, folder, artifacts },
+
+  // Context (one of these based on workflow)
+  explorationsContext: { [angle]: ExplorationResult } | null,  // From lite-plan
+  diagnosesContext: { [angle]: DiagnosisResult } | null,       // From lite-fix
+  contextAngles: string[],            // Exploration or diagnosis angles
+
+  // Optional
   clarificationContext: { [question]: answer } | null,
-  complexity: "Low" | "Medium" | "High",
-  cli_config: { tool, template, timeout, fallback },
-  session: { id, folder, artifacts }
+  complexity: "Low" | "Medium" | "High",  // For lite-plan
+  severity: "Low" | "Medium" | "High" | "Critical",  // For lite-fix
+  cli_config: { tool, template, timeout, fallback }
 }
 ```
 
+## Schema-Driven Output
+
+**CRITICAL**: Read the schema reference first to determine output structure:
+- `plan-json-schema.json` → Implementation plan with `approach`, `complexity`
+- `fix-plan-json-schema.json` → Fix plan with `root_cause`, `severity`, `risk_level`
+
+```javascript
+// Step 1: Always read schema first
+const schema = Bash(`cat ${schema_path}`)
+
+// Step 2: Generate plan conforming to schema
+const planObject = generatePlanFromSchema(schema, context)
+```
+
 ## Execution Flow
 
 ```
-Phase 1: CLI Execution
-├─ Aggregate multi-angle exploration findings
+Phase 1: Schema & Context Loading
+├─ Read schema reference (plan-json-schema or fix-plan-json-schema)
+├─ Aggregate multi-angle context (explorations or diagnoses)
+└─ Determine output structure from schema
+
+Phase 2: CLI Execution
 ├─ Construct CLI command with planning template
 ├─ Execute Gemini (fallback: Qwen → degraded mode)
 └─ Timeout: 60 minutes
 
-Phase 2: Parsing & Enhancement
-├─ Parse CLI output sections (Summary, Approach, Tasks, Flow Control)
+Phase 3: Parsing & Enhancement
+├─ Parse CLI output sections
 ├─ Validate and enhance task objects
-└─ Infer missing fields from exploration context
+└─ Infer missing fields from context
 
-Phase 3: planObject Generation
-├─ Build planObject from parsed results
-├─ Generate flow_control from depends_on if not provided
-├─ Aggregate focus_paths from all tasks
-└─ Return to orchestrator (lite-plan)
+Phase 4: planObject Generation
+├─ Build planObject conforming to schema
+├─ Assign CLI execution IDs and strategies
+├─ Generate flow_control from depends_on
+└─ Return to orchestrator
 ```
 
 ## CLI Command Template
 
 ```bash
 ccw cli exec "
-PURPOSE: Generate implementation plan for {complexity} task
+PURPOSE: Generate plan for {task_description}
 TASK:
-• Analyze: {task_description}
-• Break down into 1-10 tasks with: id, title, file, action, description, modification_points, implementation, reference, acceptance, depends_on
-• Identify parallel vs sequential execution phases
+• Analyze task/bug description and context
+• Break down into tasks following schema structure
+• Identify dependencies and execution phases
 MODE: analysis
-CONTEXT: @**/* | Memory: {exploration_summary}
+CONTEXT: @**/* | Memory: {context_summary}
 EXPECTED:
-## Implementation Summary
+## Summary
 [overview]
 
-## High-Level Approach
-[strategy]
-
 ## Task Breakdown
-### T1: [Title]
-**File**: [path]
+### T1: [Title] (or FIX1 for fix-plan)
+**Scope**: [module/feature path]
 **Action**: [type]
 **Description**: [what]
 **Modification Points**: - [file]: [target] - [change]
 **Implementation**: 1. [step]
-**Reference**: - Pattern: [name] - Files: [paths] - Examples: [guidance]
-**Acceptance**: - [quantified criterion]
+**Acceptance/Verification**: - [quantified criterion]
 **Depends On**: []
 
 ## Flow Control
 **Execution Order**: - Phase parallel-1: [T1, T2] (independent)
-**Exit Conditions**: - Success: [condition] - Failure: [condition]
 
 ## Time Estimate
 **Total**: [time]
 
 RULES: $(cat ~/.claude/workflows/cli-templates/prompts/planning/02-breakdown-task-steps.txt) |
-- Acceptance must be quantified (counts, method names, metrics)
-- Dependencies use task IDs (T1, T2)
+- Follow schema structure from {schema_path}
+- Acceptance/verification must be quantified
+- Dependencies use task IDs
 - analysis=READ-ONLY
-" --tool {cli_tool} --cd {project_root}
+" --tool {cli_tool} --mode analysis --cd {project_root}
 ```
 
 ## Core Functions
@@ -279,6 +256,51 @@ function inferFile(task, ctx) {
 }
 ```
 
+### CLI Execution ID Assignment (MANDATORY)
+
+```javascript
+function assignCliExecutionIds(tasks, sessionId) {
+  const taskMap = new Map(tasks.map(t => [t.id, t]))
+  const childCount = new Map()
+
+  // Count children for each task
+  tasks.forEach(task => {
+    (task.depends_on || []).forEach(depId => {
+      childCount.set(depId, (childCount.get(depId) || 0) + 1)
+    })
+  })
+
+  tasks.forEach(task => {
+    task.cli_execution_id = `${sessionId}-${task.id}`
+    const deps = task.depends_on || []
+
+    if (deps.length === 0) {
+      task.cli_execution = { strategy: "new" }
+    } else if (deps.length === 1) {
+      const parent = taskMap.get(deps[0])
+      const parentChildCount = childCount.get(deps[0]) || 0
+      task.cli_execution = parentChildCount === 1
+        ? { strategy: "resume", resume_from: parent.cli_execution_id }
+        : { strategy: "fork", resume_from: parent.cli_execution_id }
+    } else {
+      task.cli_execution = {
+        strategy: "merge_fork",
+        merge_from: deps.map(depId => taskMap.get(depId).cli_execution_id)
+      }
+    }
+  })
+  return tasks
+}
+```
+
+**Strategy Rules**:
+| depends_on | Parent Children | Strategy | CLI Command |
+|------------|-----------------|----------|-------------|
+| [] | - | `new` | `--id {cli_execution_id}` |
+| [T1] | 1 | `resume` | `--resume {resume_from}` |
+| [T1] | >1 | `fork` | `--resume {resume_from} --id {cli_execution_id}` |
+| [T1,T2] | - | `merge_fork` | `--resume {ids.join(',')} --id {cli_execution_id}` |
+
 ### Flow Control Inference
 
 ```javascript
@@ -303,21 +325,44 @@ function inferFlowControl(tasks) {
 ### planObject Generation
 
 ```javascript
-function generatePlanObject(parsed, enrichedContext, input) {
+function generatePlanObject(parsed, enrichedContext, input, schemaType) {
   const tasks = validateAndEnhanceTasks(parsed.raw_tasks, enrichedContext)
+  assignCliExecutionIds(tasks, input.session.id)  // MANDATORY: Assign CLI execution IDs
   const flow_control = parsed.flow_control?.execution_order?.length > 0 ? parsed.flow_control : inferFlowControl(tasks)
-  const focus_paths = [...new Set(tasks.flatMap(t => [t.file, ...t.modification_points.map(m => m.file)]).filter(Boolean))]
+  const focus_paths = [...new Set(tasks.flatMap(t => [t.file || t.scope, ...t.modification_points.map(m => m.file)]).filter(Boolean))]
 
-  return {
-    summary: parsed.summary || `Implementation plan for: ${input.task_description.slice(0, 100)}`,
-    approach: parsed.approach || "Step-by-step implementation",
+  // Base fields (common to both schemas)
+  const base = {
+    summary: parsed.summary || `Plan for: ${input.task_description.slice(0, 100)}`,
     tasks,
     flow_control,
     focus_paths,
     estimated_time: parsed.time_estimate || `${tasks.length * 30} minutes`,
-    recommended_execution: input.complexity === "Low" ? "Agent" : "Codex",
-    complexity: input.complexity,
-    _metadata: { timestamp: new Date().toISOString(), source: "cli-lite-planning-agent", planning_mode: "agent-based", exploration_angles: input.explorationAngles || [], duration_seconds: Math.round((Date.now() - startTime) / 1000) }
+    recommended_execution: (input.complexity === "Low" || input.severity === "Low") ? "Agent" : "Codex",
+    _metadata: {
+      timestamp: new Date().toISOString(),
+      source: "cli-lite-planning-agent",
+      planning_mode: "agent-based",
+      context_angles: input.contextAngles || [],
+      duration_seconds: Math.round((Date.now() - startTime) / 1000)
+    }
+  }
+
+  // Schema-specific fields
+  if (schemaType === 'fix-plan') {
+    return {
+      ...base,
+      root_cause: parsed.root_cause || "Root cause from diagnosis",
+      strategy: parsed.strategy || "comprehensive_fix",
+      severity: input.severity || "Medium",
+      risk_level: parsed.risk_level || "medium"
+    }
+  } else {
+    return {
+      ...base,
+      approach: parsed.approach || "Step-by-step implementation",
+      complexity: input.complexity || "Medium"
+    }
   }
 }
 ```
@@ -383,9 +428,12 @@ function validateTask(task) {
 ## Key Reminders
 
 **ALWAYS**:
-- Generate task IDs (T1, T2, T3...)
+- **Read schema first** to determine output structure
+- Generate task IDs (T1/T2 for plan, FIX1/FIX2 for fix-plan)
 - Include depends_on (even if empty [])
-- Quantify acceptance criteria
+- **Assign cli_execution_id** (`{sessionId}-{taskId}`)
+- **Compute cli_execution strategy** based on depends_on
+- Quantify acceptance/verification criteria
 - Generate flow_control from dependencies
 - Handle CLI errors with fallback chain
 
@@ -394,3 +442,5 @@ function validateTask(task) {
 - Use vague acceptance criteria
 - Create circular dependencies
 - Skip task validation
+- **Skip CLI execution ID assignment**
+- **Ignore schema structure**

.claude/skills/command-guide/reference/agents/cli-planning-agent.md

@@ -134,7 +134,7 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/{template}) |
 - Consider previous iteration failures
 - Validate fix doesn't introduce new vulnerabilities
 - analysis=READ-ONLY
-" --tool {cli_tool} --cd {project_root} --timeout {timeout_value}
+" --tool {cli_tool} --mode analysis --cd {project_root} --timeout {timeout_value}
 ```
 
 **Layer-Specific Guidance Injection**:
@@ -529,7 +529,7 @@ See: `.process/iteration-{iteration}-cli-output.txt`
    ```bash
    ccw cli exec "PURPOSE: Analyze integration test failure...
    TASK: Examine component interactions, data flow, interface contracts...
-   RULES: Analyze full call stack and data flow across components" --tool gemini
+   RULES: Analyze full call stack and data flow across components" --tool gemini --mode analysis
    ```
 3. **Parse Output**: Extract RCA, 修复建议, 验证建议 sections
 4. **Generate Task JSON** (IMPL-fix-1.json):

.claude/skills/command-guide/reference/agents/code-developer.md

@@ -34,10 +34,10 @@ You are a code execution specialist focused on implementing high-quality, produc
 - **context-package.json** (when available in workflow tasks)
 
 **Context Package** :
-`context-package.json` provides artifact paths - read using `ccw session`:
+`context-package.json` provides artifact paths - read using Read tool or ccw session:
 ```bash
-# Get context package content from session
-ccw session read ${SESSION_ID} --type context
+# Get context package content from session using Read tool
+Read(.workflow/active/${SESSION_ID}/.process/context-package.json)
 # Returns parsed JSON with brainstorm_artifacts, focus_paths, etc.
 ```
 
@@ -123,7 +123,7 @@ When task JSON contains `flow_control.implementation_approach` array:
 
 **CLI Command Execution (CLI Execute Mode)**:
 When step contains `command` field with Codex CLI, execute via CCW CLI. For Codex resume:
-- First task (`depends_on: []`): `ccw cli exec "..." --tool codex --mode auto --cd [path]`
+- First task (`depends_on: []`): `ccw cli exec "..." --tool codex --mode write --cd [path]`
 - Subsequent tasks (has `depends_on`): Use CCW CLI with resume context to maintain session
 
 **Test-Driven Development**:

.claude/skills/command-guide/reference/agents/conceptual-planning-agent.md

@@ -109,7 +109,7 @@ This agent processes **simplified inline [FLOW_CONTROL]** format from brainstorm
 
 3. **load_session_metadata**
    - Action: Load session metadata
-   - Command: ccw session read WFS-{session} --type session
+   - Command: Read(.workflow/active/WFS-{session}/workflow-session.json)
    - Output: session_metadata
 ```
 
@@ -155,7 +155,7 @@ When called, you receive:
 - **User Context**: Specific requirements, constraints, and expectations from user discussion
 - **Output Location**: Directory path for generated analysis files
 - **Role Hint** (optional): Suggested role or role selection guidance
-- **context-package.json** (CCW Workflow): Artifact paths catalog - use `ccw session read {session} --type context` to get context package
+- **context-package.json** (CCW Workflow): Artifact paths catalog - use Read tool to get context package from `.workflow/active/{session}/.process/context-package.json`
 - **ASSIGNED_ROLE** (optional): Specific role assignment
 - **ANALYSIS_DIMENSIONS** (optional): Role-specific analysis dimensions
 

.claude/skills/command-guide/reference/agents/doc-generator.md

@@ -216,7 +216,7 @@ Before completion, verify:
 {
   "step": "analyze_module_structure",
   "action": "Deep analysis of module structure and API",
-  "command": "ccw cli exec \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @**/* System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\" --tool gemini --cd src/auth",
+  "command": "ccw cli exec \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @**/* System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\" --tool gemini --mode analysis --cd src/auth",
   "output_to": "module_analysis",
   "on_error": "fail"
 }

.claude/skills/command-guide/reference/agents/test-context-search-agent.md

@@ -46,7 +46,7 @@ You are a test context discovery specialist focused on gathering test coverage i
 - `find` - Test file discovery
 - `Grep` - Framework detection
 
-**Priority**: CodexLens MCP > ripgrep > find > grep
+**Priority**: Code-Index MCP > ripgrep > find > grep
 
 ### 3. Framework & Convention Analysis
 **Tools**:

.claude/skills/command-guide/reference/agents/test-fix-agent.md

@@ -83,7 +83,7 @@ When task JSON contains implementation_approach array:
   - L1 (Unit): `*.test.*`, `*.spec.*` in `__tests__/`, `tests/unit/`
   - L2 (Integration): `tests/integration/`, `*.integration.test.*`
   - L3 (E2E): `tests/e2e/`, `*.e2e.test.*`, `cypress/`, `playwright/`
-- **context-package.json** (CCW Workflow): Use `ccw session read {session} --type context` to get context package with artifact paths
+- **context-package.json** (CCW Workflow): Use Read tool to get context package from `.workflow/active/{session}/.process/context-package.json`
 - Identify test commands from project configuration
 
 ```bash

.claude/skills/command-guide/reference/commands/memory/docs.md

@@ -74,7 +74,7 @@ SlashCommand(command="/workflow:session:start --type docs --new \"{project_name}
 
 ```bash
 # Update workflow-session.json with docs-specific fields
-ccw session update {sessionId} --type session --content '{"target_path":"{target_path}","project_root":"{project_root}","project_name":"{project_name}","mode":"full","tool":"gemini","cli_execute":false}'
+ccw session {sessionId} write workflow-session.json '{"target_path":"{target_path}","project_root":"{project_root}","project_name":"{project_name}","mode":"full","tool":"gemini","cli_execute":false}'
 ```
 
 ### Phase 2: Analyze Structure
@@ -136,7 +136,7 @@ bash(if [ -d .workflow/docs/\${project_name} ]; then find .workflow/docs/\${proj
 
 ```bash
 # Count existing docs from doc-planning-data.json
-ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq '.existing_docs.file_list | length'
+ccw session WFS-docs-{timestamp} read .process/doc-planning-data.json --raw | jq '.existing_docs.file_list | length'
 # Or read entire process file and parse
 ```
 
@@ -191,10 +191,10 @@ Large Projects (single dir >10 docs):
 
 ```bash
 # 1. Get top-level directories from doc-planning-data.json
-ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq -r '.top_level_dirs[]'
+ccw session WFS-docs-{timestamp} read .process/doc-planning-data.json --raw | jq -r '.top_level_dirs[]'
 
 # 2. Get mode from workflow-session.json
-ccw session read WFS-docs-{timestamp} --type session --raw | jq -r '.mode // "full"'
+ccw session WFS-docs-{timestamp} read workflow-session.json --raw | jq -r '.mode // "full"'
 
 # 3. Check for HTTP API
 bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo "NO_API")
@@ -223,7 +223,7 @@ bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo
 
 **Task ID Calculation**:
 ```bash
-group_count=$(ccw session read WFS-docs-{timestamp} --type process --filename doc-planning-data.json --raw | jq '.groups.count')
+group_count=$(ccw session WFS-docs-{timestamp} read .process/doc-planning-data.json --raw | jq '.groups.count')
 readme_id=$((group_count + 1))   # Next ID after groups
 arch_id=$((group_count + 2))
 api_id=$((group_count + 3))
@@ -239,9 +239,9 @@ api_id=$((group_count + 3))
 | **CLI** | true | implementation_approach | write | --mode write | Execute CLI commands, validate output |
 
 **Command Patterns**:
-- Gemini/Qwen: `ccw cli exec "..." --tool gemini --cd dir`
+- Gemini/Qwen: `ccw cli exec "..." --tool gemini --mode analysis --cd dir`
 - CLI Mode: `ccw cli exec "..." --tool gemini --mode write --cd dir`
-- Codex: `ccw cli exec "..." --tool codex --mode auto --cd dir`
+- Codex: `ccw cli exec "..." --tool codex --mode write --cd dir`
 
 **Generation Process**:
 1. Read configuration values (tool, cli_execute, mode) from workflow-session.json
@@ -286,8 +286,8 @@ api_id=$((group_count + 3))
         "step": "load_precomputed_data",
         "action": "Load Phase 2 analysis and extract group directories",
         "commands": [
-          "ccw session read ${session_id} --type process --filename doc-planning-data.json",
-          "ccw session read ${session_id} --type process --filename doc-planning-data.json --raw | jq '.groups.assignments[] | select(.group_id == \"${group_number}\") | .directories'"
+          "ccw session ${session_id} read .process/doc-planning-data.json",
+          "ccw session ${session_id} read .process/doc-planning-data.json --raw | jq '.groups.assignments[] | select(.group_id == \"${group_number}\") | .directories'"
         ],
         "output_to": "phase2_context",
         "note": "Single JSON file contains all Phase 2 analysis results"
@@ -364,7 +364,7 @@ api_id=$((group_count + 3))
       },
       {
         "step": "analyze_project",
-        "command": "bash(gemini \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\")",
+        "command": "bash(ccw cli exec \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\" --tool gemini --mode analysis)",
         "output_to": "project_outline"
       }
     ],
@@ -404,7 +404,7 @@ api_id=$((group_count + 3))
     "pre_analysis": [
       {"step": "load_existing_docs", "command": "bash(cat .workflow/docs/${project_name}/{ARCHITECTURE,EXAMPLES}.md 2>/dev/null || echo 'No existing docs')", "output_to": "existing_arch_examples"},
       {"step": "load_all_docs", "command": "bash(cat .workflow/docs/${project_name}/README.md && find .workflow/docs/${project_name} -type f -name '*.md' ! -path '*/README.md' ! -path '*/ARCHITECTURE.md' ! -path '*/EXAMPLES.md' ! -path '*/api/*' | xargs cat)", "output_to": "all_docs"},
-      {"step": "analyze_architecture", "command": "bash(gemini \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview and examples\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture + Examples outline\")", "output_to": "arch_examples_outline"}
+      {"step": "analyze_architecture", "command": "bash(ccw cli exec \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview and examples\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture + Examples outline\" --tool gemini --mode analysis)", "output_to": "arch_examples_outline"}
     ],
     "implementation_approach": [
       {
@@ -441,7 +441,7 @@ api_id=$((group_count + 3))
     "pre_analysis": [
       {"step": "discover_api", "command": "bash(rg 'router\\.| @(Get|Post)' -g '*.{ts,js}')", "output_to": "endpoint_discovery"},
       {"step": "load_existing_api", "command": "bash(cat .workflow/docs/${project_name}/api/README.md 2>/dev/null || echo 'No existing API docs')", "output_to": "existing_api_docs"},
-      {"step": "analyze_api", "command": "bash(gemini \"PURPOSE: Document HTTP API\\nTASK: Analyze endpoints\\nMODE: analysis\\nCONTEXT: @src/api/**/* [endpoint_discovery]\\nEXPECTED: API outline\")", "output_to": "api_outline"}
+      {"step": "analyze_api", "command": "bash(ccw cli exec \"PURPOSE: Document HTTP API\\nTASK: Analyze endpoints\\nMODE: analysis\\nCONTEXT: @src/api/**/* [endpoint_discovery]\\nEXPECTED: API outline\" --tool gemini --mode analysis)", "output_to": "api_outline"}
     ],
     "implementation_approach": [
       {

.claude/skills/command-guide/reference/commands/memory/load.md

@@ -147,7 +147,7 @@ RULES:
 - Identify key architecture patterns and technical constraints
 - Extract integration points and development standards
 - Output concise, structured format
-" --tool ${tool}
+" --tool ${tool} --mode analysis
 \`\`\`
 
 ### Step 4: Generate Core Content Package

.claude/skills/command-guide/reference/commands/memory/workflow-skill-memory.md

@@ -198,7 +198,7 @@ Objectives:
    CONTEXT: @IMPL_PLAN.md @workflow-session.json
    EXPECTED: Structured lessons and conflicts in JSON format
    RULES: Template reference from skill-aggregation.txt
-   " --tool gemini --cd .workflow/.archives/{session_id}
+   " --tool gemini --mode analysis --cd .workflow/.archives/{session_id}
 
 3.5. **Generate SKILL.md Description** (CRITICAL for auto-loading):
 
@@ -345,7 +345,7 @@ Objectives:
    CONTEXT: [Provide aggregated JSON data]
    EXPECTED: Final aggregated structure for SKILL documents
    RULES: Template reference from skill-aggregation.txt
-   " --tool gemini
+   " --tool gemini --mode analysis
 
 3. Read templates for formatting (same 4 templates as single mode)
 

.claude/skills/command-guide/reference/commands/workflow/execute.md

@@ -149,7 +149,7 @@ Parse user input (supports: number "1", full ID "WFS-auth-system", or partial "a
 
 #### Step 1.3: Load Session Metadata
 ```bash
-ccw session read ${sessionId} --type session
+ccw session ${sessionId} read workflow-session.json
 ```
 
 **Output**: Store session metadata in memory

.claude/skills/command-guide/reference/commands/workflow/lite-execute.md

@@ -473,10 +473,10 @@ Detailed plan: ${executionContext.session.artifacts.plan}`)
   return prompt
 }
 
-ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode auto
+ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write
 ```
 
-**Execution with tracking**:
+**Execution with fixed IDs** (predictable ID pattern):
 ```javascript
 // Launch CLI in foreground (NOT background)
 // Timeout based on complexity: Low=40min, Medium=60min, High=100min
@@ -486,15 +486,48 @@ const timeoutByComplexity = {
   "High": 6000000    // 100 minutes
 }
 
+// Generate fixed execution ID: ${sessionId}-${groupId}
+// This enables predictable ID lookup without relying on resume context chains
+const sessionId = executionContext?.session?.id || 'standalone'
+const fixedExecutionId = `${sessionId}-${batch.groupId}`  // e.g., "implement-auth-2025-12-13-P1"
+
+// Check if resuming from previous failed execution
+const previousCliId = batch.resumeFromCliId || null
+
+// Build command with fixed ID (and optional resume for continuation)
+const cli_command = previousCliId
+  ? `ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
+  : `ccw cli exec "${buildCLIPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
+
 bash_result = Bash(
   command=cli_command,
   timeout=timeoutByComplexity[planObject.complexity] || 3600000
 )
 
+// Execution ID is now predictable: ${fixedExecutionId}
+// Can also extract from output: "ID: implement-auth-2025-12-13-P1"
+const cliExecutionId = fixedExecutionId
+
 // Update TodoWrite when execution completes
 ```
 
-**Result Collection**: After completion, analyze output and collect result following `executionResult` structure
+**Resume on Failure** (with fixed ID):
+```javascript
+// If execution failed or timed out, offer resume option
+if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
+  console.log(`
+⚠️ Execution incomplete. Resume available:
+   Fixed ID: ${fixedExecutionId}
+   Lookup: ccw cli detail ${fixedExecutionId}
+   Resume: ccw cli exec "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
+`)
+
+  // Store for potential retry in same session
+  batch.resumeFromCliId = fixedExecutionId
+}
+```
+
+**Result Collection**: After completion, analyze output and collect result following `executionResult` structure (include `cliExecutionId` for resume capability)
 
 ### Step 4: Progress Tracking
 
@@ -541,15 +574,30 @@ RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-review-code-q
 # - Report findings directly
 
 # Method 2: Gemini Review (recommended)
-ccw cli exec "[Shared Prompt Template with artifacts]" --tool gemini
+ccw cli exec "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
 # CONTEXT includes: @**/* @${plan.json} [@${exploration.json}]
 
 # Method 3: Qwen Review (alternative)
-ccw cli exec "[Shared Prompt Template with artifacts]" --tool qwen
+ccw cli exec "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
 # Same prompt as Gemini, different execution engine
 
 # Method 4: Codex Review (autonomous)
-ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --mode auto
+ccw cli exec "[Verify plan acceptance criteria at ${plan.json}]" --tool codex --mode write
+```
+
+**Multi-Round Review with Fixed IDs**:
+```javascript
+// Generate fixed review ID
+const reviewId = `${sessionId}-review`
+
+// First review pass with fixed ID
+const reviewResult = Bash(`ccw cli exec "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
+
+// If issues found, continue review dialog with fixed ID chain
+if (hasUnresolvedIssues(reviewResult)) {
+  // Resume with follow-up questions
+  Bash(`ccw cli exec "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
+}
 ```
 
 **Implementation Note**: Replace `[Shared Prompt Template with artifacts]` placeholder with actual template content, substituting:
@@ -623,8 +671,10 @@ console.log(`✓ Development index: [${category}] ${entry.title}`)
 | Empty file | File exists but no content | Error: "File is empty: {path}. Provide task description." |
 | Invalid Enhanced Task JSON | JSON missing required fields | Warning: "Missing required fields. Treating as plain text." |
 | Malformed JSON | JSON parsing fails | Treat as plain text (expected for non-JSON files) |
-| Execution failure | Agent/Codex crashes | Display error, save partial progress, suggest retry |
+| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli exec "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
+| Execution timeout | CLI exceeded timeout | Use fixed ID for resume with extended timeout |
 | Codex unavailable | Codex not installed | Show installation instructions, offer Agent execution |
+| Fixed ID not found | Custom ID lookup failed | Check `ccw cli history`, verify date directories |
 
 ## Data Structures
 
@@ -679,8 +729,20 @@ Collected after each execution call completes:
   tasksSummary: string,                // Brief description of tasks handled
   completionSummary: string,           // What was completed
   keyOutputs: string,                  // Files created/modified, key changes
-  notes: string                        // Important context for next execution
+  notes: string,                       // Important context for next execution
+  fixedCliId: string | null            // Fixed CLI execution ID (e.g., "implement-auth-2025-12-13-P1")
 }
 ```
 
 Appended to `previousExecutionResults` array for context continuity in multi-execution scenarios.
+
+**Fixed ID Pattern**: `${sessionId}-${groupId}` enables predictable lookup without auto-generated timestamps.
+
+**Resume Usage**: If `status` is "partial" or "failed", use `fixedCliId` to resume:
+```bash
+# Lookup previous execution
+ccw cli detail ${fixedCliId}
+
+# Resume with new fixed ID for retry
+ccw cli exec "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
+```

.claude/skills/command-guide/reference/commands/workflow/lite-fix.md

@@ -72,17 +72,60 @@ Phase 5: Dispatch
 ### Phase 1: Intelligent Multi-Angle Diagnosis
 
 **Session Setup** (MANDATORY - follow exactly):
+
+**Option 1: Using CLI Command** (Recommended for simplicity):
+```bash
+# Generate session ID
+bug_slug=$(echo "${bug_description}" | tr '[:upper:]' '[:lower:]' | tr -cs '[:alnum:]' '-' | cut -c1-40)
+date_str=$(date -u '+%Y-%m-%d')
+session_id="${bug_slug}-${date_str}"
+
+# Initialize lite-fix session (location auto-inferred from type)
+ccw session init "${session_id}" \
+  --type lite-fix \
+  --content "{\"description\":\"${bug_description}\",\"severity\":\"${severity}\"}"
+
+
+
+# Get session folder
+session_folder=".workflow/.lite-fix/${session_id}"
+echo "Session initialized: ${session_id} at ${session_folder}"
+```
+
+**Option 2: Using session_manager Tool** (For programmatic access):
 ```javascript
 // Helper: Get UTC+8 (China Standard Time) ISO string
 const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
 
 const bugSlug = bug_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
-const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-11-29
+const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-12-17
 
-const sessionId = `${bugSlug}-${dateStr}`  // e.g., "user-avatar-upload-fails-2025-11-29"
-const sessionFolder = `.workflow/.lite-fix/${sessionId}`
+const sessionId = `${bugSlug}-${dateStr}`  // e.g., "user-avatar-upload-fails-2025-12-17"
 
-bash(`mkdir -p ${sessionFolder} && test -d ${sessionFolder} && echo "SUCCESS: ${sessionFolder}" || echo "FAILED: ${sessionFolder}"`)
+
+
+const sessionFolder = initResult.result.path
+console.log(`Session initialized: ${sessionId} at ${sessionFolder}`)
+```
+
+**Session File Structure**:
+- `session-metadata.json` - Session metadata (created at init, contains description, severity, status)
+- `fix-plan.json` - Actual fix planning content (created later in Phase 3, contains fix tasks, diagnosis results)
+
+**Metadata Field Usage**:
+- `description`: Displayed in dashboard session list (replaces session ID as title)
+- `severity`: Used for fix planning strategy selection (Low/Medium → Direct Claude, High/Critical → Agent)
+- `created_at`: Displayed in dashboard timeline
+- `status`: Updated through workflow (diagnosing → fixing → completed)
+- Custom fields: Any additional fields in metadata are saved and accessible programmatically
+
+**Accessing Session Data**:
+```bash
+# Read session metadata
+ccw session ${session_id} read session-metadata.json
+
+# Read fix plan content (after Phase 3 completion)
+ccw session ${session_id} read fix-plan.json
 ```
 
 **Diagnosis Decision Logic**:

.claude/skills/command-guide/reference/commands/workflow/lite-plan.md

@@ -72,17 +72,57 @@ Phase 5: Dispatch
 ### Phase 1: Intelligent Multi-Angle Exploration
 
 **Session Setup** (MANDATORY - follow exactly):
+
+**Option 1: Using CLI Command** (Recommended for simplicity):
+```bash
+# Generate session ID
+task_slug=$(echo "${task_description}" | tr '[:upper:]' '[:lower:]' | tr -cs '[:alnum:]' '-' | cut -c1-40)
+date_str=$(date -u '+%Y-%m-%d')
+session_id="${task_slug}-${date_str}"
+
+# Initialize lite-plan session (location auto-inferred from type)
+ccw session init "${session_id}" \
+  --type lite-plan \
+  --content "{\"description\":\"${task_description}\",\"complexity\":\"${complexity}\"}"
+
+# Get session folder
+session_folder=".workflow/.lite-plan/${session_id}"
+echo "Session initialized: ${session_id} at ${session_folder}"
+```
+
+**Option 2: Using session_manager Tool** (For programmatic access):
 ```javascript
 // Helper: Get UTC+8 (China Standard Time) ISO string
 const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
 
 const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
-const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-11-29
+const dateStr = getUtc8ISOString().substring(0, 10)  // Format: 2025-12-17
 
-const sessionId = `${taskSlug}-${dateStr}`  // e.g., "implement-jwt-refresh-2025-11-29"
-const sessionFolder = `.workflow/.lite-plan/${sessionId}`
+const sessionId = `${taskSlug}-${dateStr}`  // e.g., "implement-jwt-refresh-2025-12-17"
 
-bash(`mkdir -p ${sessionFolder} && test -d ${sessionFolder} && echo "SUCCESS: ${sessionFolder}" || echo "FAILED: ${sessionFolder}"`)
+
+
+const sessionFolder = initResult.result.path
+console.log(`Session initialized: ${sessionId} at ${sessionFolder}`)
+```
+
+**Session File Structure**:
+- `session-metadata.json` - Session metadata (created at init, contains description, complexity, status)
+- `plan.json` - Actual planning content (created later in Phase 3, contains tasks, steps, dependencies)
+
+**Metadata Field Usage**:
+- `description`: Displayed in dashboard session list (replaces session ID as title)
+- `complexity`: Used for planning strategy selection (Low → Direct Claude, Medium/High → Agent)
+- `created_at`: Displayed in dashboard timeline
+- Custom fields: Any additional fields in metadata are saved and accessible programmatically
+
+**Accessing Session Data**:
+```bash
+# Read session metadata
+ccw session ${session_id} read session-metadata.json
+
+# Read plan content (after Phase 3 completion)
+ccw session ${session_id} read plan.json
 ```
 
 **Exploration Decision Logic**:

.claude/skills/command-guide/reference/commands/workflow/review.md

@@ -112,14 +112,18 @@ After bash validation, the model takes control to:
 
 1. **Load Context**: Read completed task summaries and changed files
    ```bash
-   # Load implementation summaries
-   ccw session read ${sessionId} --type summary --raw
+   # Load implementation summaries (iterate through .summaries/ directory)
+   for summary in .workflow/active/${sessionId}/.summaries/*.md; do
+     cat "$summary"
+   done
 
    # Load test results (if available)
-   ccw session read ${sessionId} --type summary --filename "TEST-FIX-*.md" --raw 2>/dev/null
+   for test_summary in .workflow/active/${sessionId}/.summaries/TEST-FIX-*.md 2>/dev/null; do
+     cat "$test_summary"
+   done
 
    # Get session created_at for git log filter
-   created_at=$(ccw session read ${sessionId} --type session --raw | jq -r .created_at)
+   created_at=$(ccw session ${sessionId} read workflow-session.json | jq -r .created_at)
    git log --since="$created_at" --name-only --pretty=format: | sort -u
    ```
 
@@ -170,11 +174,13 @@ After bash validation, the model takes control to:
    - Verify all requirements and acceptance criteria met:
      ```bash
      # Load task requirements and acceptance criteria
-     ccw session read ${sessionId} --type task --raw | jq -r '
-       "Task: " + .id + "\n" +
-       "Requirements: " + (.context.requirements | join(", ")) + "\n" +
-       "Acceptance: " + (.context.acceptance | join(", "))
-     '
+     for task_file in .workflow/active/${sessionId}/.task/*.json; do
+       cat "$task_file" | jq -r '
+         "Task: " + .id + "\n" +
+         "Requirements: " + (.context.requirements | join(", ")) + "\n" +
+         "Acceptance: " + (.context.acceptance | join(", "))
+       '
+     done
 
      # Check implementation summaries against requirements
      ccw cli exec "

.claude/skills/command-guide/reference/commands/workflow/session/complete.md

@@ -34,7 +34,7 @@ ccw session list --location active
 #### Step 1.2: Check for Existing Archiving Marker (Resume Detection)
 ```bash
 # Check if session is already being archived (marker file exists)
-ccw session read WFS-session-name --type process --filename .archiving 2>/dev/null && echo "RESUMING" || echo "NEW"
+ccw session WFS-session-name read .process/.archiving 2>/dev/null && echo "RESUMING" || echo "NEW"
 ```
 
 **If RESUMING**:
@@ -47,7 +47,7 @@ ccw session read WFS-session-name --type process --filename .archiving 2>/dev/nu
 #### Step 1.3: Create Archiving Marker
 ```bash
 # Mark session as "archiving in progress"
-ccw session write WFS-session-name --type process --filename .archiving --content ''
+ccw session WFS-session-name write .process/.archiving ''
 ```
 **Purpose**:
 - Prevents concurrent operations on this session
@@ -171,8 +171,8 @@ ccw session archive WFS-session-name
 
 #### Step 3.2: Update Manifest
 ```bash
-# Read current manifest using ccw (or create empty array if not exists)
-ccw session read manifest --type manifest --raw 2>/dev/null || echo "[]"
+# Check if manifest exists
+test -f .workflow/archives/manifest.json && echo "EXISTS" || echo "NOT_FOUND"
 ```
 
 **JSON Update Logic**:
@@ -221,8 +221,8 @@ rm .workflow/archives/WFS-session-name/.process/.archiving 2>/dev/null || true
 
 #### Step 4.1: Check Project State Exists
 ```bash
-# Check project state using ccw
-ccw session read project --type project 2>/dev/null && echo "EXISTS" || echo "SKIP"
+# Check if project.json exists
+test -f .workflow/project.json && echo "EXISTS" || echo "SKIP"
 ```
 
 **If SKIP**: Output warning and skip Phase 4
@@ -249,11 +249,6 @@ const featureId = title.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 5
 
 #### Step 4.3: Update project.json
 
-```bash
-# Read current project state using ccw
-ccw session read project --type project --raw
-```
-
 **JSON Update Logic**:
 ```javascript
 // Read existing project.json (created by /workflow:init)

.claude/skills/command-guide/reference/commands/workflow/session/list.md

@@ -30,7 +30,7 @@ ccw session stats WFS-session
 
 ### Step 3: Read Session Metadata
 ```bash
-ccw session read WFS-session --type session
+ccw session WFS-session read workflow-session.json
 # Returns: session_id, status, project, created_at, etc.
 ```
 
@@ -39,8 +39,8 @@ ccw session read WFS-session --type session
 ### Basic Operations
 - **List all sessions**: `ccw session list`
 - **List active only**: `ccw session list --location active`
-- **Read session data**: `ccw session read WFS-xxx --type session`
-- **Get task stats**: `ccw session stats WFS-xxx`
+- **Read session data**: `ccw session WFS-xxx read workflow-session.json`
+- **Get task stats**: `ccw session WFS-xxx stats`
 
 ## Simple Output Format
 

.claude/skills/command-guide/reference/commands/workflow/session/resume.md

@@ -23,7 +23,7 @@ ccw session list --location active
 
 ### Step 2: Check Session Status
 ```bash
-ccw session read WFS-session --type session
+ccw session WFS-session read workflow-session.json
 # Check .status field in response
 ```
 
@@ -35,17 +35,15 @@ ccw session list --location active
 
 ### Step 4: Update Session Status to Active
 ```bash
-ccw session status WFS-session active
-# Or with full update:
-ccw session update WFS-session --type session --content '{"status":"active","resumed_at":"2025-12-10T08:00:00Z"}'
+ccw session WFS-session status active
 ```
 
 ## Simple Commands
 
 ### Basic Operations
 - **List sessions**: `ccw session list --location active`
-- **Check status**: `ccw session read WFS-xxx --type session`
-- **Update status**: `ccw session status WFS-xxx active`
+- **Check status**: `ccw session WFS-xxx read workflow-session.json`
+- **Update status**: `ccw session WFS-xxx status active`
 
 ### Resume Result
 ```

.claude/skills/command-guide/reference/commands/workflow/session/start.md

@@ -30,10 +30,17 @@ The `--type` parameter classifies sessions for CCW dashboard organization:
 | `tdd` | TDD-based development | `/workflow:tdd-plan` |
 | `test` | Test generation/fix sessions | `/workflow:test-fix-gen` |
 | `docs` | Documentation sessions | `/memory:docs` |
+| `lite-plan` | Lightweight planning workflow | `/workflow:lite-plan` |
+| `lite-fix` | Lightweight bug fix workflow | `/workflow:lite-fix` |
+
+**Special Behavior for `lite-plan` and `lite-fix`**:
+- These types automatically infer the storage location (`.workflow/.lite-plan/` or `.workflow/.lite-fix/`)
+- No need to specify `--location` parameter when using these types
+- Alternative: Use `--location lite-plan` or `--location lite-fix` directly
 
 **Validation**: If `--type` is provided with invalid value, return error:
 ```
-ERROR: Invalid session type. Valid types: workflow, review, tdd, test, docs
+ERROR: Invalid session type. Valid types: workflow, review, tdd, test, docs, lite-plan, lite-fix
 ```
 
 ## Step 0: Initialize Project State (First-time Only)
@@ -75,7 +82,7 @@ ccw session list --location active
 
 ### Step 2: Display Session Metadata
 ```bash
-ccw session read WFS-promptmaster-platform --type session
+ccw session WFS-promptmaster-platform read workflow-session.json
 ```
 
 ### Step 4: User Decision
@@ -102,7 +109,7 @@ ccw session list --location active
 # Pattern: WFS-{lowercase-slug-from-description}
 
 # Create session with ccw (creates directories + metadata atomically)
-ccw session init WFS-implement-oauth2-auth --type workflow --content '{"project":"implement OAuth2 auth","status":"planning"}'
+ccw session init WFS-implement-oauth2-auth --type workflow
 ```
 
 **Output**: `SESSION_ID: WFS-implement-oauth2-auth`
@@ -113,7 +120,7 @@ ccw session init WFS-implement-oauth2-auth --type workflow --content '{"project"
 ccw session list --location active
 
 # Read session metadata for relevance check
-ccw session read WFS-promptmaster-platform --type session
+ccw session WFS-promptmaster-platform read workflow-session.json
 
 # If task contains project keywords → Reuse session
 # If task unrelated → Create new session (use Step 2a)
@@ -149,10 +156,41 @@ ccw session list --location active
 
 ### Step 2: Create Session Structure
 ```bash
-# Single command creates directories (.process, .task, .summaries) + metadata
-ccw session init WFS-fix-login-bug --type workflow --content '{"project":"fix login bug","status":"planning"}'
+# Basic init - creates directories + default metadata
+ccw session init WFS-fix-login-bug --type workflow
+
+# Advanced init - with custom metadata
+ccw session init WFS-oauth-implementation --type workflow --content '{"description":"OAuth2 authentication system","priority":"high","complexity":"medium"}'
 ```
 
+**Default Metadata** (auto-generated):
+```json
+{
+  "session_id": "WFS-fix-login-bug",
+  "type": "workflow",
+  "status": "planning",
+  "created_at": "2025-12-17T..."
+}
+```
+
+**Custom Metadata** (merged with defaults):
+```json
+{
+  "session_id": "WFS-oauth-implementation",
+  "type": "workflow",
+  "status": "planning",
+  "created_at": "2025-12-17T...",
+  "description": "OAuth2 authentication system",
+  "priority": "high",
+  "complexity": "medium"
+}
+```
+
+**Field Usage**:
+- `description`: Displayed in dashboard (replaces session_id as title)
+- `status`: Can override default "planning" (e.g., "active", "implementing")
+- Custom fields: Any additional fields are saved and accessible programmatically
+
 **Output**: `SESSION_ID: WFS-fix-login-bug`
 
 ## Execution Guideline

.claude/skills/command-guide/reference/commands/workflow/tdd-verify.md

@@ -77,18 +77,32 @@ find .workflow/active/ -name "WFS-*" -type d | head -1 | sed 's/.*\///'
 
 ```bash
 # Load all task JSONs
-ccw session read {sessionId} --type task
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file"
+done
 
 # Extract task IDs
-ccw session read {sessionId} --type task --raw | jq -r '.id'
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file" | jq -r '.id'
+done
 
 # Check dependencies - read tasks and filter for IMPL/REFACTOR
-ccw session read {sessionId} --type task --task-id "IMPL-*" --raw | jq -r '.context.depends_on[]?'
-ccw session read {sessionId} --type task --task-id "REFACTOR-*" --raw | jq -r '.context.depends_on[]?'
+for task_file in .workflow/active/{sessionId}/.task/IMPL-*.json; do
+  cat "$task_file" | jq -r '.context.depends_on[]?'
+done
+
+for task_file in .workflow/active/{sessionId}/.task/REFACTOR-*.json; do
+  cat "$task_file" | jq -r '.context.depends_on[]?'
+done
 
 # Check meta fields
-ccw session read {sessionId} --type task --raw | jq -r '.meta.tdd_phase'
-ccw session read {sessionId} --type task --raw | jq -r '.meta.agent'
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file" | jq -r '.meta.tdd_phase'
+done
+
+for task_file in .workflow/active/{sessionId}/.task/*.json; do
+  cat "$task_file" | jq -r '.meta.agent'
+done
 ```
 
 **Validation**:
@@ -139,7 +153,7 @@ EXPECTED:
 - Red-Green-Refactor cycle validation
 - Best practices adherence assessment
 RULES: Focus on TDD best practices and workflow adherence. Be specific about violations and improvements.
-" --tool gemini --cd project-root > .workflow/active/{sessionId}/TDD_COMPLIANCE_REPORT.md
+" --tool gemini --mode analysis --cd project-root > .workflow/active/{sessionId}/TDD_COMPLIANCE_REPORT.md
 ```
 
 **Output**: TDD_COMPLIANCE_REPORT.md

.claude/skills/command-guide/reference/commands/workflow/tools/conflict-resolution.md

@@ -152,7 +152,7 @@ Task(subagent_type="cli-execution-agent", prompt=`
     - ModuleOverlap conflicts with overlap_analysis
     - Targeted clarification questions
   RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-analyze-code-patterns.txt) | Focus on breaking changes, migration needs, and functional overlaps | Prioritize exploration-identified conflicts | analysis=READ-ONLY
-  " --tool gemini --cd {project_root}
+  " --tool gemini --mode analysis --cd {project_root}
 
   Fallback: Qwen (same prompt) → Claude (manual analysis)
 

.claude/skills/command-guide/reference/commands/workflow/tools/task-generate-agent.md

@@ -28,6 +28,12 @@ Input Parsing:
    ├─ Parse flags: --session
    └─ Validation: session_id REQUIRED
 
+Phase 0: User Configuration (Interactive)
+   ├─ Question 1: Supplementary materials/guidelines?
+   ├─ Question 2: Execution method preference (Agent/CLI/Hybrid)
+   ├─ Question 3: CLI tool preference (if CLI selected)
+   └─ Store: userConfig for agent prompt
+
 Phase 1: Context Preparation & Module Detection (Command)
    ├─ Assemble session paths (metadata, context package, output dirs)
    ├─ Provide metadata (session_id, execution_mode, mcp_capabilities)
@@ -57,6 +63,82 @@ Phase 3: Integration (+1 Coordinator, Multi-Module Only)
 
 ## Document Generation Lifecycle
 
+### Phase 0: User Configuration (Interactive)
+
+**Purpose**: Collect user preferences before task generation to ensure generated tasks match execution expectations.
+
+**User Questions**:
+```javascript
+AskUserQuestion({
+  questions: [
+    {
+      question: "Do you have supplementary materials or guidelines to include?",
+      header: "Materials",
+      multiSelect: false,
+      options: [
+        { label: "No additional materials", description: "Use existing context only" },
+        { label: "Provide file paths", description: "I'll specify paths to include" },
+        { label: "Provide inline content", description: "I'll paste content directly" }
+      ]
+    },
+    {
+      question: "Select execution method for generated tasks:",
+      header: "Execution",
+      multiSelect: false,
+      options: [
+        { label: "Agent (Recommended)", description: "Claude agent executes tasks directly" },
+        { label: "Hybrid", description: "Agent orchestrates, calls CLI for complex steps" },
+        { label: "CLI Only", description: "All execution via CLI tools (codex/gemini/qwen)" }
+      ]
+    },
+    {
+      question: "If using CLI, which tool do you prefer?",
+      header: "CLI Tool",
+      multiSelect: false,
+      options: [
+        { label: "Codex (Recommended)", description: "Best for implementation tasks" },
+        { label: "Gemini", description: "Best for analysis and large context" },
+        { label: "Qwen", description: "Alternative analysis tool" },
+        { label: "Auto", description: "Let agent decide per-task" }
+      ]
+    }
+  ]
+})
+```
+
+**Handle Materials Response**:
+```javascript
+if (userConfig.materials === "Provide file paths") {
+  // Follow-up question for file paths
+  const pathsResponse = AskUserQuestion({
+    questions: [{
+      question: "Enter file paths to include (comma-separated or one per line):",
+      header: "Paths",
+      multiSelect: false,
+      options: [
+        { label: "Enter paths", description: "Provide paths in text input" }
+      ]
+    }]
+  })
+  userConfig.supplementaryPaths = parseUserPaths(pathsResponse)
+}
+```
+
+**Build userConfig**:
+```javascript
+const userConfig = {
+  supplementaryMaterials: {
+    type: "none|paths|inline",
+    content: [...],  // Parsed paths or inline content
+  },
+  executionMethod: "agent|hybrid|cli",
+  preferredCliTool: "codex|gemini|qwen|auto",
+  enableResume: true  // Always enable resume for CLI executions
+}
+```
+
+**Pass to Agent**: Include `userConfig` in agent prompt for Phase 2A/2B.
+
 ### Phase 1: Context Preparation & Module Detection (Command Responsibility)
 
 **Command prepares session paths, metadata, and detects module structure.**
@@ -159,10 +241,21 @@ Output:
 Session ID: {session-id}
 MCP Capabilities: {exa_code, exa_web, code_index}
 
+## USER CONFIGURATION (from Phase 0)
+Execution Method: ${userConfig.executionMethod}  // agent|hybrid|cli
+Preferred CLI Tool: ${userConfig.preferredCliTool}  // codex|gemini|qwen|auto
+Supplementary Materials: ${userConfig.supplementaryMaterials}
+
 ## CLI TOOL SELECTION
-Determine CLI tool usage per-step based on user's task description:
-- If user specifies "use Codex/Gemini/Qwen for X" → Add command field to relevant steps
-- Default: Agent execution (no command field) unless user explicitly requests CLI
+Based on userConfig.executionMethod:
+- "agent": No command field in implementation_approach steps
+- "hybrid": Add command field to complex steps only (agent handles simple steps)
+- "cli": Add command field to ALL implementation_approach steps
+
+CLI Resume Support (MANDATORY for all CLI commands):
+- Use --resume parameter to continue from previous task execution
+- Read previous task's cliExecutionId from session state
+- Format: ccw cli exec "[prompt]" --resume ${previousCliId} --tool ${tool} --mode write
 
 ## EXPLORATION CONTEXT (from context-package.exploration_results)
 - Load exploration_results from context-package.json
@@ -186,6 +279,7 @@ Determine CLI tool usage per-step based on user's task description:
    - Artifacts integration from context package
    - **focus_paths enhanced with exploration critical_files**
    - Flow control with pre_analysis steps (include exploration integration_points analysis)
+   - **CLI Execution IDs and strategies (MANDATORY)**
 
 2. Implementation Plan (IMPL_PLAN.md)
    - Context analysis and artifact references
@@ -197,6 +291,27 @@ Determine CLI tool usage per-step based on user's task description:
    - Links to task JSONs and summaries
    - Matches task JSON hierarchy
 
+## CLI EXECUTION ID REQUIREMENTS (MANDATORY)
+Each task JSON MUST include:
+- **cli_execution_id**: Unique ID for CLI execution (format: `{session_id}-{task_id}`)
+- **cli_execution**: Strategy object based on depends_on:
+  - No deps → `{ "strategy": "new" }`
+  - 1 dep (single child) → `{ "strategy": "resume", "resume_from": "parent-cli-id" }`
+  - 1 dep (multiple children) → `{ "strategy": "fork", "resume_from": "parent-cli-id" }`
+  - N deps → `{ "strategy": "merge_fork", "merge_from": ["id1", "id2", ...] }`
+
+**CLI Execution Strategy Rules**:
+1. **new**: Task has no dependencies - starts fresh CLI conversation
+2. **resume**: Task has 1 parent AND that parent has only this child - continues same conversation
+3. **fork**: Task has 1 parent BUT parent has multiple children - creates new branch with parent context
+4. **merge_fork**: Task has multiple parents - merges all parent contexts into new conversation
+
+**Execution Command Patterns**:
+- new: `ccw cli exec "[prompt]" --tool [tool] --mode write --id [cli_execution_id]`
+- resume: `ccw cli exec "[prompt]" --resume [resume_from] --tool [tool] --mode write`
+- fork: `ccw cli exec "[prompt]" --resume [resume_from] --id [cli_execution_id] --tool [tool] --mode write`
+- merge_fork: `ccw cli exec "[prompt]" --resume [merge_from.join(',')] --id [cli_execution_id] --tool [tool] --mode write`
+
 ## QUALITY STANDARDS
 Hard Constraints:
   - Task count <= 18 (hard limit - request re-scope if exceeded)

.claude/skills/command-guide/reference/commands/workflow/ui-design/import-from-code.md

@@ -187,7 +187,7 @@ Task(subagent_type="ui-design-agent",
     CONTEXT: @**/*.css @**/*.scss @**/*.js @**/*.ts
     EXPECTED: JSON report listing conflicts with file:line, values, semantic context
     RULES: Focus on core tokens | Report ALL variants | analysis=READ-ONLY
-    \" --tool gemini --cd ${source}
+    \" --tool gemini --mode analysis --cd ${source}
     \`\`\`
 
   **Step 1: Load file list**
@@ -302,7 +302,7 @@ Task(subagent_type="ui-design-agent",
     CONTEXT: @**/*.css @**/*.scss @**/*.js @**/*.ts
     EXPECTED: JSON report listing frameworks, animation types, file locations
     RULES: Focus on framework consistency | Map all animations | analysis=READ-ONLY
-    \" --tool gemini --cd ${source}
+    \" --tool gemini --mode analysis --cd ${source}
     \`\`\`
 
   **Step 1: Load file list**
@@ -381,7 +381,7 @@ Task(subagent_type="ui-design-agent",
     CONTEXT: @**/*.css @**/*.scss @**/*.js @**/*.ts @**/*.html
     EXPECTED: JSON report categorizing components, layout patterns, naming conventions
     RULES: Focus on component reusability | Identify layout systems | analysis=READ-ONLY
-    \" --tool gemini --cd ${source}
+    \" --tool gemini --mode analysis --cd ${source}
     \`\`\`
 
   **Step 1: Load file list**

.claude/workflows/cli-tools-usage.md

@@ -74,7 +74,7 @@ ccw cli exec "<PROMPT>" --tool <gemini|qwen|codex> --mode <analysis|write>
 - **Mode is MANDATORY** - ALWAYS explicitly specify `--mode analysis|write` (no implicit defaults)
 - **One template required** - ALWAYS reference exactly ONE template in RULES (use universal fallback if no specific match)
 - **Write protection** - Require EXPLICIT `--mode write` for file operations
-- **No escape characters** - NEVER use `\$`, `\"`, `\'` in CLI commands
+- **Use double quotes for shell expansion** - Always wrap prompts in double quotes `"..."` to enable `$(cat ...)` command substitution; NEVER use single quotes or escape characters (`\$`, `\"`, `\'`)
 
 ---
 
@@ -276,9 +276,22 @@ ccw cli exec "..." --tool gemini --mode analysis --cd src
 - `universal/00-universal-creative-style.txt` - For exploratory tasks
 
 **Command Substitution Rules**:
-- Use `$(cat ...)` directly - do NOT read template content first
-- NEVER use escape characters: `\$`, `\"`, `\'`
-- Tilde expands correctly in prompt context
+- Use `$(cat ...)` directly in **double quotes** - command substitution executes in your local shell BEFORE passing to ccw
+- Shell expands `$(cat ...)` into file content automatically - do NOT read template content first
+- NEVER use escape characters (`\$`, `\"`, `\'`) or single quotes - these prevent shell expansion
+- Tilde (`~`) expands correctly in prompt context
+
+**Critical**: Use double quotes `"..."` around the entire prompt to enable `$(cat ...)` expansion:
+```bash
+# ✓ CORRECT - double quotes allow shell expansion
+ccw cli exec "RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ..." --tool gemini
+
+# ✗ WRONG - single quotes prevent expansion
+ccw cli exec 'RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ...' --tool gemini
+
+# ✗ WRONG - escaped $ prevents expansion
+ccw cli exec "RULES: \$(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) ..." --tool gemini
+```
 
 **Examples**:
 ```bash

.claude/workflows/context-requirements.md

@@ -5,40 +5,67 @@ Before implementation, always:
 - Map dependencies and integration points
 - Understand testing framework and coding conventions
 
-## Context Gathering
+## MCP Tools Usage
 
-**MANDATORY**: Use `codex_lens` (MCP tool) for all code search and analysis.
+### smart_search - Code Search (REQUIRED)
 
-### codex_lens (REQUIRED)
+**When**: Find code, understand codebase structure, locate implementations
 
-**MCP Actions**: `init`, `search`, `search_files` (Advanced ops via CLI: `codexlens --help`)
-
-**Initialize**:
-```
-codex_lens(action="init", path=".")
-```
-- Auto-generates embeddings if `fastembed` installed
-- Skip with `--no-embeddings` flag
-
-**Search** (Auto hybrid mode):
-```
-codex_lens(action="search", query="authentication")
-```
-**Search Files**:
-```
-codex_lens(action="search_files", query="payment")
+**How**:
+```javascript
+smart_search(query="authentication logic")           // Auto mode (recommended)
+smart_search(action="init", path=".")                // First-time setup
+smart_search(query="LoginUser", mode="exact")        // Precise matching
+smart_search(query="import", mode="ripgrep")         // Fast, no index
 ```
 
-### read_file (MCP)
-- Read files found by codex_lens
-- Directory traversal with patterns
-- Batch operations
+**Modes**: `auto` (intelligent routing), `hybrid` (best quality), `exact` (FTS), `ripgrep` (fast)
 
-### smart_search
-- Fallback when codex_lens unavailable
-- Small projects (<100 files)
+---
 
-### Exa
-- External APIs, libraries, frameworks
-- Recent documentation beyond knowledge cutoff
-- Public implementation examples
+### read_file - Read File Contents
+
+**When**: Read files found by smart_search
+
+**How**:
+```javascript
+read_file(path="/path/to/file.ts")                   // Single file
+read_file(path="/src/**/*.config.ts")                // Pattern matching
+```
+
+---
+
+### edit_file - Modify Files
+
+**When**: Built-in Edit tool fails or need advanced features
+
+**How**:
+```javascript
+edit_file(path="/file.ts", old_string="...", new_string="...", mode="update")
+edit_file(path="/file.ts", line=10, content="...", mode="insert_after")
+```
+
+**Modes**: `update` (replace text), `insert_after`, `insert_before`, `delete_line`
+
+---
+
+### write_file - Create/Overwrite Files
+
+**When**: Create new files or completely replace content
+
+**How**:
+```javascript
+write_file(path="/new-file.ts", content="...")
+```
+
+---
+
+### Exa - External Search
+
+**When**: Find documentation/examples outside codebase
+
+**How**:
+```javascript
+exa(query="React hooks 2025 documentation")
+exa(query="FastAPI auth example github")
+```

.claude/workflows/file-modification.md

@@ -25,7 +25,7 @@
 1. Known single file → Built-in Read
 2. Multiple files OR pattern matching → read_file (MCP)
 3. Unknown location → smart_search then Read
-4. Large codebase + repeated access → codex_lens
+4. Large codebase + repeated access → smart_search (indexed)
 
 **File Editing**:
 1. Always try built-in Edit first
@@ -36,7 +36,7 @@
 1. External knowledge → Exa
 2. Exact pattern in small codebase → Built-in Grep
 3. Semantic/unknown location → smart_search
-4. Large codebase + repeated searches → codex_lens
+4. Large codebase + repeated searches → smart_search (indexed)
 
 ## Decision Triggers
 
@@ -46,48 +46,3 @@
 **Use indexed search** for large, stable codebases
 **Use Exa** for external/public knowledge
 
-## ⚡ Core Search Tools
-
-**rg (ripgrep)**: Fast content search with regex support
-**find**: File/directory location by name patterns
-**grep**: Built-in pattern matching (fallback when rg unavailable)
-**get_modules_by_depth**: Program architecture analysis (MANDATORY before planning)
-
-
-## 🔧 Quick Command Reference
-
-```bash
-# Semantic File Discovery (codebase-retrieval via CCW)
-ccw cli exec "
-PURPOSE: Discover files relevant to task/feature
-TASK: • List all files related to [task/feature description]
-MODE: analysis
-CONTEXT: @**/*
-EXPECTED: Relevant file paths with relevance explanation
-RULES: Focus on direct relevance to task requirements | analysis=READ-ONLY
-" --tool gemini --cd [directory]
-
-# Program Architecture (MANDATORY before planning)
-ccw tool exec get_modules_by_depth '{}'
-
-# Content Search (rg preferred)
-rg "pattern" --type js -n        # Search JS files with line numbers
-rg -i "case-insensitive"         # Ignore case
-rg -C 3 "context"                # Show 3 lines before/after
-
-# File Search
-find . -name "*.ts" -type f      # Find TypeScript files
-find . -path "*/node_modules" -prune -o -name "*.js" -print
-
-# Workflow Examples
-rg "IMPL-\d+" .workflow/ --type json                    # Find task IDs
-find .workflow/ -name "*.json" -path "*/.task/*"        # Locate task files
-rg "status.*pending" .workflow/.task/                   # Find pending tasks
-```
-
-## ⚡ Performance Tips
-
-- **rg > grep** for content search
-- **Use --type filters** to limit file types
-- **Exclude dirs**: `--glob '!node_modules'`
-- **Use -F** for literal strings (no regex)