feat: add --yes flag for auto-confirmation across multiple workflows

- Enhanced lite-execute, lite-fix, lite-lite-lite, lite-plan, multi-cli-plan, plan, replan, session complete, session solidify, and various UI design commands to support a --yes or -y flag for skipping user confirmations and auto-selecting defaults.
- Updated argument hints and examples to reflect new auto mode functionality.
- Implemented auto mode defaults for confirmation, execution methods, and code review options.
- Improved error handling and validation in command parsing and execution processes.

.claude/commands/issue/discover-by-prompt.md

@@ -1,10 +1,14 @@
 ---
 name: issue:discover-by-prompt
 description: Discover issues from user prompt with Gemini-planned iterative multi-agent exploration. Uses ACE semantic search for context gathering and supports cross-module comparison (e.g., frontend vs backend API contracts).
-argument-hint: "<prompt> [--scope=src/**] [--depth=standard|deep] [--max-iterations=5]"
+argument-hint: "[-y|--yes] <prompt> [--scope=src/**] [--depth=standard|deep] [--max-iterations=5]"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Task(*), AskUserQuestion(*), Glob(*), Grep(*), mcp__ace-tool__search_context(*), mcp__exa__search(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-continue all iterations, skip confirmations.
+
 # Issue Discovery by Prompt
 
 ## Quick Start

.claude/commands/issue/discover.md

@@ -1,10 +1,14 @@
 ---
 name: issue:discover
 description: Discover potential issues from multiple perspectives (bug, UX, test, quality, security, performance, maintainability, best-practices) using CLI explore. Supports Exa external research for security and best-practices perspectives.
-argument-hint: "<path-pattern> [--perspectives=bug,ux,...] [--external]"
+argument-hint: "[-y|--yes] <path-pattern> [--perspectives=bug,ux,...] [--external]"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Task(*), AskUserQuestion(*), Glob(*), Grep(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-select all perspectives, skip confirmations.
+
 # Issue Discovery Command
 
 ## Quick Start

.claude/commands/issue/execute.md

@@ -1,10 +1,14 @@
 ---
 name: execute
 description: Execute queue with DAG-based parallel orchestration (one commit per solution)
-argument-hint: "--queue <queue-id> [--worktree [<existing-path>]]"
+argument-hint: "[-y|--yes] --queue <queue-id> [--worktree [<existing-path>]]"
 allowed-tools: TodoWrite(*), Bash(*), Read(*), AskUserQuestion(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm execution, use recommended settings.
+
 # Issue Execute Command (/issue:execute)
 
 ## Overview

.claude/commands/issue/new.md

@@ -1,10 +1,14 @@
 ---
 name: new
 description: Create structured issue from GitHub URL or text description
-argument-hint: "<github-url | text-description> [--priority 1-5]"
+argument-hint: "[-y|--yes] <github-url | text-description> [--priority 1-5]"
 allowed-tools: TodoWrite(*), Bash(*), Read(*), AskUserQuestion(*), mcp__ace-tool__search_context(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip clarification questions, create issue with inferred details.
+
 # Issue New Command (/issue:new)
 
 ## Core Principle

.claude/commands/issue/plan.md

@@ -1,10 +1,14 @@
 ---
 name: plan
 description: Batch plan issue resolution using issue-plan-agent (explore + plan closed-loop)
-argument-hint: "--all-pending <issue-id>[,<issue-id>,...] [--batch-size 3] "
+argument-hint: "[-y|--yes] --all-pending <issue-id>[,<issue-id>,...] [--batch-size 3]"
 allowed-tools: TodoWrite(*), Task(*), SlashCommand(*), AskUserQuestion(*), Bash(*), Read(*), Write(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-bind solutions without confirmation, use recommended settings.
+
 # Issue Plan Command (/issue:plan)
 
 ## Overview

.claude/commands/issue/queue.md

@@ -1,10 +1,14 @@
 ---
 name: queue
 description: Form execution queue from bound solutions using issue-queue-agent (solution-level)
-argument-hint: "[--queues <n>] [--issue <id>]"
+argument-hint: "[-y|--yes] [--queues <n>] [--issue <id>]"
 allowed-tools: TodoWrite(*), Task(*), Bash(*), Read(*), Write(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm queue formation, use recommended conflict resolutions.
+
 # Issue Queue Command (/issue:queue)
 
 ## Overview

.claude/commands/task/breakdown.md

@@ -1,9 +1,13 @@
 ---
 name: breakdown
 description: Decompose complex task into subtasks with dependency mapping, creates child task JSONs with parent references and execution order
-argument-hint: "task-id"
+argument-hint: "[-y|--yes] task-id"
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm breakdown, use recommended subtask structure.
+
 # Task Breakdown Command (/task:breakdown)
 
 ## Overview

.claude/commands/task/replan.md

@@ -1,10 +1,14 @@
 ---
 name: replan
 description: Update task JSON with new requirements or batch-update multiple tasks from verification report, tracks changes in task-changes.json
-argument-hint: "task-id [\"text\"|file.md] | --batch [verification-report.md]"
+argument-hint: "[-y|--yes] task-id [\"text\"|file.md] | --batch [verification-report.md]"
 allowed-tools: Read(*), Write(*), Edit(*), TodoWrite(*), Glob(*), Bash(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm updates, use recommended changes.
+
 # Task Replan Command (/task:replan)
 
 > **⚠️ DEPRECATION NOTICE**: This command is maintained for backward compatibility. For new workflows, use `/workflow:replan` which provides:

.claude/commands/workflow/brainstorm/artifacts.md

@@ -1,10 +1,14 @@
 ---
 name: artifacts
 description: Interactive clarification generating confirmed guidance specification through role-based analysis and synthesis
-argument-hint: "topic or challenge description [--count N]"
+argument-hint: "[-y|--yes] topic or challenge description [--count N]"
 allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*), AskUserQuestion(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-select recommended roles, skip all clarification questions, use default answers.
+
 ## Overview
 
 Seven-phase workflow: **Context collection** → **Topic analysis** → **Role selection** → **Role questions** → **Conflict resolution** → **Final check** → **Generate specification**

.claude/commands/workflow/brainstorm/auto-parallel.md

@@ -1,10 +1,14 @@
 ---
 name: auto-parallel
 description: Parallel brainstorming automation with dynamic role selection and concurrent execution across multiple perspectives
-argument-hint: "topic or challenge description" [--count N]
+argument-hint: "[-y|--yes] topic or challenge description [--count N]"
 allowed-tools: SlashCommand(*), Task(*), TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-select recommended roles, skip all clarification questions, use default answers.
+
 # Workflow Brainstorm Parallel Auto Command
 
 ## Coordinator Role

.claude/commands/workflow/brainstorm/synthesis.md

@@ -1,10 +1,14 @@
 ---
 name: synthesis
 description: Clarify and refine role analyses through intelligent Q&A and targeted updates with synthesis agent
-argument-hint: "[optional: --session session-id]"
+argument-hint: "[-y|--yes] [optional: --session session-id]"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*), Edit(*), Glob(*), AskUserQuestion(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-select all enhancements, skip clarification questions, use default answers.
+
 ## Overview
 
 Six-phase workflow to eliminate ambiguities and enhance conceptual depth in role analyses:

.claude/commands/workflow/clean.md

@@ -1,7 +1,7 @@
 ---
 name: clean
 description: Intelligent code cleanup with mainline detection, stale artifact discovery, and safe execution
-argument-hint: "[--dry-run] [\"focus area\"]"
+argument-hint: "[-y|--yes] [--dry-run] [\"focus area\"]"
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Glob(*), Bash(*), Write(*)
 ---
 
@@ -21,8 +21,22 @@ Intelligent cleanup command that explores the codebase to identify the developme
 
 ```bash
 /workflow:clean                          # Full intelligent cleanup (explore → analyze → confirm → execute)
+/workflow:clean --yes                    # Auto mode (use safe defaults, no confirmation)
 /workflow:clean --dry-run                # Explore and analyze only, no execution
-/workflow:clean "auth module"            # Focus cleanup on specific area
+/workflow:clean -y "auth module"         # Auto mode with focus area
+```
+
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Categories to Clean**: Auto-selects `["Sessions"]` only (safest - only workflow sessions)
+- **Risk Level**: Auto-selects `"Low only"` (only low-risk items)
+- All confirmations skipped, proceeds directly to execution
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+const dryRun = $ARGUMENTS.includes('--dry-run')
 ```
 
 ## Execution Process
@@ -329,39 +343,57 @@ To execute cleanup: /workflow:clean
 
 **Step 3.3: User Confirmation**
 ```javascript
-AskUserQuestion({
+// Parse --yes flag
-  questions: [
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-    {
+
-      question: "Which categories to clean?",
+let userSelection
-      header: "Categories",
+
-      multiSelect: true,
+if (autoYes) {
-      options: [
+  // Auto mode: Use safe defaults
-        {
+  console.log(`[--yes] Auto-selecting safe cleanup defaults:`)
-          label: "Sessions",
+  console.log(`  - Categories: Sessions only`)
-          description: `${manifest.summary.by_category.stale_sessions} stale workflow sessions`
+  console.log(`  - Risk level: Low only`)
-        },
+
-        {
+  userSelection = {
-          label: "Documents",
+    categories: ["Sessions"],
-          description: `${manifest.summary.by_category.drifted_documents} drifted documents`
+    risk: "Low only"
-        },
+  }
-        {
+} else {
-          label: "Dead Code",
+  // Interactive mode: Ask user
-          description: `${manifest.summary.by_category.dead_code} unused code files`
+  userSelection = AskUserQuestion({
-        }
+    questions: [
-      ]
+      {
-    },
+        question: "Which categories to clean?",
-    {
+        header: "Categories",
-      question: "Risk level to include?",
+        multiSelect: true,
-      header: "Risk",
+        options: [
-      multiSelect: false,
+          {
-      options: [
+            label: "Sessions",
-        { label: "Low only", description: "Safest - only obviously stale items" },
+            description: `${manifest.summary.by_category.stale_sessions} stale workflow sessions`
-        { label: "Low + Medium", description: "Recommended - includes likely unused items" },
+          },
-        { label: "All", description: "Aggressive - includes high-risk items" }
+          {
-      ]
+            label: "Documents",
-    }
+            description: `${manifest.summary.by_category.drifted_documents} drifted documents`
-  ]
+          },
-})
+          {
+            label: "Dead Code",
+            description: `${manifest.summary.by_category.dead_code} unused code files`
+          }
+        ]
+      },
+      {
+        question: "Risk level to include?",
+        header: "Risk",
+        multiSelect: false,
+        options: [
+          { label: "Low only", description: "Safest - only obviously stale items" },
+          { label: "Low + Medium", description: "Recommended - includes likely unused items" },
+          { label: "All", description: "Aggressive - includes high-risk items" }
+        ]
+      }
+    ]
+  })
+}
 ```
 
 ---

.claude/commands/workflow/debug-with-file.md

@@ -1,10 +1,14 @@
 ---
 name: debug-with-file
 description: Interactive hypothesis-driven debugging with documented exploration, understanding evolution, and Gemini-assisted correction
-argument-hint: "\"bug description or error message\""
+argument-hint: "[-y|--yes] \"bug description or error message\""
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Grep(*), Glob(*), Bash(*), Edit(*), Write(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm all decisions (hypotheses, fixes, iteration), use recommended settings.
+
 # Workflow Debug-With-File Command (/workflow:debug-with-file)
 
 ## Overview

.claude/commands/workflow/debug.md

@@ -1,10 +1,14 @@
 ---
 name: debug
 description: Interactive hypothesis-driven debugging with NDJSON logging, iterative until resolved
-argument-hint: "\"bug description or error message\""
+argument-hint: "[-y|--yes] \"bug description or error message\""
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Grep(*), Glob(*), Bash(*), Edit(*), Write(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm all decisions (hypotheses, fixes, iteration), use recommended settings.
+
 # Workflow Debug Command (/workflow:debug)
 
 ## Overview

.claude/commands/workflow/develop-with-file.md

@@ -1,10 +1,14 @@
 ---
 name: develop-with-file
 description: Multi-agent development workflow with documented progress, Gemini-guided planning, and incremental iteration support
-argument-hint: "\"feature description or task file.md\""
+argument-hint: "[-y|--yes] \"feature description or task file.md\""
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Grep(*), Glob(*), Bash(*), Edit(*), Write(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-confirm all decisions (exploration, planning, execution, verification), use recommended settings.
+
 # Workflow Develop-With-File Command (/workflow:develop-with-file)
 
 ## Overview

.claude/commands/workflow/execute.md

@@ -1,7 +1,7 @@
 ---
 name: execute
 description: Coordinate agent execution for workflow tasks with automatic session discovery, parallel task processing, and status tracking
-argument-hint: "[--resume-session=\"session-id\"]"
+argument-hint: "[-y|--yes] [--resume-session=\"session-id\"]"
 ---
 
 # Workflow Execute Command
@@ -11,6 +11,30 @@ Orchestrates autonomous workflow execution through systematic task discovery, ag
 
 **Resume Mode**: When called with `--resume-session` flag, skips discovery phase and directly enters TodoWrite generation and agent execution for the specified session.
 
+## Usage
+
+```bash
+# Interactive mode (with confirmations)
+/workflow:execute
+/workflow:execute --resume-session="WFS-auth"
+
+# Auto mode (skip confirmations, use defaults)
+/workflow:execute --yes
+/workflow:execute -y
+/workflow:execute -y --resume-session="WFS-auth"
+```
+
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Session Selection**: Automatically selects the first (most recent) active session
+- **Completion Choice**: Automatically completes session (runs `/workflow:session:complete --yes`)
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+```
+
 ## Performance Optimization Strategy
 
 **Lazy Loading**: Task JSONs read **on-demand** during execution, not upfront. TODO_LIST.md + IMPL_PLAN.md provide metadata for planning.
@@ -122,24 +146,38 @@ List sessions with metadata and prompt user selection:
 bash(for dir in .workflow/active/WFS-*/; do [ -d "$dir" ] || continue; session=$(basename "$dir"); project=$(jq -r '.project // "Unknown"' "${dir}workflow-session.json" 2>/dev/null || echo "Unknown"); total=$(grep -c '^\- \[' "${dir}TODO_LIST.md" 2>/dev/null || echo 0); completed=$(grep -c '^\- \[x\]' "${dir}TODO_LIST.md" 2>/dev/null || echo 0); if [ "$total" -gt 0 ]; then progress=$((completed * 100 / total)); else progress=0; fi; echo "$session | $project | $completed/$total tasks ($progress%)"; done)
 ```
 
-Use AskUserQuestion to present formatted options (max 4 options shown):
+**Parse --yes flag**:
 ```javascript
-// If more than 4 sessions, show most recent 4 with "Other" option for manual input
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-const sessions = getActiveSessions()  // sorted by last modified
+```
-const displaySessions = sessions.slice(0, 4)
 
-AskUserQuestion({
+**Conditional Selection**:
-  questions: [{
+```javascript
-    question: "Multiple active sessions detected. Select one:",
+if (autoYes) {
-    header: "Session",
+  // Auto mode: Select first session (most recent)
-    multiSelect: false,
+  const firstSession = sessions[0]
-    options: displaySessions.map(s => ({
+  console.log(`[--yes] Auto-selecting session: ${firstSession.id}`)
-      label: s.id,
+  selectedSessionId = firstSession.id
-      description: `${s.project} | ${s.progress}`
+  // Continue to Phase 2
-    }))
+} else {
-    // Note: User can select "Other" to manually enter session ID
+  // Interactive mode: Use AskUserQuestion to present formatted options (max 4 options shown)
-  }]
+  // If more than 4 sessions, show most recent 4 with "Other" option for manual input
-})
+  const sessions = getActiveSessions()  // sorted by last modified
+  const displaySessions = sessions.slice(0, 4)
+
+  AskUserQuestion({
+    questions: [{
+      question: "Multiple active sessions detected. Select one:",
+      header: "Session",
+      multiSelect: false,
+      options: displaySessions.map(s => ({
+        label: s.id,
+        description: `${s.project} | ${s.progress}`
+      }))
+      // Note: User can select "Other" to manually enter session ID
+    }]
+  })
+}
 ```
 
 **Input Validation**:
@@ -252,23 +290,33 @@ while (TODO_LIST.md has pending tasks) {
 6. **User Choice**: When all tasks finished, ask user to choose next step:
 
 ```javascript
-AskUserQuestion({
+// Parse --yes flag
-  questions: [{
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-    question: "All tasks completed. What would you like to do next?",
+
-    header: "Next Step",
+if (autoYes) {
-    multiSelect: false,
+  // Auto mode: Complete session automatically
-    options: [
+  console.log(`[--yes] Auto-selecting: Complete Session`)
-      {
+  SlashCommand("/workflow:session:complete --yes")
-        label: "Enter Review",
+} else {
-        description: "Run specialized review (security/architecture/quality/action-items)"
+  // Interactive mode: Ask user
-      },
+  AskUserQuestion({
-      {
+    questions: [{
-        label: "Complete Session",
+      question: "All tasks completed. What would you like to do next?",
-        description: "Archive session and update manifest"
+      header: "Next Step",
-      }
+      multiSelect: false,
-    ]
+      options: [
-  }]
+        {
-})
+          label: "Enter Review",
+          description: "Run specialized review (security/architecture/quality/action-items)"
+        },
+        {
+          label: "Complete Session",
+          description: "Archive session and update manifest"
+        }
+      ]
+    }]
+  })
+}
 ```
 
 **Based on user selection**:

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

@@ -1,7 +1,7 @@
 ---
 name: lite-execute
 description: Execute tasks based on in-memory plan, prompt description, or file content
-argument-hint: "[--in-memory] [\"task description\"|file-path]"
+argument-hint: "[-y|--yes] [--in-memory] [\"task description\"|file-path]"
 allowed-tools: TodoWrite(*), Task(*), Bash(*)
 ---
 
@@ -62,31 +62,49 @@ Flexible task execution command supporting three input modes: in-memory plan (fr
 
 **User Interaction**:
 ```javascript
-AskUserQuestion({
+// Parse --yes flag
-  questions: [
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-    {
+
-      question: "Select execution method:",
+let userSelection
-      header: "Execution",
+
-      multiSelect: false,
+if (autoYes) {
-      options: [
+  // Auto mode: Use defaults
-        { label: "Agent", description: "@code-developer agent" },
+  console.log(`[--yes] Auto-confirming execution:`)
-        { label: "Codex", description: "codex CLI tool" },
+  console.log(`  - Execution method: Auto`)
-        { label: "Auto", description: "Auto-select based on complexity" }
+  console.log(`  - Code review: Skip`)
-      ]
+
-    },
+  userSelection = {
-    {
+    execution_method: "Auto",
-      question: "Enable code review after execution?",
+    code_review_tool: "Skip"
-      header: "Code Review",
+  }
-      multiSelect: false,
+} else {
-      options: [
+  // Interactive mode: Ask user
-        { label: "Skip", description: "No review" },
+  userSelection = AskUserQuestion({
-        { label: "Gemini Review", description: "Gemini CLI tool" },
+    questions: [
-        { label: "Codex Review", description: "Git-aware review (prompt OR --uncommitted)" },
+      {
-        { label: "Agent Review", description: "Current agent review" }
+        question: "Select execution method:",
-      ]
+        header: "Execution",
-    }
+        multiSelect: false,
-  ]
+        options: [
-})
+          { label: "Agent", description: "@code-developer agent" },
+          { label: "Codex", description: "codex CLI tool" },
+          { label: "Auto", description: "Auto-select based on complexity" }
+        ]
+      },
+      {
+        question: "Enable code review after execution?",
+        header: "Code Review",
+        multiSelect: false,
+        options: [
+          { label: "Skip", description: "No review" },
+          { label: "Gemini Review", description: "Gemini CLI tool" },
+          { label: "Codex Review", description: "Git-aware review (prompt OR --uncommitted)" },
+          { label: "Agent Review", description: "Current agent review" }
+        ]
+      }
+    ]
+  })
+}
 ```
 
 ### Mode 3: File Content

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

@@ -1,7 +1,7 @@
 ---
 name: lite-fix
 description: Lightweight bug diagnosis and fix workflow with intelligent severity assessment and optional hotfix mode for production incidents
-argument-hint: "[--hotfix] \"bug description or issue reference\""
+argument-hint: "[-y|--yes] [--hotfix] \"bug description or issue reference\""
 allowed-tools: TodoWrite(*), Task(*), SlashCommand(*), AskUserQuestion(*)
 ---
 
@@ -25,10 +25,32 @@ Intelligent lightweight bug fixing command with dynamic workflow adaptation base
 /workflow:lite-fix [FLAGS] <BUG_DESCRIPTION>
 
 # Flags
+-y, --yes                  Skip all confirmations (auto mode)
 --hotfix, -h               Production hotfix mode (minimal diagnosis, fast fix)
 
 # Arguments
 <bug-description>          Bug description, error message, or path to .md file (required)
+
+# Examples
+/workflow:lite-fix "用户登录失败"                    # Interactive mode
+/workflow:lite-fix --yes "用户登录失败"              # Auto mode (no confirmations)
+/workflow:lite-fix -y --hotfix "生产环境数据库连接失败"   # Auto + hotfix mode
+```
+
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Clarification Questions**: Skipped (no clarification phase)
+- **Fix Plan Confirmation**: Auto-selected "Allow"
+- **Execution Method**: Auto-selected "Auto"
+- **Code Review**: Auto-selected "Skip"
+- **Severity**: Uses auto-detected severity (no manual override)
+- **Hotfix Mode**: Respects --hotfix flag if present, otherwise normal mode
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+const hotfixMode = $ARGUMENTS.includes('--hotfix') || $ARGUMENTS.includes('-h')
 ```
 
 ## Execution Process
@@ -332,9 +354,17 @@ function deduplicateClarifications(clarifications) {
 
 const uniqueClarifications = deduplicateClarifications(allClarifications)
 
-// Multi-round clarification: batch questions (max 4 per round)
+// Parse --yes flag
-// ⚠️ MUST execute ALL rounds until uniqueClarifications exhausted
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-if (uniqueClarifications.length > 0) {
+
+if (autoYes) {
+  // Auto mode: Skip clarification phase
+  console.log(`[--yes] Skipping ${uniqueClarifications.length} clarification questions`)
+  console.log(`Proceeding to fix planning with diagnosis results...`)
+  // Continue to Phase 3
+} else if (uniqueClarifications.length > 0) {
+  // Interactive mode: Multi-round clarification
+  // ⚠️ MUST execute ALL rounds until uniqueClarifications exhausted
   const BATCH_SIZE = 4
   const totalRounds = Math.ceil(uniqueClarifications.length / BATCH_SIZE)
 
@@ -600,40 +630,60 @@ ${fixPlan.tasks.map((t, i) => `${i+1}. ${t.title} (${t.scope})`).join('\n')}
 
 **Step 4.2: Collect Confirmation**
 ```javascript
-AskUserQuestion({
+// Parse --yes flag
-  questions: [
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-    {
+
-      question: `Confirm fix plan? (${fixPlan.tasks.length} tasks, ${fixPlan.severity} severity)`,
+let userSelection
-      header: "Confirm",
+
-      multiSelect: true,
+if (autoYes) {
-      options: [
+  // Auto mode: Use defaults
-        { label: "Allow", description: "Proceed as-is" },
+  console.log(`[--yes] Auto-confirming fix plan:`)
-        { label: "Modify", description: "Adjust before execution" },
+  console.log(`  - Confirmation: Allow`)
-        { label: "Cancel", description: "Abort workflow" }
+  console.log(`  - Execution: Auto`)
-      ]
+  console.log(`  - Review: Skip`)
-    },
+
-    {
+  userSelection = {
-      question: "Execution method:",
+    confirmation: "Allow",
-      header: "Execution",
+    execution_method: "Auto",
-      multiSelect: false,
+    code_review_tool: "Skip"
-      options: [
+  }
-        { label: "Agent", description: "@code-developer agent" },
+} else {
-        { label: "Codex", description: "codex CLI tool" },
+  // Interactive mode: Ask user
-        { label: "Auto", description: `Auto: ${fixPlan.severity === 'Low' ? 'Agent' : 'Codex'}` }
+  userSelection = AskUserQuestion({
-      ]
+    questions: [
-    },
+      {
-    {
+        question: `Confirm fix plan? (${fixPlan.tasks.length} tasks, ${fixPlan.severity} severity)`,
-      question: "Code review after fix?",
+        header: "Confirm",
-      header: "Review",
+        multiSelect: false,
-      multiSelect: false,
+        options: [
-      options: [
+          { label: "Allow", description: "Proceed as-is" },
-        { label: "Gemini Review", description: "Gemini CLI" },
+          { label: "Modify", description: "Adjust before execution" },
-        { label: "Agent Review", description: "@code-reviewer" },
+          { label: "Cancel", description: "Abort workflow" }
-        { label: "Skip", description: "No review" }
+        ]
-      ]
+      },
-    }
+      {
-  ]
+        question: "Execution method:",
-})
+        header: "Execution",
+        multiSelect: false,
+        options: [
+          { label: "Agent", description: "@code-developer agent" },
+          { label: "Codex", description: "codex CLI tool" },
+          { label: "Auto", description: `Auto: ${fixPlan.severity === 'Low' ? 'Agent' : 'Codex'}` }
+        ]
+      },
+      {
+        question: "Code review after fix?",
+        header: "Review",
+        multiSelect: false,
+        options: [
+          { label: "Gemini Review", description: "Gemini CLI" },
+          { label: "Agent Review", description: "@code-reviewer" },
+          { label: "Skip", description: "No review" }
+        ]
+      }
+    ]
+  })
+}
 ```
 
 ---

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

@@ -1,10 +1,14 @@
 ---
 name: workflow:lite-lite-lite
 description: Ultra-lightweight multi-tool analysis and direct execution. No artifacts for simple tasks; auto-creates planning docs in .workflow/.scratchpad/ for complex tasks. Auto tool selection based on task analysis, user-driven iteration via AskUser.
-argument-hint: "<task description>"
+argument-hint: "[-y|--yes] <task description>"
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Bash(*), Write(*), mcp__ace-tool__search_context(*), mcp__ccw-tools__write_file(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip clarification questions, auto-select tools, execute directly with recommended settings.
+
 # Ultra-Lite Multi-Tool Workflow
 
 ## Quick Start

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

@@ -1,7 +1,7 @@
 ---
 name: lite-plan
 description: Lightweight interactive planning workflow with in-memory planning, code exploration, and execution execute to lite-execute after user confirmation
-argument-hint: "[-e|--explore] \"task description\"|file.md"
+argument-hint: "[-y|--yes] [-e|--explore] \"task description\"|file.md"
 allowed-tools: TodoWrite(*), Task(*), SlashCommand(*), AskUserQuestion(*)
 ---
 
@@ -25,10 +25,30 @@ Intelligent lightweight planning command with dynamic workflow adaptation based
 /workflow:lite-plan [FLAGS] <TASK_DESCRIPTION>
 
 # Flags
+-y, --yes                  Skip all confirmations (auto mode)
 -e, --explore              Force code exploration phase (overrides auto-detection)
 
 # Arguments
 <task-description>         Task description or path to .md file (required)
+
+# Examples
+/workflow:lite-plan "实现JWT认证"                    # Interactive mode
+/workflow:lite-plan --yes "实现JWT认证"              # Auto mode (no confirmations)
+/workflow:lite-plan -y -e "优化数据库查询性能"       # Auto mode + force exploration
+```
+
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Clarification Questions**: Skipped (no clarification phase)
+- **Plan Confirmation**: Auto-selected "Allow"
+- **Execution Method**: Auto-selected "Auto"
+- **Code Review**: Auto-selected "Skip"
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+const forceExplore = $ARGUMENTS.includes('--explore') || $ARGUMENTS.includes('-e')
 ```
 
 ## Execution Process
@@ -323,8 +343,16 @@ explorations.forEach(exp => {
 // - Produce dedupedClarifications with unique intents only
 const dedupedClarifications = intelligentMerge(allClarifications)
 
-// Multi-round clarification: batch questions (max 4 per round)
+// Parse --yes flag
-if (dedupedClarifications.length > 0) {
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+if (autoYes) {
+  // Auto mode: Skip clarification phase
+  console.log(`[--yes] Skipping ${dedupedClarifications.length} clarification questions`)
+  console.log(`Proceeding to planning with exploration results...`)
+  // Continue to Phase 3
+} else if (dedupedClarifications.length > 0) {
+  // Interactive mode: Multi-round clarification
   const BATCH_SIZE = 4
   const totalRounds = Math.ceil(dedupedClarifications.length / BATCH_SIZE)
 
@@ -497,42 +525,62 @@ ${plan.tasks.map((t, i) => `${i+1}. ${t.title} (${t.file})`).join('\n')}
 
 **Step 4.2: Collect Confirmation**
 ```javascript
-// Note: Execution "Other" option allows specifying CLI tools from ~/.claude/cli-tools.json
+// Parse --yes flag
-AskUserQuestion({
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-  questions: [
+
-    {
+let userSelection
-      question: `Confirm plan? (${plan.tasks.length} tasks, ${plan.complexity})`,
+
-      header: "Confirm",
+if (autoYes) {
-      multiSelect: true,
+  // Auto mode: Use defaults
-      options: [
+  console.log(`[--yes] Auto-confirming plan:`)
-        { label: "Allow", description: "Proceed as-is" },
+  console.log(`  - Confirmation: Allow`)
-        { label: "Modify", description: "Adjust before execution" },
+  console.log(`  - Execution: Auto`)
-        { label: "Cancel", description: "Abort workflow" }
+  console.log(`  - Review: Skip`)
-      ]
+
-    },
+  userSelection = {
-    {
+    confirmation: "Allow",
-      question: "Execution method:",
+    execution_method: "Auto",
-      header: "Execution",
+    code_review_tool: "Skip"
-      multiSelect: false,
+  }
-      options: [
+} else {
-        { label: "Agent", description: "@code-developer agent" },
+  // Interactive mode: Ask user
-        { label: "Codex", description: "codex CLI tool" },
+  // Note: Execution "Other" option allows specifying CLI tools from ~/.claude/cli-tools.json
-        { label: "Auto", description: `Auto: ${plan.complexity === 'Low' ? 'Agent' : 'Codex'}` }
+  userSelection = AskUserQuestion({
-      ]
+    questions: [
-    },
+      {
-    {
+        question: `Confirm plan? (${plan.tasks.length} tasks, ${plan.complexity})`,
-      question: "Code review after execution?",
+        header: "Confirm",
-      header: "Review",
+        multiSelect: false,
-      multiSelect: false,
+        options: [
-      options: [
+          { label: "Allow", description: "Proceed as-is" },
-        { label: "Gemini Review", description: "Gemini CLI review" },
+          { label: "Modify", description: "Adjust before execution" },
-        { label: "Codex Review", description: "Git-aware review (prompt OR --uncommitted)" },
+          { label: "Cancel", description: "Abort workflow" }
-        { label: "Agent Review", description: "@code-reviewer agent" },
+        ]
-        { label: "Skip", description: "No review" }
+      },
-      ]
+      {
-    }
+        question: "Execution method:",
-  ]
+        header: "Execution",
-})
+        multiSelect: false,
+        options: [
+          { label: "Agent", description: "@code-developer agent" },
+          { label: "Codex", description: "codex CLI tool" },
+          { label: "Auto", description: `Auto: ${plan.complexity === 'Low' ? 'Agent' : 'Codex'}` }
+        ]
+      },
+      {
+        question: "Code review after execution?",
+        header: "Review",
+        multiSelect: false,
+        options: [
+          { label: "Gemini Review", description: "Gemini CLI review" },
+          { label: "Codex Review", description: "Git-aware review (prompt OR --uncommitted)" },
+          { label: "Agent Review", description: "@code-reviewer agent" },
+          { label: "Skip", description: "No review" }
+        ]
+      }
+    ]
+  })
+}
 ```
 
 ---

.claude/commands/workflow/multi-cli-plan.md

@@ -1,10 +1,14 @@
 ---
 name: workflow:multi-cli-plan
 description: Multi-CLI collaborative planning workflow with ACE context gathering and iterative cross-verification. Uses cli-discuss-agent for Gemini+Codex+Claude analysis to converge on optimal execution plan.
-argument-hint: "<task description> [--max-rounds=3] [--tools=gemini,codex] [--mode=parallel|serial]"
+argument-hint: "[-y|--yes] <task description> [--max-rounds=3] [--tools=gemini,codex] [--mode=parallel|serial]"
 allowed-tools: TodoWrite(*), Task(*), AskUserQuestion(*), Read(*), Bash(*), Write(*), mcp__ace-tool__search_context(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-approve plan, use recommended solution and execution method (Agent, Skip review).
+
 # Multi-CLI Collaborative Planning Command
 
 ## Quick Start

.claude/commands/workflow/plan.md

@@ -1,10 +1,14 @@
 ---
 name: plan
 description: 5-phase planning workflow with action-planning-agent task generation, outputs IMPL_PLAN.md and task JSONs
-argument-hint: "\"text description\"|file.md"
+argument-hint: "[-y|--yes] \"text description\"|file.md"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-continue all phases (skip confirmations), use recommended conflict resolutions.
+
 # Workflow Plan Command (/workflow:plan)
 
 ## Coordinator Role

.claude/commands/workflow/replan.md

@@ -1,7 +1,7 @@
 ---
 name: replan
 description: Interactive workflow replanning with session-level artifact updates and boundary clarification through guided questioning
-argument-hint: "[--session session-id] [task-id] \"requirements\"|file.md [--interactive]"
+argument-hint: "[-y|--yes] [--session session-id] [task-id] \"requirements\"|file.md [--interactive]"
 allowed-tools: Read(*), Write(*), Edit(*), TodoWrite(*), Glob(*), Bash(*)
 ---
 
@@ -117,10 +117,48 @@ const taskId = taskIdMatch?.[1]
 
 ---
 
+### Auto Mode Support
+
+When `--yes` or `-y` flag is used, the command skips interactive clarification and uses safe defaults:
+
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+```
+
+**Auto Mode Defaults**:
+- **Modification Scope**: `tasks_only` (safest - only update task details)
+- **Affected Modules**: All modules related to the task
+- **Task Changes**: `update_only` (no structural changes)
+- **Dependency Changes**: `no` (preserve existing dependencies)
+- **User Confirmation**: Auto-confirm execution
+
+**Note**: `--interactive` flag overrides `--yes` flag (forces interactive mode).
+
+---
+
 ### Phase 2: Interactive Requirement Clarification
 
 **Purpose**: Define modification scope through guided questioning
 
+**Auto Mode Check**:
+```javascript
+if (autoYes && !interactive) {
+  // Use defaults and skip to Phase 3
+  console.log(`[--yes] Using safe defaults for replan:`)
+  console.log(`  - Scope: tasks_only`)
+  console.log(`  - Changes: update_only`)
+  console.log(`  - Dependencies: preserve existing`)
+
+  userSelections = {
+    scope: 'tasks_only',
+    modules: 'all_affected',
+    task_changes: 'update_only',
+    dependency_changes: false
+  }
+  // Proceed to Phase 3
+}
+```
+
 #### Session Mode Questions
 
 **Q1: Modification Scope**
@@ -228,10 +266,29 @@ interface ImpactAnalysis {
 **Step 3.3: User Confirmation**
 
 ```javascript
-Options:
+// Parse --yes flag
-- 确认执行: 开始应用所有修改
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-- 调整计划: 重新回答问题调整范围
+
-- 取消操作: 放弃本次重规划
+if (autoYes) {
+  // Auto mode: Auto-confirm execution
+  console.log(`[--yes] Auto-confirming replan execution`)
+  userConfirmation = '确认执行'
+  // Proceed to Phase 4
+} else {
+  // Interactive mode: Ask user
+  AskUserQuestion({
+    questions: [{
+      question: "修改计划已生成，请确认操作:",
+      header: "Confirm",
+      options: [
+        { label: "确认执行", description: "开始应用所有修改" },
+        { label: "调整计划", description: "重新回答问题调整范围" },
+        { label: "取消操作", description: "放弃本次重规划" }
+      ],
+      multiSelect: false
+    }]
+  })
+}
 ```
 
 **Output**: Modification plan confirmed or adjusted

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

@@ -606,5 +606,3 @@ Use `ccw view` to open the workflow dashboard in browser:
 ```bash
 ccw view
 ```
-
-

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

@@ -1,8 +1,10 @@
 ---
 name: complete
 description: Mark active workflow session as complete, archive with lessons learned, update manifest, remove active flag
+argument-hint: "[-y|--yes] [--detailed]"
 examples:
   - /workflow:session:complete
+  - /workflow:session:complete --yes
   - /workflow:session:complete --detailed
 ---
 
@@ -139,20 +141,41 @@ test -f .workflow/project-tech.json || echo "SKIP"
 After successful archival, prompt user to capture learnings:
 
 ```javascript
-AskUserQuestion({
+// Parse --yes flag
-  questions: [{
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-    question: "Would you like to solidify learnings from this session into project guidelines?",
+
-    header: "Solidify",
+if (autoYes) {
-    options: [
+  // Auto mode: Skip solidify
-      { label: "Yes, solidify now", description: "Extract learnings and update project-guidelines.json" },
+  console.log(`[--yes] Auto-selecting: Skip solidify`)
-      { label: "Skip", description: "Archive complete, no learnings to capture" }
+  console.log(`Session archived successfully.`)
-    ],
+  // Done - no solidify
-    multiSelect: false
+} else {
-  }]
+  // Interactive mode: Ask user
-})
+  AskUserQuestion({
+    questions: [{
+      question: "Would you like to solidify learnings from this session into project guidelines?",
+      header: "Solidify",
+      options: [
+        { label: "Yes, solidify now", description: "Extract learnings and update project-guidelines.json" },
+        { label: "Skip", description: "Archive complete, no learnings to capture" }
+      ],
+      multiSelect: false
+    }]
+  })
+
+  // **If "Yes, solidify now"**: Execute `/workflow:session:solidify` with the archived session ID.
+}
 ```
 
-**If "Yes, solidify now"**: Execute `/workflow:session:solidify` with the archived session ID.
+## Auto Mode Defaults
+
+When `--yes` or `-y` flag is used:
+- **Solidify Learnings**: Auto-selected "Skip" (archive only, no solidify)
+
+**Flag Parsing**:
+```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+```
 
 **Output**:
 ```

.claude/commands/workflow/session/solidify.md

@@ -1,14 +1,18 @@
 ---
 name: solidify
 description: Crystallize session learnings and user-defined constraints into permanent project guidelines
-argument-hint: "[--type <convention|constraint|learning>] [--category <category>] \"rule or insight\""
+argument-hint: "[-y|--yes] [--type <convention|constraint|learning>] [--category <category>] \"rule or insight\""
 examples:
   - /workflow:session:solidify "Use functional components for all React code" --type convention
-  - /workflow:session:solidify "No direct DB access from controllers" --type constraint --category architecture
+  - /workflow:session:solidify -y "No direct DB access from controllers" --type constraint --category architecture
   - /workflow:session:solidify "Cache invalidation requires event sourcing" --type learning --category architecture
   - /workflow:session:solidify --interactive
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-categorize and add guideline without confirmation.
+
 # Session Solidify Command (/workflow:session:solidify)
 
 ## Overview

.claude/commands/workflow/tools/conflict-resolution.md

@@ -1,12 +1,16 @@
 ---
 name: conflict-resolution
 description: Detect and resolve conflicts between plan and existing codebase using CLI-powered analysis with Gemini/Qwen
-argument-hint: "--session WFS-session-id --context path/to/context-package.json"
+argument-hint: "[-y|--yes] --session WFS-session-id --context path/to/context-package.json"
 examples:
   - /workflow:tools:conflict-resolution --session WFS-auth --context .workflow/active/WFS-auth/.process/context-package.json
-  - /workflow:tools:conflict-resolution --session WFS-payment --context .workflow/active/WFS-payment/.process/context-package.json
+  - /workflow:tools:conflict-resolution -y --session WFS-payment --context .workflow/active/WFS-payment/.process/context-package.json
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Auto-select recommended strategy for each conflict, skip clarification questions.
+
 # Conflict Resolution Command
 
 ## Purpose
@@ -209,6 +213,8 @@ Task(subagent_type="cli-execution-agent", run_in_background=false, prompt=`
 ### Phase 3: User Interaction Loop
 
 ```javascript
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
 FOR each conflict:
   round = 0, clarified = false, userClarifications = []
 
@@ -216,8 +222,13 @@ FOR each conflict:
     // 1. Display conflict info (text output for context)
     displayConflictSummary(conflict)  // id, brief, severity, overlap_analysis if ModuleOverlap
 
-    // 2. Strategy selection via AskUserQuestion
+    // 2. Strategy selection
-    AskUserQuestion({
+    if (autoYes) {
+      console.log(`[--yes] Auto-selecting recommended strategy`)
+      selectedStrategy = conflict.strategies[conflict.recommended || 0]
+      clarified = true  // Skip clarification loop
+    } else {
+      AskUserQuestion({
       questions: [{
         question: formatStrategiesForDisplay(conflict.strategies),
         header: "策略选择",
@@ -230,18 +241,19 @@ FOR each conflict:
           { label: "自定义修改", description: `建议: ${conflict.modification_suggestions?.slice(0,2).join('; ')}` }
         ]
       }]
-    })
+      })
 
-    // 3. Handle selection
+      // 3. Handle selection
-    if (userChoice === "自定义修改") {
+      if (userChoice === "自定义修改") {
-      customConflicts.push({ id, brief, category, suggestions, overlap_analysis })
+        customConflicts.push({ id, brief, category, suggestions, overlap_analysis })
-      break
+        break
+      }
+
+      selectedStrategy = findStrategyByName(userChoice)
     }
 
-    selectedStrategy = findStrategyByName(userChoice)
-
     // 4. Clarification (if needed) - batched max 4 per call
-    if (selectedStrategy.clarification_needed?.length > 0) {
+    if (!autoYes && selectedStrategy.clarification_needed?.length > 0) {
       for (batch of chunk(selectedStrategy.clarification_needed, 4)) {
         AskUserQuestion({
           questions: batch.map((q, i) => ({

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

@@ -1,11 +1,16 @@
 ---
 name: task-generate-agent
 description: Generate implementation plan documents (IMPL_PLAN.md, task JSONs, TODO_LIST.md) using action-planning-agent - produces planning artifacts, does NOT execute code implementation
-argument-hint: "--session WFS-session-id"
+argument-hint: "[-y|--yes] --session WFS-session-id"
 examples:
   - /workflow:tools:task-generate-agent --session WFS-auth
+  - /workflow:tools:task-generate-agent -y --session WFS-auth
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip user questions, use defaults (no materials, Agent executor, Codex CLI tool).
+
 # Generate Implementation Plan Command
 
 ## Overview
@@ -67,9 +72,25 @@ Phase 3: Integration (+1 Coordinator, Multi-Module Only)
 
 **Purpose**: Collect user preferences before task generation to ensure generated tasks match execution expectations.
 
-**User Questions**:
+**Auto Mode Check**:
 ```javascript
-AskUserQuestion({
+const autoYes = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
+
+if (autoYes) {
+  console.log(`[--yes] Using defaults: No materials, Agent executor, Codex CLI`)
+  userConfig = {
+    supplementaryMaterials: { type: "none", content: [] },
+    executionMethod: "agent",
+    preferredCliTool: "codex",
+    enableResume: true
+  }
+  // Skip to Phase 1
+}
+```
+
+**User Questions** (skipped if autoYes):
+```javascript
+if (!autoYes) AskUserQuestion({
   questions: [
     {
       question: "Do you have supplementary materials or guidelines to include?",
@@ -104,11 +125,10 @@ AskUserQuestion({
     }
   ]
 })
-```
 
-**Handle Materials Response**:
+**Handle Materials Response** (skipped if autoYes):
 ```javascript
-if (userConfig.materials === "Provide file paths") {
+if (!autoYes && userConfig.materials === "Provide file paths") {
   // Follow-up question for file paths
   const pathsResponse = AskUserQuestion({
     questions: [{

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

@@ -1,11 +1,16 @@
 ---
 name: task-generate-tdd
 description: Autonomous TDD task generation using action-planning-agent with Red-Green-Refactor cycles, test-first structure, and cycle validation
-argument-hint: "--session WFS-session-id"
+argument-hint: "[-y|--yes] --session WFS-session-id"
 examples:
   - /workflow:tools:task-generate-tdd --session WFS-auth
+  - /workflow:tools:task-generate-tdd -y --session WFS-auth
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip user questions, use defaults (no materials, Agent executor).
+
 # Autonomous TDD Task Generation Command
 
 ## Overview

.claude/commands/workflow/ui-design/animation-extract.md

@@ -1,10 +1,14 @@
 ---
 name: animation-extract
 description: Extract animation and transition patterns from prompt inference and image references for design system documentation
-argument-hint: "[--design-id <id>] [--session <id>] [--images "<glob>"] [--focus "<types>"] [--interactive] [--refine]"
+argument-hint: "[-y|--yes] [--design-id <id>] [--session <id>] [--images "<glob>"] [--focus "<types>"] [--interactive] [--refine]"
 allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*), Bash(*), AskUserQuestion(*), Task(ui-design-agent)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip all clarification questions, use AI-inferred animation decisions.
+
 # Animation Extraction Command
 
 ## Overview

.claude/commands/workflow/ui-design/layout-extract.md

@@ -1,10 +1,14 @@
 ---
 name: layout-extract
 description: Extract structural layout information from reference images or text prompts using Claude analysis with variant generation or refinement mode
-argument-hint: [--design-id <id>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--targets "<list>"] [--variants <count>] [--device-type <desktop|mobile|tablet|responsive>] [--interactive] [--refine]
+argument-hint: "[-y|--yes] [--design-id <id>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--targets "<list>"] [--variants <count>] [--device-type <desktop|mobile|tablet|responsive>] [--interactive] [--refine]"
 allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*), Bash(*), AskUserQuestion(*), Task(ui-design-agent), mcp__exa__web_search_exa(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip all clarification questions, use AI-inferred layout decisions.
+
 # Layout Extraction Command
 
 ## Overview

.claude/commands/workflow/ui-design/style-extract.md

@@ -1,10 +1,14 @@
 ---
 name: style-extract
 description: Extract design style from reference images or text prompts using Claude analysis with variant generation or refinement mode
-argument-hint: "[--design-id <id>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--variants <count>] [--interactive] [--refine]"
+argument-hint: "[-y|--yes] [--design-id <id>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--variants <count>] [--interactive] [--refine]"
 allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*), AskUserQuestion(*)
 ---
 
+## Auto Mode
+
+When `--yes` or `-y`: Skip all clarification questions, use AI-inferred design decisions.
+
 # Style Extraction Command
 
 ## Overview

.claude/skills/ccw-coordinator/SKILL.md

@@ -45,6 +45,7 @@ allowed-tools: Task, AskUserQuestion, Read, Write, Bash, Glob, Grep
 5. **执行透明性**: 展示执行进度、结果和可能的错误
 6. **会话持久化**: 保存编排会话，支持中途暂停和恢复
 7. **智能提示词生成**: 根据任务上下文和前序产物自动生成 ccw cli 提示词
+8. **自动确认**: 所有命令自动添加 `-y` 参数，跳过交互式确认，实现无人值守执行
 
 ## Intelligent Prompt Generation
 

.claude/skills/ccw-coordinator/phases/actions/action-command-execute.md

@@ -66,8 +66,8 @@ for (let i = current_command_index; i < command_chain.length; i++) {
   const prompt = generatePrompt(cmd, state, commandMeta);
 
   try {
-    // 使用 ccw cli 执行
+    // 使用 ccw cli 执行（添加 -y 参数跳过确认）
-    const result = Bash(`ccw cli -p "${prompt.replace(/"/g, '\\"')}" ${cmd.command}`, {
+    const result = Bash(`ccw cli -p "${prompt.replace(/"/g, '\\"')}" ${cmd.command} -y`, {
       run_in_background: true
     });
 

.claude/skills/ccw-coordinator/tools/chain-validate.cjs

@@ -254,8 +254,30 @@ function main() {
     chain = args[1].split(',').map(s => s.trim());
   } else if (args[0] === '--file') {
     const filePath = args[1];
-    const fileContent = JSON.parse(fs.readFileSync(filePath, 'utf8'));
+
-    chain = fileContent.chain || fileContent.steps.map(s => s.command);
+    // SEC-001: 路径遍历验证 - 只允许访问工作目录下的文件
+    const resolvedPath = path.resolve(filePath);
+    const workDir = path.resolve('.');
+    if (!resolvedPath.startsWith(workDir)) {
+      console.error('Error: File path must be within current working directory');
+      process.exit(1);
+    }
+
+    // CORR-001: JSON 解析错误处理
+    let fileContent;
+    try {
+      fileContent = JSON.parse(fs.readFileSync(resolvedPath, 'utf8'));
+    } catch (error) {
+      console.error(`Error: Failed to parse JSON file ${filePath}: ${error.message}`);
+      process.exit(1);
+    }
+
+    // CORR-002: 嵌套属性 null 检查
+    chain = fileContent.chain || fileContent.steps?.map(s => s.command) || [];
+    if (chain.length === 0) {
+      console.error('Error: No valid chain found in file (expected "chain" array or "steps" with "command" fields)');
+      process.exit(1);
+    }
   } else {
     chain = args;
   }

.claude/skills/ccw-coordinator/tools/command-registry.cjs

@@ -48,7 +48,19 @@ class CommandRegistry {
   }
 
   /**
-   * 解析 YAML 头
+   * 解析 YAML 头 (简化版本)
+   *
+   * 限制:
+   * - 只支持简单的 key: value 对 (单行值)
+   * - 不支持多行值、嵌套对象、复杂列表
+   * - allowed-tools 字段支持逗号分隔的字符串，自动转为数组
+   *
+   * 示例:
+   * ---
+   * name: lite-plan
+   * description: "Lightweight planning workflow"
+   * allowed-tools: Read, Write, Bash
+   * ---
    */
   parseYamlHeader(content) {
     // 处理 Windows 行结尾 (\r\n)
@@ -58,23 +70,36 @@ class CommandRegistry {
     const yamlContent = match[1];
     const result = {};
 
-    const lines = yamlContent.split(/[\r\n]+/);
+    try {
-    for (const line of lines) {
+      const lines = yamlContent.split(/[\r\n]+/);
-      if (!line.trim()) continue;
+      for (const line of lines) {
+        const trimmed = line.trim();
+        if (!trimmed || trimmed.startsWith('#')) continue; // 跳过空行和注释
 
-      const colonIndex = line.indexOf(':');
+        const colonIndex = trimmed.indexOf(':');
-      if (colonIndex === -1) continue;
+        if (colonIndex === -1) continue;
 
-      const key = line.substring(0, colonIndex).trim();
+        const key = trimmed.substring(0, colonIndex).trim();
-      const value = line.substring(colonIndex + 1).trim();
+        const value = trimmed.substring(colonIndex + 1).trim();
 
-      let cleanValue = value.replace(/^["']|["']$/g, '');
+        if (!key) continue; // 跳过无效行
 
-      if (key === 'allowed-tools') {
+        // 去除引号 (单引号或双引号)
-        cleanValue = cleanValue.split(',').map(t => t.trim());
+        let cleanValue = value.replace(/^["']|["']$/g, '');
+
+        // allowed-tools 字段特殊处理：转为数组
+        // 支持格式: "Read, Write, Bash" 或 "Read,Write,Bash"
+        if (key === 'allowed-tools') {
+          cleanValue = Array.isArray(cleanValue)
+            ? cleanValue
+            : cleanValue.split(',').map(t => t.trim()).filter(t => t);
+        }
+
+        result[key] = cleanValue;
       }
-
+    } catch (error) {
-      result[key] = cleanValue;
+      console.error('YAML parsing error:', error.message);
+      return null;
     }
 
     return result;