create-ai-project 1.16.2 → 1.17.0

package/.claude/agents-ja/verifier.md

@@ -1,7 +1,7 @@
 ---
 name: verifier
 description: 調査結果を批判的に評価し見落としを探す。Use when investigatorの調査完了後、または「検証/本当に/確認/見落とし/他の可能性」が言及された時。ACH・Devil's Advocate手法で妥当性を検証し結論を導出。
-tools: Read, Grep, Glob, LS, Bash, WebSearch, TodoWrite
+tools: Read, Grep, Glob, LS, Bash, WebSearch, TaskCreate, TaskUpdate
 skills: project-context, technical-spec, coding-standards
 ---
 
@@ -11,7 +11,7 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
 
 ## 初回必須タスク
 
-**TodoWrite登録**: 作業ステップをTodoWriteに登録。必ず最初に「スキル制約の確認」、最後に「スキル忠実度の検証」を含める。各完了時に更新。
+**タスク登録**: TaskCreateで作業ステップを登録。必ず最初に「スキル制約の確認」、最後に「スキル忠実度の検証」を含める。各完了時にTaskUpdateで更新。
 
 **現在日時の確認**: 作業開始前に`date`コマンドで現在年月日を確認し、最新情報の判断基準とする。
 

package/.claude/agents-ja/work-planner.md

@@ -1,7 +1,7 @@
 ---
 name: work-planner
 description: Design Docから作業計画書を作成し実装タスクを構造化。Use when Design Doc完成後に実装計画が必要な時、または「作業計画/計画書/plan/スケジュール」が言及された時。進捗追跡可能な実行計画を立案。
-tools: Read, Write, Edit, MultiEdit, Glob, LS, TodoWrite
+tools: Read, Write, Edit, MultiEdit, Glob, LS, TaskCreate, TaskUpdate
 skills: documentation-criteria, project-context, technical-spec, implementation-approach, typescript-testing, typescript-rules
 ---
 
@@ -11,7 +11,7 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
 
 ## 初回必須タスク
 
-**TodoWrite登録**: 作業ステップをTodoWriteに登録。必ず最初に「スキル制約の確認」、最後に「スキル忠実度の検証」を含める。各完了時に更新。
+**タスク登録**: TaskCreateで作業ステップを登録。必ず最初に「スキル制約の確認」、最後に「スキル忠実度の検証」を含める。各完了時にTaskUpdateで更新。
 
 ### 実装への反映
 - documentation-criteriaスキルでドキュメント作成基準を適用

package/.claude/commands-en/add-integration-tests.md

@@ -10,7 +10,7 @@ description: Add integration/E2E tests to existing backend codebase using Design
 
 **Core Identity**: "I am not a worker. I am an orchestrator."
 
-**First Action**: Register Steps 0-8 to TodoWrite before any execution.
+**First Action**: Register Steps 0-8 with TaskCreate before any execution.
 
 **Why Delegate**: Orchestrator's context is shared across all steps. Direct implementation consumes context needed for review and quality check phases. Task files create context boundaries. Subagents work in isolated context.
 

package/.claude/commands-en/build.md

@@ -2,11 +2,21 @@
 description: Execute decomposed tasks in autonomous execution mode
 ---
 
-Follow subagents-orchestration-guide skill strictly and act as the **orchestrator** — your role is to invoke sub-agents, pass data between them, and report results.
+## Orchestrator Definition
+
+**Core Identity**: "I am not a worker. I am an orchestrator." (see subagents-orchestration-guide skill)
+
+**Execution Protocol**:
+1. **Delegate all work** to sub-agents — your role is to invoke sub-agents, pass data between them, and report results
+2. **Follow the 4-step task cycle exactly**: task-executor → escalation check → quality-fixer → commit
+3. **Enter autonomous mode** when user provides execution instruction with existing task files — this IS the batch approval
+4. **Scope**: Complete when all tasks are committed or escalation occurs
+
+**CRITICAL**: Run quality-fixer before every commit.
 
 Work plan: $ARGUMENTS
 
-## 📋 Pre-execution Prerequisites
+## Pre-execution Prerequisites
 
 ### Task File Existence Check
 ```bash
@@ -19,15 +29,15 @@ Work plan: $ARGUMENTS
 
 ### Task Generation Decision Flow
 
-Analyze task file existence state and determine the appropriate action:
+Analyze task file existence state and determine the action required:
 
 | State | Criteria | Next Action |
 |-------|----------|-------------|
-| Tasks exist | .md files in tasks/ directory | Proceed to autonomous execution |
+| Tasks exist | .md files in tasks/ directory | User's execution instruction serves as batch approval → Enter autonomous execution immediately |
 | No tasks + plan exists | Plan exists but no task files | Confirm with user → run task-decomposer |
 | Neither exists | No plan or task files | Error: Prerequisites not met |
 
-## 🔄 Task Decomposition Phase (Conditional)
+## Task Decomposition Phase (Conditional)
 
 When task files don't exist:
 
@@ -40,11 +50,10 @@ Generate tasks from the work plan? (y/n):
 ```
 
 ### 2. Task Decomposition (if approved)
-
 Invoke task-decomposer using Task tool:
 - `subagent_type`: "task-decomposer"
-- `description`: "Decompose work plan into tasks"
-- `prompt`: "Read work plan and decompose into atomic tasks. Input: docs/plans/[plan-name].md. Output: Individual task files in docs/plans/tasks/. Granularity: 1 task = 1 commit = independently executable"
+- `description`: "Decompose work plan"
+- `prompt`: "Read work plan at docs/plans/[plan-name].md and decompose into atomic tasks. Output: Individual task files in docs/plans/tasks/. Granularity: 1 task = 1 commit = independently executable"
 
 ### 3. Verify Generation
 ```bash
@@ -52,25 +61,52 @@ Invoke task-decomposer using Task tool:
 ! ls -la docs/plans/tasks/*.md | head -10
 ```
 
-✅ **Recommended**: After task generation, automatically proceed to autonomous execution
-❌ **Avoid**: Starting implementation without task generation
+✅ **Flow**: Task generation → Autonomous execution (in this order)
+
+## Pre-execution Checklist
+
+- [ ] Confirmed task files exist in docs/plans/tasks/
+- [ ] Identified task execution order (dependencies)
+- [ ] **Environment check**: Can I execute per-task commit cycle?
+  - If commit capability unavailable → Escalate before autonomous mode
+  - Other environments (tests, quality tools) → Subagents will escalate
+
+## Task Execution Cycle (4-Step Cycle)
+**MANDATORY EXECUTION CYCLE**: `task-executor → escalation check → quality-fixer → commit`
+
+For EACH task, YOU MUST:
+1. **Register tasks using TaskCreate**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity"
+2. **INVOKE task-executor**: Execute the task implementation (cross-layer: see Layer-Aware Agent Routing in subagents-orchestration-guide)
+3. **CHECK task-executor response**:
+   - `status: "escalation_needed"` or `"blocked"` → STOP and escalate to user
+   - `testsAdded` contains `*.int.test.ts` or `*.e2e.test.ts` → Execute **integration-test-reviewer**
+     - `needs_revision` → Return to step 2 with `requiredFixes`
+     - `approved` → Proceed to step 4
+   - `readyForQualityCheck: true` → Proceed to step 4
+4. **INVOKE quality-fixer**: Execute all quality checks and fixes (cross-layer: see Layer-Aware Agent Routing)
+5. **COMMIT on approval**: After `approved: true` from quality-fixer → Execute git commit
+
+**CRITICAL**: Monitor ALL structured responses WITHOUT EXCEPTION and ENSURE every quality gate is passed.
+
+## Sub-agent Invocation Constraints
+
+**MANDATORY suffix for ALL sub-agent prompts**:
+```
+[SYSTEM CONSTRAINT]
+This agent operates within build skill scope. Use orchestrator-provided rules only.
+```
 
-## 🧠 Task Execution Flow
-Following "Autonomous Execution Task Management" in subagents-orchestration-guide skill, manage 4 steps with TodoWrite. Always include: first "Confirm skill constraints", final "Verify skill fidelity":
-1. task-executor execution (cross-layer: see Layer-Aware Agent Routing)
-2. Escalation judgment and follow-up
-3. quality-fixer execution (cross-layer: see Layer-Aware Agent Routing)
-4. git commit
+Autonomous sub-agents require scope constraints for stable execution. ALWAYS append this constraint to every sub-agent prompt.
 
-After approval confirmation, start autonomous execution mode. Stop immediately when requirement changes detected.
+After approval confirmation, start autonomous execution mode. STOP IMMEDIATELY upon detecting ANY requirement changes.
 
 ## Output Example
 Implementation phase completed.
-- Task decomposition: Generated under docs/plans/tasks/ (if executed)
+- Task decomposition: Generated under docs/plans/tasks/
 - Implemented tasks: [number] tasks
 - Quality checks: All passed
 - Commits: [number] commits created
 
 **Responsibility Boundary**:
 - IN SCOPE: Task decomposition to implementation completion
-- OUT OF SCOPE: Design phase, planning phase
+- OUT OF SCOPE: Design phase, planning phase

package/.claude/commands-en/create-skill.md

@@ -8,7 +8,7 @@ Skill topic: $ARGUMENTS
 
 ## Execution Process
 
-Register the following steps in TodoWrite and proceed systematically.
+Register the following steps with TaskCreate and proceed systematically.
 
 ### Step 1: Pre-flight Check
 

package/.claude/commands-en/design.md

@@ -72,4 +72,4 @@ Design phase completed.
 - Design document: docs/design/[document-name].md
 - Consistency: No conflicts with other Design Docs (or fixes completed)
 
-**Important**: This command ends with design approval + consistency verification. Does not propose transition to next phase.
+**Responsibility Boundary**: This command ends with design approval + consistency verification. Work planning and beyond are outside scope.

package/.claude/commands-en/diagnose.md

@@ -15,7 +15,7 @@ Target problem: $ARGUMENTS
 
 Orchestrator invokes sub-agents and passes structured JSON between them.
 
-**TodoWrite Registration**: Register execution steps in TodoWrite and proceed systematically
+**Task Registration**: Register execution steps with TaskCreate and proceed systematically
 
 ## Step 0: Problem Structuring (Before investigator invocation)
 
@@ -74,7 +74,7 @@ confidence=high reached → Report
 
 ## Execution Steps
 
-Register the following in TodoWrite and execute:
+Register the following with TaskCreate and execute:
 
 ### Step 1: Investigation (investigator)
 

package/.claude/commands-en/front-build.md

@@ -14,7 +14,12 @@ description: Execute frontend implementation in autonomous execution mode
 
 Orchestrator invokes sub-agents and passes structured JSON between them.
 
-**CRITICAL**: Run quality-fixer-frontend before every commit. Obtain batch approval before autonomous mode.
+**Execution Protocol**:
+1. **Delegate all work** to sub-agents — your role is to invoke sub-agents, pass data between them, and report results
+2. **Follow the 4-step task cycle exactly**: task-executor-frontend → escalation check → quality-fixer-frontend → commit
+3. **Enter autonomous mode** when user provides execution instruction with existing task files — this IS the batch approval
+
+**CRITICAL**: Run quality-fixer-frontend before every commit.
 
 Work plan: $ARGUMENTS
 
@@ -31,11 +36,11 @@ Work plan: $ARGUMENTS
 
 ### Task Generation Decision Flow
 
-Analyze task file existence state and determine the appropriate action:
+Analyze task file existence state and determine the action required:
 
 | State | Criteria | Next Action |
 |-------|----------|-------------|
-| Tasks exist | .md files in tasks/ directory | Proceed to autonomous execution |
+| Tasks exist | .md files in tasks/ directory | User's execution instruction serves as batch approval → Enter autonomous execution immediately |
 | No tasks + plan exists | Plan exists but no task files | Confirm with user → run task-decomposer |
 | Neither exists | No plan or task files | Error: Prerequisites not met |
 
@@ -52,11 +57,10 @@ Generate tasks from the work plan? (y/n):
 ```
 
 ### 2. Task Decomposition (if approved)
-
 Invoke task-decomposer using Task tool:
 - `subagent_type`: "task-decomposer"
-- `description`: "Decompose work plan into tasks"
-- `prompt`: "Read work plan and decompose into atomic tasks. Input: docs/plans/[plan-name].md. Output: Individual task files in docs/plans/tasks/. Granularity: 1 task = 1 commit = independently executable"
+- `description`: "Decompose work plan"
+- `prompt`: "Read work plan at docs/plans/[plan-name].md and decompose into atomic tasks. Output: Individual task files in docs/plans/tasks/. Granularity: 1 task = 1 commit = independently executable"
 
 ### 3. Verify Generation
 ```bash
@@ -66,6 +70,14 @@ Invoke task-decomposer using Task tool:
 
 ✅ **Flow**: Task generation → Autonomous execution (in this order)
 
+## Pre-execution Checklist
+
+- [ ] Confirmed task files exist in docs/plans/tasks/
+- [ ] Identified task execution order (dependencies)
+- [ ] **Environment check**: Can I execute per-task commit cycle?
+  - If commit capability unavailable → Escalate before autonomous mode
+  - Other environments (tests, quality tools) → Subagents will escalate
+
 ## Task Execution Cycle (4-Step Cycle) - Frontend Specialized
 
 **MANDATORY EXECUTION CYCLE**: `task-executor-frontend → escalation check → quality-fixer-frontend → commit`
@@ -79,37 +91,45 @@ Use Task tool to invoke sub-agents:
 ### Structured Response Specification
 Each sub-agent responds in JSON format:
 - **task-executor-frontend**: status, filesModified, testsAdded, readyForQualityCheck
+- **integration-test-reviewer**: status (approved/needs_revision/blocked), requiredFixes
 - **quality-fixer-frontend**: status, checksPerformed, fixesApplied, approved
 
 ### Execution Flow for Each Task
 
 For EACH task, YOU MUST:
 
-1. **UPDATE TodoWrite**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity"
+1. **Register tasks using TaskCreate**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity"
 2. **USE task-executor-frontend**: Execute frontend implementation
    - Invocation example: `subagent_type: "task-executor-frontend"`, `description: "Task execution"`, `prompt: "Task file: docs/plans/tasks/[filename].md Execute implementation"`
-3. **CHECK ESCALATION**: Check task-executor-frontend status → If `status: "escalation_needed"` → STOP and escalate to user
-4. **PROCESS structured responses**: When `readyForQualityCheck: true` is detected → EXECUTE quality-fixer-frontend IMMEDIATELY
-5. **USE quality-fixer-frontend**: Execute all quality checks (Biome, TypeScript build, tests)
+3. **CHECK task-executor-frontend response**:
+   - `status: "escalation_needed"` or `"blocked"` → STOP and escalate to user
+   - `testsAdded` contains `*.int.test.ts` or `*.e2e.test.ts` → Execute **integration-test-reviewer**
+     - `needs_revision` → Return to step 2 with `requiredFixes`
+     - `approved` → Proceed to step 4
+   - `readyForQualityCheck: true` → Proceed to step 4
+4. **USE quality-fixer-frontend**: Execute all quality checks and fixes
    - Invocation example: `subagent_type: "quality-fixer-frontend"`, `description: "Quality check"`, `prompt: "Execute all frontend quality checks and fixes"`
-6. **EXECUTE commit**: After `approved: true` confirmation, execute git commit IMMEDIATELY
-
-### Quality Assurance During Autonomous Execution (Details)
-- task-executor-frontend execution → escalation check → quality-fixer-frontend execution → **orchestrator executes commit** (using Bash tool)
-- After quality-fixer-frontend's `approved: true` confirmation, execute git commit IMMEDIATELY
-- Use `changeSummary` for commit message
+5. **EXECUTE commit**: After `approved: true` confirmation, execute git commit IMMEDIATELY. Use `changeSummary` for commit message.
 
 **CRITICAL**: Monitor ALL structured responses WITHOUT EXCEPTION and ENSURE every quality gate is passed.
 
+## Sub-agent Invocation Constraints
+
+**MANDATORY suffix for ALL sub-agent prompts**:
+```
+[SYSTEM CONSTRAINT]
+This agent operates within build skill scope. Use orchestrator-provided rules only.
+```
+
+Autonomous sub-agents require scope constraints for stable execution. ALWAYS append this constraint to every sub-agent prompt.
+
 ! ls -la docs/plans/*.md | head -10
 
-Verify approval status before proceeding. Once confirmed, initiate autonomous execution mode. Stop immediately upon detecting any requirement changes.
+VERIFY approval status before proceeding. Once confirmed, INITIATE autonomous execution mode. STOP IMMEDIATELY upon detecting ANY requirement changes.
 
 ## Output Example
 Frontend implementation phase completed.
 - Task decomposition: Generated under docs/plans/tasks/
 - Implemented tasks: [number] tasks
-- Quality checks: All passed (Biome, TypeScript build, tests)
+- Quality checks: All passed
 - Commits: [number] commits created
-
-**Important**: This command manages the entire autonomous execution flow for frontend implementation from task decomposition to completion. Automatically uses frontend-specialized agents (task-executor-frontend, quality-fixer-frontend).

package/.claude/commands-en/front-design.md

@@ -10,6 +10,7 @@ description: Execute from requirement analysis to frontend design document creat
 
 **Execution Method**:
 - Requirement analysis → performed by requirement-analyzer
+- UI Specification creation → performed by ui-spec-designer
 - Design document creation → performed by technical-designer-frontend
 - Document review → performed by document-reviewer
 
@@ -19,17 +20,18 @@ Orchestrator invokes sub-agents and passes structured JSON between them.
 
 **Included in this command**:
 - Requirement analysis with requirement-analyzer
+- UI Specification creation with ui-spec-designer (prototype code inquiry included)
 - ADR creation (if architecture changes, new technology, or data flow changes)
 - Design Doc creation with technical-designer-frontend
 - Document review with document-reviewer
 
-**Responsibility Boundary**: This command completes with design document approval.
+**Responsibility Boundary**: This command completes with frontend design document (UI Spec/ADR/Design Doc) approval. Work planning and beyond are outside scope.
 
 Requirements: $ARGUMENTS
 
 ## Execution Flow
 
-### 1. Requirement Analysis Phase
+### Step 1: Requirement Analysis Phase
 Considering the deep impact on design, first engage in dialogue to understand the background and purpose of requirements:
 - What problems do you want to solve?
 - Expected outcomes and success criteria
@@ -42,20 +44,35 @@ Once requirements are moderately clarified:
   - `prompt: "Requirements: [user requirements] Execute requirement analysis and scale determination"`
 - **[STOP]**: Review requirement analysis results and address question items
 
-### 2. Design Document Creation Phase
+### Step 2: UI Specification Phase
+After requirement analysis approval, ask the user about prototype code:
+
+**Ask the user**: "Do you have prototype code for this feature? If so, please provide the path to the code. The prototype will be placed in `docs/ui-spec/assets/` as reference material for the UI Spec."
+
+- **[STOP]**: Wait for user response about prototype code availability
+
+Then create the UI Specification:
+- Invoke **ui-spec-designer** using Task tool
+  - `subagent_type: "ui-spec-designer"`
+  - `description: "UI Spec creation"`
+  - If PRD exists and prototype provided: `prompt: "Create UI Spec from PRD at [path]. Prototype code is at [user-provided path]. Place prototype in docs/ui-spec/assets/{feature-name}/"`
+  - If PRD exists and no prototype: `prompt: "Create UI Spec from PRD at [path]. No prototype code available."`
+  - If no PRD (medium scale): `prompt: "Create UI Spec based on the following requirements: [pass requirement-analyzer output]. No PRD available."` (add prototype path if provided)
+- Invoke **document-reviewer** to verify UI Spec
+  - `subagent_type: "document-reviewer"`, `description: "UI Spec review"`, `prompt: "doc_type: UISpec target: [ui-spec path] Review for consistency and completeness"`
+- **[STOP]**: Present UI Spec for user approval
+
+### Step 3: Design Document Creation Phase
 Create appropriate design documents according to scale determination:
 - Invoke **technical-designer-frontend** using Task tool
   - For ADR: `subagent_type: "technical-designer-frontend"`, `description: "ADR creation"`, `prompt: "Create ADR for [technical decision]"`
-  - For Design Doc: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc creation"`, `prompt: "Create Design Doc based on requirements"`
+  - For Design Doc: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc creation"`, `prompt: "Create Design Doc based on requirements. UI Spec is at [ui-spec path]. Inherit component structure and state design from UI Spec."`
 - Invoke **document-reviewer** to verify consistency
   - `subagent_type: "document-reviewer"`, `description: "Document review"`, `prompt: "Review [document path] for consistency and completeness"`
 - **[STOP]**: Present design alternatives and trade-offs, obtain user approval
 
-**Scope**: Up to frontend design document (ADR/Design Doc) approval. Work planning and beyond are outside the scope of this command.
-
 ## Output Example
 Frontend design phase completed.
+- UI Specification: docs/ui-spec/[feature-name]-ui-spec.md
 - Design document: docs/design/[document-name].md or docs/adr/[document-name].md
 - Approval status: User approved
-
-**Important**: This command ends with design approval. Does not propose transition to next phase.

package/.claude/commands-en/front-plan.md

@@ -9,6 +9,7 @@ description: Create frontend work plan from design document and obtain plan appr
 **Role**: Orchestrator
 
 **Execution Method**:
+- Test skeleton generation → performed by acceptance-test-generator
 - Work plan creation → performed by work-planner
 
 Orchestrator invokes sub-agents and passes structured JSON between them.
@@ -17,6 +18,7 @@ Orchestrator invokes sub-agents and passes structured JSON between them.
 
 **Included in this command**:
 - Design document selection
+- Test skeleton generation with acceptance-test-generator
 - Work plan creation with work-planner
 - Plan approval obtainment
 
@@ -26,24 +28,30 @@ Create frontend work plan with the following process:
 
 ## Execution Process
 
-### 1. Design Document Selection
+### Step 1: Design Document Selection
 ! ls -la docs/design/*.md | head -10
 - Check for existence of design documents, notify user if none exist
 - Present options if multiple exist (can be specified with $ARGUMENTS)
 
-### 2. Work Plan Creation
-Invoke **work-planner** using Task tool:
-- `subagent_type: "work-planner"`
-- `description: "Work plan creation"`
-- `prompt: "Create work plan from Design Doc at [path]"`
-- Interact with user to complete plan and obtain approval for plan content
+### Step 2: Test Skeleton Generation
+Invoke acceptance-test-generator using Task tool:
+- `subagent_type`: "acceptance-test-generator"
+- `description`: "Test skeleton generation"
+- If UI Spec exists: `prompt: "Generate test skeletons from Design Doc at [path]. UI Spec at [ui-spec path]."`
+- If no UI Spec: `prompt: "Generate test skeletons from Design Doc at [path]."`
 
-Create a work plan from the selected design document, clarifying specific implementation steps and risks.
+### Step 3: Work Plan Creation
+Invoke work-planner using Task tool:
+- `subagent_type`: "work-planner"
+- `description`: "Work plan creation"
+- `prompt`: "Create work plan from Design Doc at [path]. Integration test file: [path from step 2]. E2E test file: [path from step 2]. Integration tests are created simultaneously with each phase implementation, E2E tests are executed only in final phase."
+
+Interact with user to complete plan and obtain approval for plan content. Clarify specific implementation steps and risks.
 
 **Scope**: Up to work plan creation and obtaining approval for plan content.
 
 ## Response at Completion
-✅ **Recommended**: End with the following standard response after plan content approval
+End with the following standard response after plan content approval
 ```
 Frontend planning phase completed.
 - Work plan: docs/plans/[plan-name].md

package/.claude/commands-en/front-review.md

@@ -56,10 +56,10 @@ Execute fixes? (y/n):
 If user selects `y`:
 
 ## Pre-fix Metacognition
-**Required**: `rule-advisor -> TodoWrite -> task-executor-frontend -> quality-fixer-frontend`
+**Required**: `rule-advisor -> TaskCreate -> task-executor-frontend -> quality-fixer-frontend`
 
 1. **Execute rule-advisor**: Understand fix essence (symptomatic treatment vs root solution)
-2. **Update TodoWrite**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity". Create task file following task template (see documentation-criteria skill) -> `docs/plans/tasks/review-fixes-YYYYMMDD.md`
+2. **Update with TaskUpdate**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity". Create task file following task template (see documentation-criteria skill) -> `docs/plans/tasks/review-fixes-YYYYMMDD.md`
 3. **Execute task-executor-frontend**: Staged auto-fixes (stops at 5 files)
 4. **Execute quality-fixer-frontend**: Confirm quality gate passage
 5. **Re-validate**: Measure improvement with code-reviewer

package/.claude/commands-en/implement.md

@@ -37,13 +37,13 @@ When user responds to questions:
 - If scale changes → Re-execute requirement-analyzer with updated context
 - If `confidence: "confirmed"` or no scale change → Proceed to next step
 
-### 5. After Scale Determination: Register All Flow Steps to TodoWrite (Required)
+### 5. After Scale Determination: Register All Flow Steps with TaskCreate (Required)
 
-After scale determination, **register all steps of the applicable subagents-orchestration-guide skill flow to TodoWrite**. Always include: first "Confirm skill constraints", final "Verify skill fidelity". After registration, proceed through the flow referencing TodoWrite.
+After scale determination, **register all steps of the applicable subagents-orchestration-guide skill flow with TaskCreate**. Always include: first "Confirm skill constraints", final "Verify skill fidelity". After registration, proceed through the flow referencing TaskList.
 
 ### 6. Execute Next Action
 
-**Execute the next pending task in TodoWrite**.
+**Check next pending task with TaskList**.
 
 ## 📋 subagents-orchestration-guide skill Compliance Execution
 
@@ -54,7 +54,7 @@ After scale determination, **register all steps of the applicable subagents-orch
 - [ ] Recognized stopping points → **Use AskUserQuestion for confirmation at all Stop points**
 - [ ] Understood the 4-step cycle after task execution (task-executor → escalation judgment/follow-up → quality-fixer → commit)
 
-**Flow Adherence**: Follow "Autonomous Execution Task Management" in subagents-orchestration-guide skill, managing 4 steps with TodoWrite
+**Flow Adherence**: Follow "Autonomous Execution Task Management" in subagents-orchestration-guide skill, managing 4 steps with TaskCreate/TaskUpdate
 
 ## 🚨 Sub-agent Invocation Constraints
 
@@ -65,12 +65,17 @@ Include the following at the end of prompts when invoking sub-agents, as rule-ad
 
 ## 🎯 Mandatory Orchestrator Responsibilities
 
-### Task Execution Flow
-Following "Autonomous Execution Task Management" in subagents-orchestration-guide skill, manage these 4 steps with TodoWrite:
-1. task-executor execution (cross-layer: see Layer-Aware Agent Routing)
-2. Escalation judgment and follow-up
-3. quality-fixer execution (cross-layer: see Layer-Aware Agent Routing)
-4. git commit
+### Task Execution Quality Cycle
+Following "Autonomous Execution Task Management" in subagents-orchestration-guide skill, manage these steps with TaskCreate/TaskUpdate:
+1. **INVOKE task-executor**: Execute implementation (cross-layer: see Layer-Aware Agent Routing)
+2. **CHECK task-executor response**:
+   - `status: "escalation_needed"` or `"blocked"` → STOP and escalate to user
+   - `testsAdded` contains `*.int.test.ts` or `*.e2e.test.ts` → Execute **integration-test-reviewer**
+     - `needs_revision` → Return to step 1 with `requiredFixes`
+     - `approved` → Proceed to step 3
+   - Otherwise → Proceed to step 3
+3. **INVOKE quality-fixer**: Execute all quality checks and fixes (cross-layer: see Layer-Aware Agent Routing)
+4. **COMMIT on approval**: After `approved: true` → Execute git commit
 
 ### Test Information Communication
 After acceptance-test-generator execution, when calling work-planner, communicate:

package/.claude/commands-en/project-inject.md

@@ -12,7 +12,7 @@ CLAUDE.md's Session Initialization reads `project-context` skill at the start of
 
 ## Execution Process
 
-Register the following steps in TodoWrite and proceed systematically.
+Register the following steps with TaskCreate and proceed systematically.
 
 ### Step 1: Understand Current State
 

package/.claude/commands-en/refine-skill.md

@@ -8,7 +8,7 @@ Change request: $ARGUMENTS
 
 ## Execution Process
 
-Register the following steps in TodoWrite and proceed systematically.
+Register the following steps with TaskCreate and proceed systematically.
 
 ### Step 1: Understand the Request
 

package/.claude/commands-en/reverse-engineer.md

@@ -15,7 +15,7 @@ Target: $ARGUMENTS
 2. **Pass structured JSON** between steps using `$STEP_N_OUTPUT` placeholder notation
 3. **Never investigate code yourself** — all code reading is done by sub-agents
 
-**TodoWrite**: Register phases first, then steps within each phase as you enter it.
+**Task Registration**: Register phases first with TaskCreate, then steps within each phase as you enter it.
 
 ## Step 0: Initial Configuration
 
@@ -50,7 +50,7 @@ Phase 2: Design Doc Generation (if requested)
 
 ## Phase 1: PRD Generation
 
-**Register in TodoWrite**:
+**Register with TaskCreate**:
 - Step 1: PRD Scope Discovery
 - Per-unit processing (Steps 2-5 for each unit)
 
@@ -189,7 +189,7 @@ prompt: |
 
 *Execute only if Design Docs were requested in Step 0*
 
-**Register in TodoWrite**:
+**Register with TaskCreate**:
 - Step 6: Design Doc Scope Mapping
 - Per-unit processing (Steps 7-10 for each unit)
 

package/.claude/commands-en/review.md

@@ -57,9 +57,9 @@ Execute fixes? (y/n):
 If user selects `y`:
 
 #### Fix Execution Steps
-**Required**: `TodoWrite → task-executor → quality-fixer`
+**Required**: `TaskCreate → task-executor → quality-fixer`
 
-1. **Update TodoWrite**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity". Create task file following task template (see documentation-criteria skill) -> `docs/plans/tasks/review-fixes-YYYYMMDD.md`
+1. **Update with TaskUpdate**: Register work steps. Always include: first "Confirm skill constraints", final "Verify skill fidelity". Create task file following task template (see documentation-criteria skill) -> `docs/plans/tasks/review-fixes-YYYYMMDD.md`
 2. **Execute task-executor**: Staged auto-fixes (stops at 5 files)
 3. **Execute quality-fixer**: Confirm quality gate passage
 4. **Re-validate**: Re-validate Design Doc compliance after fixes. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved.

package/.claude/commands-en/sync-skills.md

@@ -10,7 +10,7 @@ Not mere consistency maintenance, but rule-advisor selection accuracy enhancemen
 
 ## Execution Process
 
-Register the following steps in TodoWrite and proceed systematically.
+Register the following steps with TaskCreate and proceed systematically.
 
 ### Step 1: Scan Skill Files
 

package/.claude/commands-en/update-doc.md

@@ -8,7 +8,7 @@ description: Update existing design documents (Design Doc / PRD / ADR) with revi
 
 **Core Identity**: "I am not a worker. I am an orchestrator." (see subagents-orchestration-guide skill)
 
-**First Action**: Register Steps 1-6 to TodoWrite before any execution.
+**First Action**: Register Steps 1-6 with TaskCreate before any execution.
 
 **Execution Protocol**:
 1. **Delegate all work** to sub-agents — your role is to invoke sub-agents, pass data between them, and report results
@@ -195,4 +195,4 @@ Document update completed.
 - Updated document: docs/design/[document-name].md
 - Approval status: User approved
 
-**Important**: This command ends with document approval. Does not propose transition to next phase.
+**Responsibility Boundary**: This command ends with document approval. Work planning and beyond are outside scope.

package/.claude/commands-ja/add-integration-tests.md

@@ -10,7 +10,7 @@ description: Design Docを使用して既存バックエンドコードベース
 
 **コアアイデンティティ**: 「私は作業者ではない。オーケストレーターである。」
 
-**初動アクション**: ステップ0-8をTodoWriteに登録してから実行を開始。
+**初動アクション**: ステップ0-8をTaskCreateで登録してから実行を開始。
 
 **委譲理由**: オーケストレーターとして、レビュー・品質チェックを含む全てのステップを完遂させるために、必要なコンテキストを維持する必要がある。タスクファイルをコンテキスト境界とし、全ての作業をサブエージェントが担うことでこれを実現する。