create-ai-project 1.20.2 → 1.20.4

package/.claude/agents-ja/ui-spec-designer.md

@@ -104,7 +104,7 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
 - [ ] プロトタイプ提供時: ACトレーサビリティ表が採用判定付きで完成している
 - [ ] プロトタイプ提供時: プロトタイプが`docs/ui-spec/assets/`に配置されている
 - [ ] 未確定事項の全TBDに担当者と期限がある
-- [ ] PRD要件との矛盾がない
+- [ ] UI Specの全要件がPRD要件と整合している
 
 ## 重要な設計原則
 

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

@@ -79,7 +79,7 @@ documentation-criteriaスキルの計画テンプレートに従って作業計
 1. **実行可能な粒度**: 論理的な意味のある1コミット単位、明確な完了条件、依存関係の明示
 2. **品質の組み込み**: テストは同時実装、各タスクに品質チェック組み込み
 3. **リスク管理**: 事前にリスクと対策を列挙、検知方法も定義
-4. **柔軟性の確保**: 本質的な目的を優先、過度な詳細化を避ける
+4. **柔軟性の確保**: 本質的な目的を優先し、タスク実行と検証に必要な情報のみを含める
 5. **Design Doc準拠**: 全タスクの完了条件はDesign Docの仕様から導出
 6. **実装方針の一貫性**: 実装サンプルを含める場合は、Design Docの実装方針に完全準拠すること
 

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

@@ -62,7 +62,7 @@ Invoke task-decomposer using Agent tool:
 ! ls -la docs/plans/tasks/*.md | head -10
 ```
 
-✅ **Flow**: Task generation → Autonomous execution (in this order)
+**Flow**: Task generation → Autonomous execution (in this order)
 
 ## Pre-execution Checklist
 
@@ -101,14 +101,23 @@ Autonomous sub-agents require scope constraints for stable execution. ALWAYS app
 
 After approval confirmation, start autonomous execution mode. STOP IMMEDIATELY upon detecting ANY requirement changes.
 
-## Security Review (After All Tasks Complete)
+## Post-Implementation Verification (After All Tasks Complete)
 
-After all task cycles finish, invoke security-reviewer before the completion report:
-1. **Agent tool** (subagent_type: "security-reviewer") → Pass Design Doc path and implementation file list
-2. Check response:
-   - `approved` or `approved_with_notes` → Proceed to completion report (include notes if present)
-   - `needs_revision` → Execute task-executor with `requiredFixes`, then quality-fixer, then re-invoke security-reviewer
-   - `blocked` → Escalate to user
+After all task cycles finish, run verification agents **in parallel** before the completion report:
+
+1. **Invoke both in parallel** using Agent tool:
+   - code-verifier (subagent_type: "code-verifier") → `doc_type: design-doc`, Design Doc path, `code_paths`: implementation file list (`git diff --name-only main...HEAD`)
+   - security-reviewer (subagent_type: "security-reviewer") → Design Doc path, implementation file list
+
+2. **Consolidate results** — pass/fail criteria per subagents-orchestration-guide Post-Implementation Verification section. Present unified verification report to user.
+
+3. **Fix cycle** (when any verifier failed, max 2 cycles):
+   - Consolidate all actionable findings into a single task file
+   - Execute task-executor with consolidated fixes → quality-fixer
+   - Re-run only the failed verifiers
+   - If still failing after 2 cycles → Escalate to user with remaining findings
+
+4. **All passed** → Proceed to completion report
 
 ## Output Example
 Implementation phase completed.

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

@@ -4,20 +4,13 @@ description: Execute frontend implementation in autonomous execution mode
 
 ## Orchestrator Definition
 
-**Core Identity**: "I am not a worker. I am an orchestrator." (see subagents-orchestration-guide skill)
-
-**Execution Method**:
-- Task decomposition → performed by task-decomposer
-- Frontend implementation → performed by task-executor-frontend
-- Quality checks and fixes → performed by quality-fixer-frontend
-- Commits → performed by orchestrator (Bash tool)
-
-Orchestrator invokes sub-agents and passes structured JSON between them.
+**Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
 
 **Execution Protocol**:
-1. **Delegate all work through Agent tool** — invoke sub-agents, pass data between them, and report results (permitted tools: see subagents-orchestration-guide "Orchestrator's Permitted Tools")
+1. **Delegate all work through Agent tool** — invoke sub-agents, pass deliverable paths between them, and report results (permitted tools: see subagents-orchestration-guide "Orchestrator's Permitted Tools")
 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
+4. **Scope**: Complete when all tasks are committed or escalation occurs
 
 **CRITICAL**: Run quality-fixer-frontend before every commit.
 
@@ -69,7 +62,7 @@ Invoke task-decomposer using Agent tool:
 ! ls -la docs/plans/tasks/*.md | head -10
 ```
 
-✅ **Flow**: Task generation → Autonomous execution (in this order)
+**Flow**: Task generation → Autonomous execution (in this order)
 
 ## Pre-execution Checklist
 
@@ -79,40 +72,22 @@ Invoke task-decomposer using Agent tool:
   - If commit capability unavailable → Escalate before autonomous mode
   - Other environments (tests, quality tools) → Subagents will escalate
 
-## Task Execution Cycle (4-Step Cycle) - Frontend Specialized
-
+## Task Execution Cycle (4-Step Cycle)
 **MANDATORY EXECUTION CYCLE**: `task-executor-frontend → escalation check → quality-fixer-frontend → commit`
 
-### Sub-agent Invocation Method
-Use Agent tool to invoke sub-agents:
-- `subagent_type`: Agent name
-- `description`: Brief task description (3-5 words)
-- `prompt`: Specific instructions
-
-### Structured Response Specification
-Each sub-agent responds in JSON format:
-- **task-executor-frontend**: status, filesModified, testsAdded, requiresTestReview, 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. **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"`
+2. **Agent tool** (subagent_type: "task-executor-frontend") → Pass task file path in prompt, receive structured response
 3. **CHECK task-executor-frontend response**:
    - `status: "escalation_needed"` or `"blocked"` → STOP and escalate to user
    - `requiresTestReview` is `true` → 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"`
-5. **EXECUTE commit**: After `approved: true` confirmation, execute git commit IMMEDIATELY. Use `changeSummary` for commit message.
+4. **INVOKE quality-fixer-frontend**: Execute all quality checks and fixes
+5. **COMMIT on approval**: After `approved: true` from quality-fixer-frontend → Execute git commit
 
-**CRITICAL**: Monitor ALL structured responses WITHOUT EXCEPTION and ENSURE every quality gate is passed.
+**CRITICAL**: Parse every sub-agent response for status fields. Execute the matching branch in the 4-step cycle. Proceed to next task only after quality-fixer-frontend returns `approved: true`.
 
 ## Sub-agent Invocation Constraints
 
@@ -128,14 +103,23 @@ Autonomous sub-agents require scope constraints for stable execution. ALWAYS app
 
 VERIFY approval status before proceeding. Once confirmed, INITIATE autonomous execution mode. STOP IMMEDIATELY upon detecting ANY requirement changes.
 
-## Security Review (After All Tasks Complete)
+## Post-Implementation Verification (After All Tasks Complete)
+
+After all task cycles finish, run verification agents **in parallel** before the completion report:
+
+1. **Invoke both in parallel** using Agent tool:
+   - code-verifier (subagent_type: "code-verifier") → `doc_type: design-doc`, Design Doc path, `code_paths`: implementation file list (`git diff --name-only main...HEAD`)
+   - security-reviewer (subagent_type: "security-reviewer") → Design Doc path, implementation file list
+
+2. **Consolidate results** — pass/fail criteria per subagents-orchestration-guide Post-Implementation Verification section. Present unified verification report to user.
+
+3. **Fix cycle** (when any verifier failed, max 2 cycles):
+   - Consolidate all actionable findings into a single task file
+   - Execute task-executor-frontend with consolidated fixes → quality-fixer-frontend
+   - Re-run only the failed verifiers
+   - If still failing after 2 cycles → Escalate to user with remaining findings
 
-After all task cycles finish, invoke security-reviewer before the completion report:
-1. **Agent tool** (subagent_type: "security-reviewer") → Pass Design Doc path and implementation file list
-2. Check response:
-   - `approved` or `approved_with_notes` → Proceed to completion report (include notes if present)
-   - `needs_revision` → Execute task-executor-frontend with `requiredFixes`, then quality-fixer-frontend, then re-invoke security-reviewer
-   - `blocked` → Escalate to user
+4. **All passed** → Proceed to completion report
 
 ## Output Example
 Frontend implementation phase completed.

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

@@ -6,26 +6,42 @@ description: Execute from requirement analysis to frontend design document creat
 
 ## Orchestrator Definition
 
-**Role**: Orchestrator
-
-**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
-
-Orchestrator invokes sub-agents and passes structured JSON between them.
+**Core Identity**: "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 frontend design flow below** (this command covers medium/large frontend; UI Spec is created before codebase analysis so that component structure informs the technical design):
+   - Execute: requirement-analyzer → ui-spec-designer → codebase-analyzer → technical-designer-frontend → code-verifier → document-reviewer → design-sync
+   - **Stop at every `[Stop: ...]` marker** → Wait for user approval before proceeding
+3. **Scope**: Complete when design documents receive approval
+
+**CRITICAL**: Execute document-reviewer, design-sync, and all stopping points defined in subagents-orchestration-guide skill flows — each serves as a quality gate. Skipping any step risks undetected inconsistencies.
+
+## Workflow Overview
+
+```
+Requirements → requirement-analyzer → [Stop: Scale determination]
+                                           ↓
+                                   ui-spec-designer → [Stop: UI Spec approval]
+                                           ↓
+                                   codebase-analyzer → technical-designer-frontend
+                                           ↓
+                                   code-verifier → document-reviewer
+                                           ↓
+                                      design-sync → [Stop: Design approval]
+```
 
 ## Scope Boundaries
 
 **Included in this command**:
 - Requirement analysis with requirement-analyzer
-- Codebase analysis with codebase-analyzer (before Design Doc creation)
+- Codebase analysis with codebase-analyzer (before technical design)
 - 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
 - Design Doc verification with code-verifier (before document review)
 - Document review with document-reviewer
+- Design Doc consistency verification with design-sync
 
 **Responsibility Boundary**: This command completes with frontend design document (UI Spec/ADR/Design Doc) approval. Work planning and beyond are outside scope.
 
@@ -39,7 +55,8 @@ Considering the deep impact on design, first engage in dialogue to understand th
 - Expected outcomes and success criteria
 - Relationship with existing systems
 
-Once requirements are moderately clarified:
+Once the user has answered the three dialogue questions above, execute the process below within design scope. Follow subagents-orchestration-guide Call Examples for codebase-analyzer and code-verifier invocations.
+
 - Invoke **requirement-analyzer** using Agent tool
   - `subagent_type: "requirement-analyzer"`
   - `description: "Requirement analysis"`
@@ -69,15 +86,30 @@ First, analyze the existing codebase:
 - Invoke **codebase-analyzer** using Agent tool
   - `subagent_type: "codebase-analyzer"`, `description: "Codebase analysis"`, `prompt: "requirement_analysis: [JSON from Step 1]. requirements: [user requirements]. Analyze existing codebase for frontend design guidance."`
 
-Create appropriate design documents according to scale determination:
+Create appropriate design documents according to scale determination. technical-designer-frontend presents at least two architecture alternatives (technology selection, data flow design) with trade-offs for each:
 - Invoke **technical-designer-frontend** using Agent 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. Codebase analysis: [JSON from codebase-analyzer]. UI Spec is at [ui-spec path]. Inherit component structure and state design from UI Spec."`
+  - For ADR: `subagent_type: "technical-designer-frontend"`, `description: "ADR creation"`, `prompt: "Create ADR for [technical decision]. Present at least two alternatives with trade-offs."`
+  - For Design Doc: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc creation"`, `prompt: "Create Design Doc based on requirements. Codebase analysis: [JSON from codebase-analyzer]. UI Spec is at [ui-spec path]. Inherit component structure and state design from UI Spec. Present at least two architecture alternatives with trade-offs."`
 - **(Design Doc only)** Invoke **code-verifier** to verify Design Doc against existing code. Skip for ADR.
-  - `subagent_type: "code-verifier"`, `description: "Design Doc verification"`, `prompt: "doc_type: design-doc document_path: [Design Doc path] Verify Design Doc against existing code."`
+  - `subagent_type: "code-verifier"`, `description: "Design Doc verification"`, `prompt: "doc_type: design-doc document_path: [Design Doc path] mode: pre-implementation (code_paths omitted — verifier discovers scope from document). Verify Design Doc against existing code."`
 - Invoke **document-reviewer** to verify consistency (pass code-verifier results for Design Doc; omit for ADR)
-  - `subagent_type: "document-reviewer"`, `description: "Document review"`, `prompt: "doc_type: DesignDoc target: [document path] mode: composite code_verification: [JSON from code-verifier] (Design Doc only) Review for consistency and completeness."`
-- **[STOP]**: Present design alternatives and trade-offs, obtain user approval
+  - `subagent_type: "document-reviewer"`, `description: "Document review"`, `prompt: "doc_type: DesignDoc target: [document path] mode: composite code_verification: [JSON from code-verifier] (Design Doc only). Review for consistency and completeness."`
+
+### Step 4: Design Consistency Verification
+- Invoke **design-sync** using Agent tool
+  - `subagent_type: "design-sync"`, `description: "Design consistency check"`, `prompt: "Check consistency across all Design Docs in docs/design/. Report conflicts and overlaps."`
+- **[STOP]**: Present design documents and design-sync results, obtain user approval
+
+## Completion Criteria
+
+- [ ] Executed requirement-analyzer and determined scale
+- [ ] Executed codebase-analyzer and passed results to technical-designer-frontend
+- [ ] Created UI Specification with ui-spec-designer (when applicable)
+- [ ] Created appropriate design document (ADR or Design Doc) with technical-designer-frontend
+- [ ] Executed code-verifier on Design Doc and passed results to document-reviewer (skip for ADR-only)
+- [ ] Executed document-reviewer and addressed feedback
+- [ ] Executed design-sync for consistency verification
+- [ ] Obtained user approval for design document
 
 ## Output Example
 Frontend design phase completed.

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

@@ -6,13 +6,16 @@ description: Create frontend work plan from design document and obtain plan appr
 
 ## Orchestrator Definition
 
-**Role**: Orchestrator
+**Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
 
-**Execution Method**:
-- Test skeleton generation → performed by acceptance-test-generator
-- Work plan creation → performed by work-planner
+**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 subagents-orchestration-guide skill planning flow**:
+   - Execute steps defined below
+   - **Stop and obtain approval** for plan content before completion
+3. **Scope**: See Scope Boundaries below
 
-Orchestrator invokes sub-agents and passes structured JSON between them.
+**CRITICAL**: Always execute acceptance-test-generator before work-planner — the test skeleton is a required input per subagents-orchestration-guide medium/large flow.
 
 ## Scope Boundaries
 
@@ -24,14 +27,14 @@ Orchestrator invokes sub-agents and passes structured JSON between them.
 
 **Responsibility Boundary**: This command completes with work plan approval.
 
-Create frontend work plan with the following process:
+Follow the planning process below:
 
 ## Execution Process
 
 ### 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)
+   ! 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)
 
 ### Step 2: Test Skeleton Generation
 Invoke acceptance-test-generator using Agent tool:
@@ -40,13 +43,17 @@ Invoke acceptance-test-generator using Agent tool:
 - 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]."`
 
+Pass integration test file path and E2E test file path to work-planner according to subagents-orchestration-guide "acceptance-test-generator → work-planner" section.
+
 ### Step 3: Work Plan Creation
 Invoke work-planner using Agent tool:
 - `subagent_type`: "work-planner"
 - `description`: "Work plan creation"
 - `prompt`: "Create work plan from Design Doc at [path]. Integration test file: [integration test path from step 2]. E2E test file: [E2E test 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.
+- Follow subagents-orchestration-guide Prompt Construction Rule for additional prompt parameters
+- Present work plan to user for review. If user requests changes, re-invoke work-planner with revised parameters
+- Highlight steps with unclear scope or external dependencies and ask user to confirm
 
 **Scope**: Up to work plan creation and obtaining approval for plan content.
 

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

@@ -4,24 +4,25 @@ description: Design Doc compliance and security validation with optional auto-fi
 
 **Command Context**: Post-implementation quality assurance command for React/TypeScript frontend
 
-## Execution Method
+## Orchestrator Definition
 
-- Compliance validation -> performed by code-reviewer
-- Security validation -> performed by security-reviewer
-- Rule analysis -> performed by rule-advisor
-- Fix implementation -> performed by task-executor-frontend
-- Quality checks -> performed by quality-fixer-frontend
-- Re-validation -> performed by code-reviewer / security-reviewer
+**Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
 
-Orchestrator invokes sub-agents and passes structured JSON between them.
+**First Action**: Register Steps 1-11 using TaskCreate before any execution.
 
-Design Doc (uses most recent if omitted): $ARGUMENTS
+## Execution Method
+
+- Compliance validation → performed by code-reviewer
+- Security validation → performed by security-reviewer
+- Fix implementation → performed by task-executor-frontend
+- Quality checks → performed by quality-fixer-frontend
+- Re-validation → performed by code-reviewer / security-reviewer
 
-**Think deeply** Understand the essence of compliance validation and execute:
+Design Doc (uses most recent if omitted): $ARGUMENTS
 
 ## Execution Flow
 
-### 1. Prerequisite Check
+### Step 1: Prerequisite Check
 ```bash
 # Identify Design Doc
 ls docs/design/*.md | grep -v template | tail -1
@@ -30,15 +31,15 @@ ls docs/design/*.md | grep -v template | tail -1
 git diff --name-only main...HEAD
 ```
 
-### 2. Execute code-reviewer
+### Step 2: Execute code-reviewer
 Invoke code-reviewer using Agent tool:
 - `subagent_type`: "code-reviewer"
 - `description`: "Code compliance review"
-- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report with complianceRate, verdict, acceptanceCriteria, and qualityIssues."
+- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report."
 
 **Store output as**: `$STEP_2_OUTPUT`
 
-### 3. Execute security-reviewer
+### Step 3: Execute security-reviewer
 Invoke security-reviewer using Agent tool:
 - `subagent_type`: "security-reviewer"
 - `description`: "Security review"
@@ -46,7 +47,7 @@ Invoke security-reviewer using Agent tool:
 
 **Store output as**: `$STEP_3_OUTPUT`
 
-### 4. Verdict and Response
+### Step 4: Verdict and Response
 
 **If security-reviewer returned `blocked`**: Stop immediately. Report the blocked finding and escalate to user. Do not proceed to fix steps.
 
@@ -63,10 +64,15 @@ Invoke security-reviewer using Agent tool:
 ```
 Code Compliance: [complianceRate from code-reviewer]
   Verdict: [verdict from code-reviewer]
+  Identifier Match Rate: [identifierMatchRate from code-reviewer]
   Acceptance Criteria:
-  - [fulfilled] [item]
+  - [fulfilled] [item] (confidence: [high/medium/low])
   - [partially_fulfilled] [item]: [gap] — [suggestion]
   - [unfulfilled] [item]: [gap] — [suggestion]
+  Identifier Mismatches:
+  - [identifier]: DD=[designDocValue] Code=[codeValue] at [location]
+  Quality Findings:
+  - [category] [location]: [description] — [rationale]
 
 Security Review: [status from security-reviewer]
   Findings by category:
@@ -79,46 +85,44 @@ Security Review: [status from security-reviewer]
 Execute fixes? (y/n):
 ```
 
-If both pass and user selects `n`: Skip fix steps, proceed to Final Report.
+If both pass and user selects `n`: Skip Steps 5-10, proceed to Step 11.
 
-If user selects `y`:
+### Step 5: Load Task Template
 
-## Pre-fix Metacognition
+Read documentation-criteria skill to obtain the task file template (references/task-template.md) for Step 6.
 
-### 5. Execute rule-advisor
-Invoke rule-advisor using Agent tool:
-- `subagent_type`: "rule-advisor"
-- `description`: "Analyze fix approach"
-- `prompt`: "Task: Fix review findings. Code issues: $STEP_2_OUTPUT. Security findings: $STEP_3_OUTPUT. Analyze fix essence and select appropriate rules."
+### Step 6: Create Task File
 
-### 6. Create Task File
-Register work steps using TaskCreate. 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`. Include both code compliance issues and security requiredFixes.
+Create task file at `docs/plans/tasks/review-fixes-YYYYMMDD.md`
+Include both code compliance issues and security requiredFixes.
 
-### 7. Execute Fixes
+### Step 7: Execute Fixes
 Invoke task-executor-frontend using Agent tool:
 - `subagent_type`: "task-executor-frontend"
 - `description`: "Execute review fixes"
 - `prompt`: "Task file: docs/plans/tasks/review-fixes-YYYYMMDD.md. Apply staged fixes (stops at 5 files)."
 
-### 8. Quality Check
+### Step 8: Quality Check
 Invoke quality-fixer-frontend using Agent tool:
 - `subagent_type`: "quality-fixer-frontend"
 - `description`: "Quality gate check"
 - `prompt`: "Confirm quality gate passage for fixed files."
 
-### 9. Re-validate code-reviewer
+### Step 9: Re-validate code-reviewer
+
 Invoke code-reviewer using Agent tool:
 - `subagent_type`: "code-reviewer"
 - `description`: "Re-validate compliance"
-- `prompt`: "Re-validate Design Doc compliance after fixes. Prior issues: $STEP_2_OUTPUT. Design Doc: [path]. Implementation files: [file list]."
+- `prompt`: "Re-validate Design Doc compliance after fixes. Design Doc: [path]. Implementation files: [file list]. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved."
 
-### 10. Re-validate security-reviewer (only if security fixes were applied)
-Invoke security-reviewer using Agent tool:
+### Step 10: Re-validate security-reviewer
+
+Invoke security-reviewer using Agent tool (only if security fixes were applied):
 - `subagent_type`: "security-reviewer"
 - `description`: "Re-validate security"
 - `prompt`: "Re-validate security after fixes. Prior findings: $STEP_3_OUTPUT. Design Doc: [path]. Implementation files: [file list]."
 
-### Final Report
+### Step 11: Final Report
 ```
 Code Compliance:
   Initial: [X]%

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

@@ -33,7 +33,7 @@ git diff --name-only main...HEAD
 Invoke code-reviewer using Agent tool:
 - `subagent_type`: "code-reviewer"
 - `description`: "Code compliance review"
-- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report with complianceRate, verdict, acceptanceCriteria, and qualityIssues."
+- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report."
 
 **Store output as**: `$STEP_2_OUTPUT`
 
@@ -62,10 +62,15 @@ Invoke security-reviewer using Agent tool:
 ```
 Code Compliance: [complianceRate from code-reviewer]
   Verdict: [verdict from code-reviewer]
+  Identifier Match Rate: [identifierMatchRate from code-reviewer]
   Acceptance Criteria:
-  - [fulfilled] [item]
+  - [fulfilled] [item] (confidence: [high/medium/low])
   - [partially_fulfilled] [item]: [gap] — [suggestion]
   - [unfulfilled] [item]: [gap] — [suggestion]
+  Identifier Mismatches:
+  - [identifier]: DD=[designDocValue] Code=[codeValue] at [location]
+  Quality Findings:
+  - [category] [location]: [description] — [rationale]
 
 Security Review: [status from security-reviewer]
   Findings by category:
@@ -80,9 +85,9 @@ Execute fixes? (y/n):
 
 If both pass and user selects `n`: Skip Steps 5-10, proceed to Step 11.
 
-### 5. Execute Skill
+### 5. Load Task Template
 
-Execute Skill: documentation-criteria (for task file template)
+Read documentation-criteria skill to obtain the task file template (references/task-template.md) for Step 6.
 
 ### 6. Create Task File
 
@@ -108,7 +113,7 @@ Invoke quality-fixer using Agent tool:
 Invoke code-reviewer using Agent tool:
 - `subagent_type`: "code-reviewer"
 - `description`: "Re-validate compliance"
-- `prompt`: "Re-validate Design Doc compliance after fixes. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved."
+- `prompt`: "Re-validate Design Doc compliance after fixes. Design Doc: [path]. Implementation files: [file list]. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved."
 
 ### 10. Re-validate security-reviewer
 

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

@@ -62,7 +62,7 @@ Agentツールでtask-decomposerを呼び出す:
 ! ls -la docs/plans/tasks/*.md | head -10
 ```
 
-✅ **フロー**: タスク生成 → 自律実行（この順序で実行）
+**フロー**: タスク生成 → 自律実行（この順序で実行）
 
 ## 実行前チェックリスト
 
@@ -101,14 +101,23 @@ Agentツールでtask-decomposerを呼び出す:
 
 承認確認後、自律実行モードを開始。要件変更を検知した場合は即座に停止。
 
-## Security Review（全タスク完了後）
+## 実装後検証（全タスク完了後）
 
-全タスクサイクル完了後、完了レポートの前にsecurity-reviewerを実行:
-1. **Agent tool** (subagent_type: "security-reviewer") → Design Docパスと実装ファイルリストを渡す
-2. レスポンスを確認:
-   - `approved` または `approved_with_notes` → 完了レポートへ（notesがあれば含める）
-   - `needs_revision` → task-executorで`requiredFixes`を実行、quality-fixer実行後、security-reviewerを再実行
-   - `blocked` → ユーザーにエスカレーション
+全タスクサイクル完了後、完了レポートの前に検証エージェントを**並列実行**:
+
+1. **両方を並列で実行** (Agent tool):
+   - code-verifier (subagent_type: "code-verifier") → `doc_type: design-doc`、Design Docパス、`code_paths`: 実装ファイルリスト（`git diff --name-only main...HEAD`）
+   - security-reviewer (subagent_type: "security-reviewer") → Design Docパス、実装ファイルリスト
+
+2. **結果の統合** — 合格/不合格の基準はsubagents-orchestration-guideの実装後検証セクション参照。統合検証レポートをユーザーに提示。
+
+3. **修正サイクル**（いずれかの検証エージェントが不合格の場合、最大2回）:
+   - 全ての対応可能な検出事項を1つのタスクファイルに統合
+   - task-executorで統合修正を実行 → quality-fixer
+   - 不合格の検証エージェントのみ再実行
+   - 2回のサイクル後も不合格が残る場合 → 残存する検出事項とともにユーザーにエスカレーション
+
+4. **全て合格** → 完了レポートへ
 
 ## 出力例
 実装フェーズが完了しました。