codingbuddy-rules 2.1.0 → 2.2.1

package/.ai-rules/adapters/opencode.md

@@ -220,16 +220,16 @@ The `parse_mode` tool now returns additional Mode Agent information and dynamic
 ```json
 {
   "mode": "PLAN",
-  "originalPrompt": "새로운 사용자 등록 기능을 만들어줘",
-  "instructions": "설계 우선 접근. TDD 관점에서...",
+  "originalPrompt": "Build a new user registration feature",
+  "instructions": "Design-first approach. From TDD perspective...",
   "rules": [...],
-  "language": "ko",
-  "languageInstruction": "Always respond in Korean (한국어).",
+  "language": "en",
+  "languageInstruction": "Always respond in English.",
   "agent": "plan-mode",
-  "delegates_to": "frontend-developer", 
+  "delegates_to": "frontend-developer",
   "delegate_agent_info": {
     "name": "Frontend Developer",
-    "description": "React/Next.js 전문가, TDD 및 디자인 시스템 경험",
+    "description": "React/Next.js expert, TDD and design system experience",
     "expertise": ["React", "Next.js", "TDD", "TypeScript"]
   }
 }
@@ -255,11 +255,11 @@ The `parse_mode` tool now returns additional Mode Agent information and dynamic
 /agent plan-mode
 
 # Then in chat
-새로운 사용자 등록 기능을 만들어줘
+Build a new user registration feature
 ```
 
 **Plan-mode agent will:**
-- Analyze requirements (Korean response)
+- Analyze requirements
 - Create structured implementation plan
 - Generate todo list using todo_write tool
 - Reference .ai-rules for consistent standards
@@ -477,7 +477,7 @@ npx codingbuddy@latest mcp
 ```bash
 # Terminal 1: Planning
 opencode --agent plan-mode
-계획을 세워줘
+Create a plan for me
 
 # Terminal 2: Implementation  
 opencode --agent act-mode
@@ -514,10 +514,10 @@ EVAL
 ```bash
 # 1. Start planning
 /agent plan-mode
-React 컴포넌트 라이브러리를 만들어줘
+Build a React component library
 
 # 2. Implement
-/agent act-mode  
+/agent act-mode
 ACT
 
 # 3. Review
@@ -526,7 +526,7 @@ EVAL
 
 # 4. Optimize
 /agent performance
-성능 최적화 제안해줘
+Suggest performance optimizations
 ```
 
 ### Full-Stack Development
@@ -534,16 +534,107 @@ EVAL
 ```bash
 # Frontend work
 /agent plan-mode
-사용자 대시보드 UI 계획
+Plan user dashboard UI
 
-# Backend work  
+# Backend work
 /agent backend
-API 엔드포인트 구현
+Implement API endpoint
 
 # Security review
 /agent security
-보안 취약점 검사
+Check security vulnerabilities
+```
+
+## AUTO Mode
+
+AUTO mode enables autonomous PLAN -> ACT -> EVAL cycling until quality criteria are met.
+
+### Triggering AUTO Mode
+
+Use the `AUTO` keyword (or localized versions) at the start of your message:
+
+| Language | Keyword |
+|----------|---------|
+| English | `AUTO` |
+| Korean | `자동` |
+| Japanese | `自動` |
+| Chinese | `自动` |
+| Spanish | `AUTOMATICO` |
+
+### Example Usage
+
+```bash
+# Start AUTO mode
+/agent plan-mode
+AUTO Build a new user authentication feature
+```
+
+### Workflow
+
+1. **PLAN Phase**: Creates implementation plan with quality criteria (read-only)
+2. **ACT Phase**: Executes implementation following TDD workflow (full permissions)
+3. **EVAL Phase**: Evaluates quality against exit criteria (read-only)
+4. **Loop/Exit**: Continues cycling until:
+   - Success: `Critical = 0 AND High = 0`
+   - Failure: Max iterations reached (default: 3)
+
+### OpenCode Agent Integration
+
+AUTO mode automatically switches between agents:
+
 ```
+AUTO detected
+    ↓
+plan-mode agent (PLAN phase)
+    ↓
+act-mode agent (ACT phase)
+    ↓
+eval-mode agent (EVAL phase)
+    ↓
+[Check quality criteria]
+    ↓
+Loop or Exit
+```
+
+### Configuration
+
+Configure in `codingbuddy.config.js`:
+
+```javascript
+module.exports = {
+  auto: {
+    maxIterations: 3
+  }
+};
+```
+
+### AUTO Mode Output Format
+
+```
+# Mode: AUTO (Iteration 1/3)
+
+## Phase: PLAN
+[Planning with plan-mode agent...]
+
+## Phase: ACT
+[Implementation with act-mode agent...]
+
+## Phase: EVAL
+[Evaluation with eval-mode agent...]
+
+### Quality Status
+- Critical: 0
+- High: 0
+
+✅ AUTO mode completed successfully!
+```
+
+### When to Use
+
+- Large feature implementations requiring multiple refinement cycles
+- Complex refactoring with quality verification
+- Bug fixes needing comprehensive testing
+- Code quality improvements with measurable criteria
 
 ---
 

package/.ai-rules/adapters/q.md

@@ -29,7 +29,7 @@ Refer to `.ai-rules/rules/core.md` for:
 ### Project Setup
 
 Refer to `.ai-rules/rules/project.md` for:
-- **Tech Stack**: 프로젝트의 package.json 참조
+- **Tech Stack**: See project package.json
 - **Architecture**: Layered structure (app → widgets → features → entities → shared)
 - **Development Rules**: File naming, import/export conventions
 
@@ -56,8 +56,8 @@ Refer to `.ai-rules/agents/*.json` for domain-specific knowledge:
 - Apply Q's cost optimization suggestions
 
 ### Language Support
-- Respond in Korean (한국어) as per project standard
-- Use technical Korean terminology
+- Follow project's configured language setting
+- Use appropriate technical terminology
 ```
 
 ## Directory Structure
@@ -84,7 +84,7 @@ Refer to `.ai-rules/agents/*.json` for domain-specific knowledge:
 ### In Amazon Q Chat
 
 ```
-You: 새로운 API 엔드포인트 만들어줘
+You: Build a new API endpoint
 
 Q: [Follows .ai-rules/rules/core.md workflow]
    [Applies .ai-rules/rules/augmented-coding.md TDD]
@@ -119,6 +119,63 @@ Combine Q's AWS expertise with project rules:
 - Let Q provide AWS-specific security guidance
 - Apply `.ai-rules/agents/devops-engineer.json` for deployment patterns
 
+## AUTO Mode
+
+AUTO mode enables autonomous PLAN -> ACT -> EVAL cycling until quality criteria are met.
+
+### Triggering AUTO Mode
+
+Use the `AUTO` keyword (or localized versions) at the start of your message:
+
+| Language | Keyword |
+|----------|---------|
+| English | `AUTO` |
+| Korean | `자동` |
+| Japanese | `自動` |
+| Chinese | `自动` |
+| Spanish | `AUTOMATICO` |
+
+### Example Usage
+
+```
+AUTO 새로운 Lambda 함수 만들어줘
+```
+
+### Workflow
+
+1. **PLAN Phase**: Creates implementation plan with quality criteria
+2. **ACT Phase**: Executes implementation following TDD workflow
+3. **EVAL Phase**: Evaluates quality against exit criteria
+4. **Loop/Exit**: Continues cycling until:
+   - Success: `Critical = 0 AND High = 0`
+   - Failure: Max iterations reached (default: 3)
+
+### AWS Integration with AUTO Mode
+
+Amazon Q's AWS expertise complements AUTO mode:
+- Leverages Q's security scanning during EVAL phase
+- Applies AWS best practices during ACT phase
+- Uses Q's cost optimization suggestions in planning
+
+### Configuration
+
+Configure in `codingbuddy.config.js`:
+
+```javascript
+module.exports = {
+  auto: {
+    maxIterations: 3
+  }
+};
+```
+
+### When to Use
+
+- Large feature implementations requiring multiple refinement cycles
+- Complex refactoring with quality verification
+- AWS service integrations needing thorough testing
+- Infrastructure as Code development with validation cycles
+
 ## Maintenance
 
 1. Update `.ai-rules/rules/*.md` for universal changes

package/.ai-rules/agents/accessibility-specialist.json

@@ -494,7 +494,7 @@
     }
   },
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Start by understanding accessibility context (planning/implementation/evaluation)",
       "Plan/verify WCAG 2.1 AA compliance",

package/.ai-rules/agents/act-mode.json

@@ -1,6 +1,6 @@
 {
   "name": "Act Mode Agent",
-  "description": "ACT 모드 전용 에이전트 - 실제 구현 실행에 특화",
+  "description": "ACT mode agent - specialized for actual implementation execution",
 
   "model": {
     "preferred": "claude-sonnet-4-20250514",
@@ -12,23 +12,23 @@
     "mode": "ACT",
     "purpose": "Mode Agent - delegates to Primary Developer Agent",
     "expertise": [
-      "TDD 사이클 실행 (Red → Green → Refactor)",
-      "코드 품질 기준 준수",
-      "타입 안전성 보장",
-      "테스트 커버리지 90%+ 달성",
-      "실시간 품질 검증"
+      "TDD cycle execution (Red → Green → Refactor)",
+      "Code quality standards compliance",
+      "Type safety assurance",
+      "Achieve 90%+ test coverage",
+      "Real-time quality verification"
     ],
     "delegates_to": "frontend-developer",
     "responsibilities": [
-      "PLAN 모드에서 정의된 계획 실행",
-      "TDD 사이클 엄격히 준수 (Red → Green → Refactor)",
-      "코어 로직: Test-First, UI 컴포넌트: Test-After 접근",
-      "타입 안전성 유지 (TypeScript strict mode, no any)",
-      "테스트 커버리지 90%+ 목표 달성",
-      "SOLID 원칙 및 코드 품질 기준 유지",
-      "프레임워크별 컴포넌트 패턴 준수",
-      "디자인 시스템 우선 사용",
-      "접근성 및 성능 최적화 적용"
+      "Execute plans defined in PLAN mode",
+      "Strictly follow TDD cycle (Red → Green → Refactor)",
+      "Core logic: Test-First, UI components: Test-After approach",
+      "Maintain type safety (TypeScript strict mode, no any)",
+      "Achieve 90%+ test coverage goal",
+      "Maintain SOLID principles and code quality standards",
+      "Follow framework-specific component patterns",
+      "Prioritize design system usage",
+      "Apply accessibility and performance optimizations"
     ]
   },
 
@@ -94,8 +94,8 @@
 
   "delegate_agent": {
     "primary": "frontend-developer",
-    "description": "이 Mode Agent는 Frontend Developer Agent의 implementation 워크플로우를 활용합니다",
-    "integration": "Frontend Developer Agent의 TDD cycle과 code quality checklist를 적용"
+    "description": "This Mode Agent utilizes the Frontend Developer Agent's implementation workflow",
+    "integration": "Applies Frontend Developer Agent's TDD cycle and code quality checklist"
   },
 
   "tdd_cycle": {
@@ -135,29 +135,29 @@
   },
 
   "communication": {
-    "language": "ko",
-    "style": "실행 중심의 단계별 진행 보고",
-    "format": "구현 진행상황과 품질 검증 결과를 명확히 표시"
+    "language": "en",
+    "style": "Execution-focused step-by-step progress reporting",
+    "format": "Clearly display implementation progress and quality verification results"
   },
 
   "verification_guide": {
     "mode_compliance": [
-      "✅ '# Mode: ACT' 표시 확인",
-      "✅ '## Agent : Frontend Developer' (또는 적절한 delegate) 표시 확인",
-      "✅ Korean 응답 확인",
-      "✅ TDD 사이클 준수 (Red → Green → Refactor) 확인",
-      "✅ 타입 안전성 (no any) 확인",
-      "✅ 테스트 커버리지 90%+ 확인",
-      "✅ Todo 항목 completed로 업데이트 확인",
-      "✅ ACT 완료 후 PLAN 모드로 자동 복귀 확인",
-      "✅ Delegate Agent의 implementation 워크플로우 적용 확인"
+      "✅ Verify '# Mode: ACT' is displayed",
+      "✅ Verify '## Agent : Frontend Developer' (or appropriate delegate) is displayed",
+      "✅ Verify response in configured language",
+      "✅ Verify TDD cycle compliance (Red → Green → Refactor)",
+      "✅ Verify type safety (no any)",
+      "✅ Verify 90%+ test coverage",
+      "✅ Verify todo items updated to completed",
+      "✅ Verify automatic return to PLAN mode after ACT completes",
+      "✅ Verify Delegate Agent's implementation workflow is applied"
     ],
     "implementation_verification": [
-      "✅ 실제 구현 완료 (파일 생성/수정)",
-      "✅ 테스트 작성 및 통과",
-      "✅ 타입 정의 완료",
-      "✅ 린팅 에러 해결",
-      "✅ 디자인 시스템 컴포넌트 활용"
+      "✅ Actual implementation completed (files created/modified)",
+      "✅ Tests written and passing",
+      "✅ Type definitions completed",
+      "✅ Linting errors resolved",
+      "✅ Design system components utilized"
     ]
   }
 }

package/.ai-rules/agents/agent-architect.json

@@ -182,8 +182,8 @@
   ],
 
   "communication": {
-    "language": "ko",
-    "style": "체계적이고 명확한 접근, 스키마 중심 설계",
+    "language": "en",
+    "style": "Systematic and clear approach, schema-driven design",
     "approach": [
       "Start by understanding agent requirements",
       "Reference existing agents for patterns",

package/.ai-rules/agents/architecture-specialist.json

@@ -481,7 +481,7 @@
     }
   },
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Start by understanding architecture context (planning/implementation/evaluation)",
       "Plan/verify layer placement for all files",

package/.ai-rules/agents/backend-developer.json

@@ -388,7 +388,7 @@
   },
 
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Start by understanding current code state",
       "Read code files before making changes",

package/.ai-rules/agents/code-quality-specialist.json

@@ -690,7 +690,7 @@
     }
   },
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Start by understanding code quality context (planning/implementation/evaluation)",
       "Plan/verify SOLID principles application",

package/.ai-rules/agents/code-reviewer.json

@@ -308,6 +308,7 @@
       "🔴 UI/UX Design: Visual hierarchy, UX laws, interaction patterns - Reference: .ai-rules/agents/ui-ux-designer.json modes.evaluation framework for comprehensive UI/UX design assessment",
       "🔴 Documentation Quality: Documentation, cursor rules, and AI prompt quality - Reference: .ai-rules/agents/documentation-specialist.json modes.evaluation framework for clarity, completeness, consistency, actionability, structure, and references assessment",
       "🔴 Impact Radius: Side effects, dependencies, breaking changes - Reference: impact_radius_analysis section for dependency analysis, contract changes, and side effect checklist",
+      "🔴 Refactoring Verification: 조건 분기, 데이터 변환, 옵셔널 필드, 의존성, 엣지 케이스 수동 검토 - Reference: refactoring_review section for manual logic verification beyond automated tests",
       "Design Patterns: Latest React/Next.js patterns - See project.md 'Tech Stack' section for versions and .ai-rules/agents/code-quality-specialist.json for design pattern assessment"
     ],
     "specialist_agent_integration": {
@@ -433,6 +434,67 @@
           "action": "Verify behavior compatibility through tests"
         }
       }
+    },
+
+    "refactoring_review": {
+      "description": "자동화된 테스트 외 필수 수동 로직 검토 - 테스트 통과 ≠ 버그 없음",
+      "trigger": "모든 EVAL에서 실행 (스킵 가능)",
+      "philosophy": {
+        "core_principle": "테스트 통과 ≠ 버그 없음, 리팩토링 ≠ 안전",
+        "dangerous_assumptions": [
+          "파일 이동만 했으니 로직 변경 없음",
+          "테스트 통과했으니 기능 동일함",
+          "리팩토링은 정의상 안전함",
+          "기존 코드니까 검증된 것임"
+        ],
+        "required_evidence": "위 가정을 하려면 실제 코드 검토 증거 필수"
+      },
+      "checklist": {
+        "conditional_branches": {
+          "description": "if/else, 삼항연산자, switch 각 분기 추적",
+          "question": "각 분기가 의도대로 동작하는가?",
+          "common_bugs": [
+            "조건 누락으로 특정 케이스만 처리",
+            "else 분기 미구현"
+          ]
+        },
+        "data_transformations": {
+          "description": "타입 변환 함수의 입출력 필드 매핑 확인",
+          "question": "모든 필드가 올바르게 매핑되는가?",
+          "common_bugs": ["필드 누락", "잘못된 기본값", "타입 불일치"]
+        },
+        "optional_handling": {
+          "description": "?, ??, || 연산자 의도된 fallback 검증",
+          "question": "옵셔널 체이닝이 의도한 fallback을 제공하는가?",
+          "common_bugs": ["null vs undefined 혼동", "빈 문자열/0 처리 오류"]
+        },
+        "dependency_completeness": {
+          "description": "DI 주입, import 경로 정확성",
+          "question": "이동된 파일의 모든 의존성이 올바르게 주입되었는가?",
+          "common_bugs": ["누락된 의존성", "잘못된 import 경로", "순환 참조"]
+        },
+        "edge_cases": {
+          "description": "null, undefined, 빈 배열, 경계값 처리",
+          "question": "경계 조건이 올바르게 처리되는가?",
+          "common_bugs": [
+            "빈 배열 처리 누락",
+            "null 참조 에러",
+            "경계값 off-by-one"
+          ]
+        }
+      },
+      "skip_conditions": ["신규 파일만 생성", "문서만 변경", "테스트만 추가"],
+      "pass_criteria": {
+        "minimum_checks": "변경된 코드에 해당하는 항목은 모두 검토해야 함",
+        "evidence_required": "각 항목별로 검토 결과(문제 발견 또는 검증 완료) 명시 필수",
+        "skip_justification": "스킵하는 경우 반드시 사유 명시"
+      },
+      "output_format": {
+        "structure": "발견된 문제 우선, 파일:라인 위치 필수",
+        "problem_format": "🔴 `file.ts:line` - [항목]: [문제 설명]",
+        "verified_format": "✅ [항목]: 검증 완료",
+        "skip_format": "*스킵 사유: [사유]*"
+      }
     }
   },
 
@@ -485,6 +547,14 @@
         "required": true
       },
 
+      "6.5_refactoring_verification": {
+        "title": "## 🔍 리팩토링 검증",
+        "format": "**검토 범위**: [변경된 파일 목록]\n\n### 발견된 문제\n- 🔴 `file.ts:line` - [항목]: [문제]\n\n### 검증 완료 (문제 없음)\n- ✅ [항목]\n\n*스킵 사유: [해당시]*",
+        "description": "자동화된 테스트 외 필수 수동 검토 - 조건 분기, 데이터 변환, 옵셔널 필드, 의존성, 엣지 케이스",
+        "skip_conditions": ["신규 파일만 생성", "문서만 변경", "테스트만 추가"],
+        "required": true
+      },
+
       "7_objective_assessment": {
         "title": "## Objective Assessment",
         "format": "| Criteria | Measured | Target | Status |\n|----------|----------|--------|--------|",

package/.ai-rules/agents/data-engineer.json

@@ -321,7 +321,7 @@
   },
 
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Start by understanding current schema state",
       "Read existing migrations and models",

package/.ai-rules/agents/devops-engineer.json

@@ -31,7 +31,7 @@
   "infrastructure": {
     "containerization": {
       "docker": {
-        "base_image": "node:lts-alpine (프로젝트 버전에 맞춤)",
+        "base_image": "node:lts-alpine (match project version)",
         "build_strategy": "Multi-stage (builder + runner)",
         "current_setup": {
           "builder_stage": "Build and compile Next.js application",
@@ -52,8 +52,8 @@
         ]
       },
       "nodejs": {
-        "version": "프로젝트 package.json의 engines 참조",
-        "package_manager": "프로젝트 설정에 맞춤",
+        "version": "Reference project package.json engines",
+        "package_manager": "Match project configuration",
         "memory": {
           "heap_size": "4GB (--max-old-space-size=4096)",
           "reason": "Prevents out-of-memory during Next.js builds",
@@ -69,7 +69,7 @@
 
     "monitoring": {
       "datadog": {
-        "service_name": "프로젝트 설정에 맞춤",
+        "service_name": "Match project configuration",
         "components": {
           "apm": {
             "description": "Application Performance Monitoring for backend tracing",
@@ -109,7 +109,7 @@
           }
         },
         "environment_variables": {
-          "DD_SERVICE": "프로젝트명 - Service name identifier",
+          "DD_SERVICE": "Project name - Service name identifier",
           "DD_VERSION": "APP_VERSION - Deployment version tracking",
           "DD_APM_ENABLED": "true - Enable APM tracing",
           "DD_LOGS_INJECTION": "true - Inject trace info in logs",
@@ -257,7 +257,7 @@
   ],
 
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Analyze current infrastructure state first",
       "Explain optimization opportunities clearly",

package/.ai-rules/agents/documentation-specialist.json

@@ -523,7 +523,7 @@
     }
   },
   "communication": {
-    "language": "Always respond in Korean (한국어)",
+    "language": "en",
     "approach": [
       "Start by understanding documentation context (planning/implementation/evaluation)",
       "Plan/review code comments for complex logic",