codingbuddy-rules 2.1.0 → 2.2.1

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

@@ -50,7 +50,7 @@ See full workflow details in `.ai-rules/rules/core.md`
 
 #### Tech Stack
 
-프로젝트의 `package.json`을 참조하세요.
+See project `package.json`.
 
 #### Project Structure
 ```
@@ -126,7 +126,7 @@ Antigravity uses artifact files for:
 
 ### Communication
 
-- **Always respond in Korean (한국어)** as specified in common rules
+- **Follow project's configured language setting**
 - Use structured markdown formatting
 - Provide clear, actionable feedback
 
@@ -161,7 +161,7 @@ When working with Antigravity, it automatically has access to:
 ### Workflow Example
 
 ```
-User: 새로운 뉴스레터 기능 만들어줘
+User: Build a new newsletter feature
 
 AI: # Mode: PLAN
     ## 📋 Plan Overview
@@ -187,6 +187,86 @@ AI: # Mode: EVAL
 - ✅ Access to all specialist agent knowledge
 - ✅ Easy to update: change `.ai-rules/` once, all tools benefit
 
+## 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
+
+```
+User: AUTO Build a new payment system feature
+
+AI: # Mode: AUTO (Iteration 1/3)
+    ## Phase: PLAN
+    [Following .ai-rules/rules/core.md workflow]
+
+    ## Phase: ACT
+    [Execute with .ai-rules guidelines]
+
+    ## Phase: EVAL
+    [Evaluate with quality criteria]
+
+    ### Quality Status
+    - Critical: 0
+    - High: 0
+
+    ✅ AUTO mode completed successfully!
+```
+
+### 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)
+
+### Antigravity-Specific Integration
+
+AUTO mode works with Antigravity's task boundary tracking:
+
+```python
+task_boundary(
+  TaskName="AUTO: Feature Implementation",
+  Mode="AUTO_ITERATION",
+  TaskSummary="Iteration 1/3 - PLAN phase completed",
+  TaskStatus="Executing ACT phase",
+  PredictedTaskSize=30
+)
+```
+
+### 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
+- Bug fixes needing comprehensive testing
+- Code quality improvements with measurable criteria
+
 ## Maintenance
 
 When updating rules:

package/.ai-rules/adapters/claude-code.md

@@ -6,6 +6,42 @@ This guide explains how to use the common AI rules (`.ai-rules/`) in Claude Code
 
 Claude Code uses the `.claude/` directory for project-specific custom instructions, referencing the common rules from `.ai-rules/`.
 
+## 🆕 Code Conventions Support
+
+CodingBuddy now automatically enforces project code conventions from config files:
+
+### Available MCP Tool
+
+**`get_code_conventions`**: Parses and exposes project conventions from:
+- `tsconfig.json` - TypeScript strict mode, compiler options
+- `eslint.config.js` / `.eslintrc.json` - Linting rules
+- `.prettierrc` - Formatting rules (quotes, semicolons, indentation)
+- `.editorconfig` - Editor settings (indent style/size, line endings, charset)
+- `.markdownlint.json` - Markdown linting rules
+
+### When to Use
+
+**ACT Mode**: Call `get_code_conventions` before implementing to verify code follows project conventions.
+
+**EVAL Mode**: The `conventions` checklist domain is automatically included in code reviews.
+
+### Example Usage
+
+```typescript
+// In ACT mode
+const conventions = await get_code_conventions();
+
+// Verify TypeScript strict mode
+if (conventions.typescript.strict) {
+  // Ensure no implicit any types
+}
+
+// Check Prettier formatting
+if (conventions.prettier.singleQuote) {
+  // Use single quotes
+}
+```
+
 ## Integration Method
 
 ### 1. Create Claude Configuration
@@ -27,7 +63,7 @@ See `.ai-rules/rules/core.md` for:
 
 ### Project Context
 See `.ai-rules/rules/project.md` for:
-- Tech stack (프로젝트의 package.json 참조)
+- Tech stack (see project package.json)
 - Project structure (app → widgets → features → entities → shared)
 - Development rules and file naming conventions
 - Domain knowledge
@@ -44,7 +80,7 @@ See `.ai-rules/agents/README.md` for available specialist agents and their exper
 
 ## Claude Code Specific
 
-- Always respond in Korean (한국어)
+- Follow project's configured language setting
 - Use structured markdown formatting
 - Provide clear, actionable feedback
 - Reference project context from `.ai-rules/rules/project.md`
@@ -85,7 +121,7 @@ See `.ai-rules/agents/README.md` for available specialist agents and their exper
 ### In Claude Chat
 
 ```
-User: 새로운 기능 만들어줘
+User: Build a new feature
 
 Claude: # Mode: PLAN
         [Following .ai-rules/rules/core.md workflow]
@@ -198,7 +234,7 @@ Specialist agents can be invoked by any Primary Agent as needed:
 
 1. **PLAN mode**: Always uses `solution-architect` or `technical-planner` based on prompt analysis
 2. **ACT mode**: Resolution priority:
-   1. Explicit agent request in prompt (e.g., "backend-developer로 작업해")
+   1. Explicit agent request in prompt (e.g., "work with backend-developer")
    2. `recommended_agent` parameter (from PLAN mode recommendation)
    3. Tooling pattern matching (config files, build tools → `tooling-engineer`)
    4. Project configuration (`primaryAgent` setting)
@@ -321,22 +357,22 @@ The `parse_mode` MCP tool returns this field to recommend parallel specialist ex
 ### Parallel Execution Workflow
 
 ```
-parse_mode 호출
+Call parse_mode
      ↓
-parallelAgentsRecommendation 확인
-     ↓ (있으면)
-사용자에게 시작 메시지 표시
+Check parallelAgentsRecommendation
+     ↓ (if exists)
+Display start message to user
      ↓
-prepare_parallel_agents MCP 호출
+Call prepare_parallel_agents MCP
      ↓
-반환된 각 agent.taskPrompt를 Task tool로 병렬 호출:
+Call each agent.taskPrompt via Task tool in parallel:
   - subagent_type: "general-purpose"
   - run_in_background: true
   - prompt: agent.taskPrompt
      ↓
-TaskOutput으로 결과 수집
+Collect results with TaskOutput
      ↓
-사용자에게 결과 종합하여 표시
+Display consolidated results to user
 ```
 
 ### Code Example
@@ -368,7 +404,7 @@ if (parseModeResult.parallelAgentsRecommendation) {
       prompt: agent.taskPrompt,
       description: agent.description,
       run_in_background: true,
-      model: "haiku" // Use haiku for efficiency
+      model: "opus" // Use opus for thorough analysis
     })
   );
 
@@ -450,3 +486,93 @@ Each workflow mode activates different specialist agents:
 - **EVAL mode**: Security, accessibility, performance, and code quality specialists provide comprehensive review
 
 **Important:** Specialists from one mode do NOT carry over to the next mode. Each mode has its own recommended specialist set.
+
+## AUTO Mode
+
+AUTO mode enables autonomous iteration through PLAN -> ACT -> EVAL cycles 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 implement user authentication with JWT tokens
+```
+
+```
+자동 사용자 인증 기능을 JWT로 구현해줘
+```
+
+### Expected Behavior
+
+1. **Initial PLAN**: Creates implementation plan with quality criteria
+2. **ACT Iteration**: Executes implementation following TDD workflow
+3. **EVAL Check**: Evaluates quality against exit criteria
+4. **Loop or Exit**:
+   - If quality met (Critical=0, High=0): Exits with success summary
+   - If max iterations reached: Exits with failure summary and remaining issues
+   - Otherwise: Returns to PLAN with improvement focus
+
+### Exit Criteria
+
+- **Success**: `Critical = 0 AND High = 0` severity issues
+- **Failure**: Max iterations reached (default: 3, configurable via `auto.maxIterations`)
+
+### Configuration
+
+Configure AUTO mode in `codingbuddy.config.js`:
+
+```javascript
+module.exports = {
+  auto: {
+    maxIterations: 3  // Default: 3
+  }
+};
+```
+
+### AUTO Mode Output Format
+
+```
+# Mode: AUTO (Iteration 1/3)
+
+## Phase: PLAN
+[Planning content...]
+
+## Phase: ACT
+[Implementation content...]
+
+## Phase: EVAL
+[Evaluation content...]
+
+### Quality Status
+- Critical: 0
+- High: 0
+
+✅ AUTO mode completed successfully!
+```
+
+### When to Use AUTO Mode
+
+- **Large feature implementations** that require multiple refinement cycles
+- **Complex refactoring** where quality verification is critical
+- **Bug fixes** that need comprehensive testing and validation
+- **Code quality improvements** with measurable success criteria
+
+### Differences from Manual Mode Flow
+
+| Aspect | Manual Mode | AUTO Mode |
+|--------|-------------|-----------|
+| Transition | User triggers each mode | Automatic cycling |
+| Iterations | Single pass per mode | Multiple cycles until quality met |
+| Exit | User decides completion | Quality criteria or max iterations |
+| Intervention | Required for each step | Only when requested or on failure |

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

@@ -147,3 +147,60 @@ Skills are located in `.ai-rules/skills/`. To use a skill:
 - `subagent-driven-development` - In-session plan execution
 - `dispatching-parallel-agents` - Handle parallel tasks
 - `frontend-design` - Build production-grade UI
+
+## 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 implement user authentication with JWT
+```
+
+### 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)
+
+### Copilot Integration
+
+When using GitHub Copilot Chat with AUTO mode:
+- Copilot references `.ai-rules/rules/core.md` for workflow
+- Applies `.ai-rules/rules/augmented-coding.md` TDD principles
+- Uses project structure from `.ai-rules/rules/project.md`
+
+### 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
+- Bug fixes needing comprehensive testing
+- Code quality improvements with measurable criteria

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

@@ -166,6 +166,62 @@ This project uses codingbuddy MCP server to manage AI Agents.
 
 See `AGENTS.md` in project root for details.
 
+## 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 implement user authentication feature
+```
+
+```
+자동 사용자 인증 기능 구현해줘
+```
+
+When AUTO keyword is detected, Cursor calls `parse_mode` MCP tool which returns AUTO mode instructions.
+
+### 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)
+
+### 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
+- Bug fixes needing comprehensive testing
+- Code quality improvements with measurable criteria
+
 ## Reference
 
 - [AGENTS.md Official Spec](https://agents.md)

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

@@ -29,7 +29,7 @@ See `.ai-rules/rules/core.md` for:
 ### Project Context
 
 See `.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)
 - **Conventions**: File naming, import/export rules, pure/impure function separation
 
@@ -56,7 +56,7 @@ See `.ai-rules/agents/` for domain expertise:
 [Add Kiro-specific customizations here]
 
 ### Communication
-- Always respond in Korean (한국어)
+- Follow project's configured language setting
 - Use clear, structured markdown formatting
 - Provide actionable, specific feedback
 ```
@@ -85,7 +85,7 @@ See `.ai-rules/agents/` for domain expertise:
 ### In Kiro Session
 
 ```
-User: 새로운 컴포넌트 구현해줘
+User: Build a new component
 
 Kiro: # Mode: PLAN
       [Follows .ai-rules/rules/core.md workflow]
@@ -122,9 +122,75 @@ Kiro will generate code following:
 2. Update `.kiro/rules/guidelines.md` only for Kiro-specific features
 3. Common rules propagate automatically to all Kiro sessions
 
+## 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
+
+```
+User: AUTO 새로운 컴포넌트 구현해줘
+
+Kiro: # Mode: AUTO (Iteration 1/3)
+      ## Phase: PLAN
+      [Follows .ai-rules/rules/core.md workflow]
+
+      ## Phase: ACT
+      [Executes with quality standards from .ai-rules]
+
+      ## Phase: EVAL
+      [Evaluates against quality criteria]
+
+      ### Quality Status
+      - Critical: 0
+      - High: 0
+
+      ✅ AUTO mode completed successfully!
+```
+
+### 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)
+
+### 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
+- Bug fixes needing comprehensive testing
+- Code quality improvements with measurable criteria
+
 ## Getting Started
 
 1. Ensure `.ai-rules/` directory exists with all common rules
 2. Create `.kiro/rules/guidelines.md` with content above
 3. Start a Kiro session - it will automatically reference common rules
-4. Use PLAN/ACT/EVAL workflow as defined in `.ai-rules/rules/core.md`
+4. Use PLAN/ACT/EVAL/AUTO workflow as defined in `.ai-rules/rules/core.md`

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

@@ -50,24 +50,24 @@ OpenCode/Crush supports Agent Skills standard for structured AI capabilities. Th
 ### 1. Direct Skill Invocation
 ```bash
 # In OpenCode CLI
-/skill brainstorming "새로운 기능 아이디어"
-/skill tdd "사용자 인증 구현"
-/skill debug "로그인 버그 해결"
+/skill brainstorming "new feature ideas"
+/skill tdd "user authentication implementation"
+/skill debug "fix login bug"
 ```
 
 ### 2. Agent + Skill Combination
 ```bash
 # Planning with brainstorming skill
 /agent plan
-/skill brainstorming "대시보드 UI 개선"
+/skill brainstorming "improve dashboard UI"
 
-# Implementation with TDD skill  
+# Implementation with TDD skill
 /agent build
-/skill tdd "API 연동 구현"
+/skill tdd "implement API integration"
 
 # Review with debugging skill
 /agent reviewer
-/skill debug "성능 이슈 분석"
+/skill debug "analyze performance issues"
 ```
 
 ### 3. Automatic Skill Recommendation
@@ -76,9 +76,9 @@ OpenCode can automatically recommend skills based on prompts using the `recommen
 
 ```typescript
 // Auto-triggered when user enters certain keywords
-"버그가 있어" → recommends: systematic-debugging
-"계획을 세워줘" → recommends: writing-plans  
-"UI를 만들어줘" → recommends: frontend-design
+"there's a bug" → recommends: systematic-debugging
+"create a plan" → recommends: writing-plans
+"build the UI" → recommends: frontend-design
 ```
 
 ## Skill Conversion Process
@@ -201,20 +201,20 @@ The MCP server handles Korean→English skill name mapping automatically.
 /agent plan
 
 # Use brainstorming skill
-/skill brainstorming "사용자 대시보드 개선"
+/skill brainstorming "improve user dashboard"
 
 # Generate implementation plan
-계획을 세워줘
+Create a plan for me
 ```
 
 ### Implementing with TDD
 
-```bash  
+```bash
 # Switch to build agent
 /agent build
 
 # Load TDD skill
-/skill test-driven-development "로그인 API 구현"
+/skill test-driven-development "implement login API"
 
 # Start TDD cycle
 ACT
@@ -224,10 +224,10 @@ ACT
 
 ```bash
 # Use systematic debugging
-/skill systematic-debugging "로그인 후 화면이 안 나와"
+/skill systematic-debugging "screen not showing after login"
 
 # Apply debugging methodology
-디버깅해줘
+Debug this for me
 ```
 
 ## Benefits