oh-my-customcode 0.1.2 → 0.1.4

package/templates/agents/orchestrator/secretary/refs/rules/MAY-optimization.md

@@ -0,0 +1,93 @@
+# [MAY] Optimization Guide
+
+> **Priority**: MAY - Optional
+> **Apply when**: Basic functionality is stable
+
+## Efficiency Optimization
+
+### Parallel Processing
+```
+Apply when:
+- 3+ independent tasks
+- Each task is I/O bound
+
+Example:
+- Read multiple files simultaneously
+- Run independent searches in parallel
+```
+
+### Caching
+```
+Apply when:
+- Same data accessed repeatedly
+- Data changes infrequently
+
+Example:
+- Cache file contents
+- Reuse search results
+```
+
+### Lazy Loading
+```
+Apply when:
+- Large datasets
+- Only portion actually used
+
+Example:
+- Read only needed files
+- Stream results
+```
+
+## Token Optimization
+
+### Context Management
+```
+✓ Include only necessary info
+✓ Remove duplicates
+✓ Use summaries
+```
+
+### Response Optimization
+```
+✓ Concise expressions
+✓ Minimize code blocks
+✓ Remove unnecessary repetition
+```
+
+## Task Optimization
+
+### Batch Processing
+```
+Group similar tasks together
+Example: Edit 10 files → Process at once
+```
+
+### Incremental Processing
+```
+Process only changed parts
+Example: Full build → Incremental build
+```
+
+## Apply Criteria
+
+### Do Optimize
+```
+✓ Repetitive tasks
+✓ Clear performance bottleneck
+✓ Measurable improvement
+```
+
+### Don't Optimize
+```
+✗ One-time tasks
+✗ Already fast enough
+✗ Complexity increase outweighs benefit
+```
+
+## Caution
+
+```
+⚠ Premature optimization is root of evil
+⚠ Readability > Optimization
+⚠ No optimization without measurement
+```

package/templates/agents/orchestrator/secretary/refs/rules/MUST-agent-design.md

@@ -0,0 +1,107 @@
+# [MUST] Agent Design Rules
+
+> **Priority**: MUST - Never violate
+> **ID**: R006
+
+## Agent Structure
+
+### Required Files
+```
+agents/{type}/{name}/
+├── AGENT.md          # Agent definition (REQUIRED)
+├── index.yaml        # Agent metadata (REQUIRED)
+└── refs/             # Symlinks to guides/skills (OPTIONAL)
+```
+
+### AGENT.md Must NOT Contain
+```
+✗ Detailed skill instructions (use skills/ instead)
+✗ Reference documentation (use guides/ instead)
+✗ Implementation scripts (use skills/scripts/ instead)
+```
+
+### AGENT.md Should Contain
+```
+✓ Agent purpose and role
+✓ Capabilities overview (not details)
+✓ Required skills (by reference)
+✓ Workflow description
+✓ Source info (if external)
+```
+
+## External Agent Requirements
+
+External agents (from GitHub, npm, etc.) MUST include:
+
+### index.yaml Fields
+```yaml
+metadata:
+  name: agent-name
+  type: worker | orchestrator
+  source:
+    type: external
+    origin: github | npm | other
+    url: https://github.com/org/repo
+    version: 1.0.0
+    last_updated: 2025-01-22
+    update_command: "npx add-skill org/repo"
+```
+
+### Update Tracking
+```
+- version: Current version installed
+- last_updated: Date of last sync
+- update_command: Command to update
+- changelog_url: Where to check updates
+```
+
+## Separation of Concerns
+
+### agents/
+```
+Purpose: Define WHAT the agent does
+Content: Role, capabilities, workflow
+NOT: How to do it (that's skills/)
+```
+
+### skills/
+```
+Purpose: Define HOW to do tasks
+Content: Instructions, scripts, rules
+Location: skills/{category}/{name}/
+```
+
+### guides/
+```
+Purpose: Reference documentation
+Content: Best practices, tutorials
+Location: guides/{topic}/
+```
+
+## Linking
+
+### Agent → Skills
+```yaml
+# In AGENT.md or index.yaml
+skills:
+  - category: development
+    name: react-best-practices
+    path: ../../../../skills/development/react-best-practices
+```
+
+### Agent → Guides
+```bash
+# Symlink in refs/
+ln -s ../../../../guides/web-design refs/web-design
+```
+
+## Naming Conventions
+
+| Type | Pattern | Example |
+|------|---------|---------|
+| Agent folder | `kebab-case` | `vercel-agent` |
+| Skill folder | `kebab-case` | `react-best-practices` |
+| Guide folder | `kebab-case` | `web-design` |
+| AGENT.md | UPPERCASE | `AGENT.md` |
+| SKILL.md | UPPERCASE | `SKILL.md` |
+| index.yaml | lowercase | `index.yaml` |

package/templates/agents/orchestrator/secretary/refs/rules/MUST-agent-identification.md

@@ -0,0 +1,108 @@
+# [MUST] Agent Identification Rules
+
+> **Priority**: MUST - ENFORCED, NO EXCEPTIONS
+> **ID**: R007
+> **Violation**: Immediate correction required
+
+## CRITICAL
+
+**EVERY response MUST start with agent identification. This is NON-NEGOTIABLE.**
+
+Failure to include agent identification = Rule violation = Must be corrected immediately.
+
+## Purpose
+
+Display which agent is responding and which skills are being used for transparency and traceability.
+
+## Response Header Format
+
+Every response MUST start with an agent identification block:
+
+```
+┌─ Agent: {agent-name} ({agent-type})
+├─ Skill: {skill-name} (if applicable)
+└─ Task: {brief-task-description}
+```
+
+## Examples
+
+### Single Agent Response
+```
+┌─ Agent: creator (manager)
+└─ Task: Creating new agent
+
+[Response content...]
+```
+
+### With Skill Usage
+```
+┌─ Agent: vercel-agent (worker)
+├─ Skill: react-best-practices
+└─ Task: Optimizing React component
+
+[Response content...]
+```
+
+### Multiple Skills
+```
+┌─ Agent: vercel-agent (worker)
+├─ Skills: react-best-practices, web-design-guidelines
+└─ Task: Full code review
+
+[Response content...]
+```
+
+### No Specific Agent (Default)
+```
+┌─ Agent: claude (default)
+└─ Task: General assistance
+
+[Response content...]
+```
+
+## When to Display
+
+| Situation | Display |
+|-----------|---------|
+| Agent-specific task | Full header with agent |
+| Using skill | Include skill name |
+| General conversation | "claude (default)" |
+| Multiple agents | Show primary agent |
+
+## Agent Types
+
+| Type | Symbol | Example |
+|------|--------|---------|
+| manager | 🔧 | creator, updater |
+| worker | ⚙️ | vercel-agent |
+| orchestrator | 🎯 | (future) |
+| default | 💬 | claude |
+
+## Simplified Format (Optional)
+
+For brief responses, use inline format:
+
+```
+[creator] Creating agent structure...
+```
+
+Or with skill:
+
+```
+[vercel-agent → react-best-practices] Analyzing performance...
+```
+
+## Status Updates
+
+During long tasks, show progress with agent context:
+
+```
+┌─ Agent: updater (manager)
+└─ Task: Checking external updates
+
+[Progress] Scanning agents/index.yaml (1/3)
+[Progress] Scanning skills/index.yaml (2/3)
+[Progress] Scanning guides/index.yaml (3/3)
+
+[Done] Found 2 updates available
+```

package/templates/agents/orchestrator/secretary/refs/rules/MUST-continuous-improvement.md

@@ -0,0 +1,132 @@
+# [MUST] Continuous Improvement Rules
+
+> **Priority**: MUST - Top-level enforcement
+> **ID**: R016
+> **Trigger**: User points out rule violation
+
+## CRITICAL
+
+**When user points out a rule violation, you MUST update the rules to prevent future violations BEFORE continuing with the task.**
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  WHEN USER POINTS OUT A VIOLATION:                               ║
+║                                                                   ║
+║  1. STOP current task immediately                                ║
+║  2. UPDATE the relevant rule to be clearer/stronger              ║
+║  3. COMMIT the rule update                                       ║
+║  4. THEN continue with the original task                         ║
+║                                                                   ║
+║  DO NOT just apologize and continue.                             ║
+║  DO NOT promise to do better next time.                          ║
+║  ACTUALLY UPDATE THE RULES.                                      ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
+## Workflow
+
+```
+User points out violation
+         │
+         ▼
+┌─────────────────────────┐
+│ 1. Acknowledge violation │
+└───────────┬─────────────┘
+            │
+            ▼
+┌─────────────────────────┐
+│ 2. Identify root cause   │
+│    - Which rule was weak?│
+│    - What was unclear?   │
+└───────────┬─────────────┘
+            │
+            ▼
+┌─────────────────────────┐
+│ 3. Update the rule       │
+│    - Add clarity         │
+│    - Add examples        │
+│    - Add self-checks     │
+└───────────┬─────────────┘
+            │
+            ▼
+┌─────────────────────────┐
+│ 4. Commit the change     │
+└───────────┬─────────────┘
+            │
+            ▼
+┌─────────────────────────┐
+│ 5. Continue original task│
+│    (now following rules) │
+└─────────────────────────┘
+```
+
+## Examples
+
+### Example 1: Parallel Execution Violation
+
+```
+User: "병렬 실행을 안 지킨거 아닌가?"
+
+WRONG Response:
+  "맞습니다, 죄송합니다. 다음부터 잘 지키겠습니다."
+  [continues task without updating rules]
+
+CORRECT Response:
+  1. "맞습니다. R009 위반입니다."
+  2. [Updates MUST-parallel-execution.md with clearer guidance]
+  3. [Commits the update]
+  4. [Continues task with proper parallel execution]
+```
+
+### Example 2: Wrong Agent Used
+
+```
+User: "creator 에이전트를 써야 하는거 아닌가?"
+
+WRONG Response:
+  "맞습니다. creator를 사용하겠습니다."
+  [continues without updating rules]
+
+CORRECT Response:
+  1. "맞습니다. R010 위반입니다."
+  2. [Updates relevant rules to clarify agent delegation]
+  3. [Commits the update]
+  4. [Continues with proper agent delegation]
+```
+
+## Why This Matters
+
+```
+Without rule updates:
+  Violation → Apology → Same mistake later → Apology → ...
+
+With rule updates:
+  Violation → Rule improvement → Better behavior → Learning preserved
+```
+
+1. **Institutional Memory**: Rules capture learnings permanently
+2. **Prevents Recurrence**: Clearer rules = fewer future violations
+3. **Continuous Improvement**: System gets better over time
+4. **Accountability**: Actions, not just words
+
+## Integration with Other Rules
+
+This rule takes precedence when violations are pointed out:
+
+| Situation | Action |
+|-----------|--------|
+| User points out violation | STOP → Update rule → Continue |
+| Self-detected violation | Fix immediately, consider rule update |
+| Ambiguous situation | Ask user, then update if needed |
+
+## Enforcement
+
+```
+Violation of this rule = Ignoring user feedback = Unacceptable
+
+When caught violating this rule:
+1. Stop immediately
+2. Update THIS rule to be even clearer
+3. Update the ORIGINAL violated rule
+4. Continue with proper behavior
+```

package/templates/agents/orchestrator/secretary/refs/rules/MUST-intent-transparency.md

@@ -0,0 +1,199 @@
+# [MUST] Intent Transparency Rules
+
+> **Priority**: MUST - Required for user control
+> **ID**: R015
+
+## Purpose
+
+Ensure transparency when automatically detecting user intent and routing to agents. Users should always understand why a specific agent was chosen.
+
+## Detection Display (REQUIRED)
+
+When intent is detected, display the reasoning:
+
+```
+[Intent Detected]
+├── Input: "{user input}"
+├── Agent: {detected-agent}
+├── Confidence: {percentage}%
+└── Reason: {explanation}
+```
+
+## Confidence Thresholds
+
+| Confidence | Action |
+|------------|--------|
+| >= 90% | Auto-execute with display |
+| 70-89% | Request confirmation |
+| < 70% | List options for user to choose |
+
+## Detection Factors
+
+Intent is detected using multiple factors:
+
+```yaml
+factors:
+  keywords:
+    weight: 40
+    description: Language-specific keywords in input
+    example: "Go", "Python", "리뷰", "생성"
+
+  file_patterns:
+    weight: 30
+    description: File extensions mentioned or in context
+    example: "*.go", "main.py"
+
+  action_verbs:
+    weight: 20
+    description: Action words in user input
+    example: "review", "create", "fix", "리뷰", "생성"
+
+  context:
+    weight: 10
+    description: Recent conversation context
+    example: Previous agent used, current working directory
+```
+
+## High Confidence Display (>= 90%)
+
+```
+[Intent Detected]
+├── Input: "Go 코드 리뷰해줘"
+├── Agent: golang-expert
+├── Confidence: 95%
+└── Reason: "Go" keyword (40%) + "리뷰" action verb (55%)
+
+Executing...
+```
+
+## Medium Confidence Display (70-89%)
+
+```
+[Intent Detected]
+├── Input: "백엔드 코드 체크해줘"
+├── Agent: go-backend-expert (?)
+├── Confidence: 75%
+└── Reason: "백엔드" keyword (40%) + "체크" action (35%)
+
+Possible alternatives:
+  1. go-backend-expert (75%)
+  2. fastapi-expert (65%)
+  3. springboot-expert (60%)
+
+Proceed with go-backend-expert? [Y/n/1-3]
+```
+
+## Low Confidence Display (< 70%)
+
+```
+[Intent Unclear]
+├── Input: "이 코드 좀 봐줘"
+├── Confidence: < 70%
+└── Need more context
+
+Available agents for code review:
+  1. golang-expert (Go files)
+  2. python-expert (Python files)
+  3. typescript-expert (TypeScript files)
+  4. rust-expert (Rust files)
+
+Which agent should review the code? [1-4]
+```
+
+## Override Syntax
+
+Users can explicitly specify an agent:
+
+```
+@{agent-name} {command}
+```
+
+Examples:
+```
+@golang-expert review this code
+@python-expert src/main.py 분석해줘
+@secretary create a new agent
+```
+
+Override bypasses intent detection:
+
+```
+[Override] Agent explicitly specified: python-expert
+Executing...
+```
+
+## Implementation
+
+### Secretary Workflow
+
+```
+1. Receive user input
+2. Check for explicit override (@agent)
+3. If no override:
+   a. Extract keywords, file patterns, action verbs
+   b. Match against agent triggers
+   c. Calculate confidence score
+   d. Display detection reasoning
+   e. Execute or request confirmation based on threshold
+4. Route to selected agent
+```
+
+### Detection Log
+
+For debugging and transparency:
+
+```yaml
+detection_log:
+  input: "Go 코드 리뷰해줘"
+  extracted:
+    keywords: ["Go"]
+    file_patterns: []
+    action_verbs: ["리뷰"]
+  matches:
+    - agent: golang-expert
+      score: 95
+      breakdown:
+        keyword_go: 40
+        action_review: 40
+        context: 15
+  selected: golang-expert
+  confidence: 95%
+```
+
+## Agent Triggers
+
+Each agent has defined triggers in:
+`skills/orchestration/intent-detection/patterns/agent-triggers.yaml`
+
+```yaml
+agents:
+  golang-expert:
+    keywords: [go, golang, "go 언어"]
+    file_patterns: ["*.go", "go.mod", "go.sum"]
+    actions: [review, analyze, fix, optimize]
+    base_confidence: 40
+
+  python-expert:
+    keywords: [python, py, "파이썬"]
+    file_patterns: ["*.py", "requirements.txt", "pyproject.toml"]
+    actions: [review, analyze, fix, optimize]
+    base_confidence: 40
+```
+
+## Benefits
+
+1. **Transparency**: Users understand agent selection
+2. **Control**: Users can override or choose alternatives
+3. **Trust**: Clear reasoning builds user confidence
+4. **Learning**: Users learn which agents handle what
+5. **Debugging**: Clear logs for troubleshooting
+
+## Violations
+
+Proceeding without displaying intent reasoning = Rule violation
+
+The user must always know:
+- Which agent was selected
+- Why it was selected
+- What confidence level
+- How to override if needed

package/templates/agents/orchestrator/secretary/refs/rules/MUST-language-policy.md

@@ -0,0 +1,62 @@
+# [MUST] Language & Delegation Policy
+
+> **Priority**: MUST - Never violate
+> **ID**: R000
+
+## Core Principles
+
+### 1. User Input Language
+```
+User prompts are in Korean.
+Always understand and process Korean input.
+```
+
+### 2. Output Language
+
+| Context | Language | Example |
+|---------|----------|---------|
+| User communication | Korean | 상태 보고, 질문, 설명 |
+| Code | English | variables, functions, comments |
+| File contents | English | .md, .yaml, configs |
+| Commit messages | English | git commits |
+| Error messages to user | Korean | 에러 설명, 해결 방안 |
+
+### 3. Delegation Model
+```
+User does NOT directly edit files.
+User delegates ALL file operations to AI agent.
+
+User → (Korean prompt) → Agent → (file operations)
+```
+
+### 4. Context Efficiency
+```
+All file contents in English for:
+- Token efficiency
+- Consistent parsing
+- Universal compatibility
+```
+
+## Examples
+
+### Correct
+```
+User: "새로운 에이전트를 만들어줘"
+Agent: "에이전트를 생성하겠습니다." (Korean to user)
+Agent writes AGENT.md in English
+```
+
+### Incorrect
+```
+Agent writes: "# 에이전트 이름" in file  ← Wrong
+Agent writes: "# Agent Name" in file     ← Correct
+```
+
+## File Naming
+
+| Type | Convention | Example |
+|------|------------|---------|
+| Rules | `{PRIORITY}-{name}.md` | `MUST-safety.md` |
+| Agents | `AGENT.md` | - |
+| Skills | `SKILL.md` | - |
+| Index | `index.yaml` | - |