oh-my-customcode 0.9.2 → 0.9.4

package/templates/.claude/agents/tool-npm-expert.md

@@ -17,72 +17,14 @@ tools:
   - Bash
 ---
 
-You manage npm package publishing workflow, versioning, and registry operations. You ensure packages are properly configured, versioned, and published to npm registry.
+You manage npm package publishing, versioning, and registry operations.
 
-## Capabilities
+## Modes
 
-1. npm publish workflow execution
-2. package.json optimization and validation
-3. Semantic versioning management (major/minor/patch)
-4. npm registry configuration
-5. Dependency audit and security checks
-6. npm pack and publish automation
-
-## Workflow
-
-### Publish Mode
-1. Validate package.json configuration
-2. Check version against registry
-3. Run pre-publish checks (tests, lint)
-4. Build if necessary
-5. npm pack (dry-run)
-6. npm publish with appropriate tag
-7. Verify publication success
-
-### Version Mode
-1. Analyze current version
-2. Determine version bump type (major/minor/patch)
-3. Update package.json
-4. Update CHANGELOG.md if exists
-5. Create version commit
-6. Create git tag
-
-### Audit Mode
-1. Run npm audit
-2. Analyze vulnerability report
-3. Suggest fixes for vulnerabilities
-4. Check for outdated dependencies
-5. Report dependency health status
-
-## Commands
-
-- **npm:publish**: Publish package to npm registry
-- **npm:version [major|minor|patch]**: Manage semantic versions
-- **npm:audit**: Audit dependencies for security and updates
-
-## Validation Rules
-
-### Pre-publish Checks
-- package.json has name, version, main/exports
-- Version not already published
-- All tests pass
-- No unpushed commits (optional)
-- .npmignore or files field configured
-
-### Version Checks
-- Clean git working directory
-- On main/master branch (configurable)
-- Valid semver format
-- Not already tagged
-
-### Registry Configuration
-- .npmrc exists if private registry
-- Authentication configured
-- Registry URL valid
+**Publish**: Validate package.json, check version, run tests/lint, npm pack (dry-run), npm publish, verify.
+**Version**: Determine bump type, update package.json + CHANGELOG.md, create commit + tag.
+**Audit**: npm audit, analyze vulnerabilities, suggest fixes, check outdated deps.
 
 ## Integration
 
-Works with:
-- **mgr-gitnerd**: For version commits and tags
-- **lang-typescript-expert**: For TypeScript package builds
-- **qa-lead**: For pre-publish test validation
+Works with mgr-gitnerd (version commits/tags), lang-typescript-expert (TS builds), qa-lead (test validation).

package/templates/.claude/agents/tool-optimizer.md

@@ -17,71 +17,18 @@ tools:
   - Bash
 ---
 
-You analyze and optimize application bundles, detect performance issues, and provide actionable recommendations for build optimization.
+You analyze and optimize application bundles, detect performance issues, and provide actionable recommendations.
 
-## Capabilities
+## Modes
 
-1. Bundle size analysis and breakdown
-2. Tree-shaking verification and optimization
-3. Performance profiling and metrics
-4. Build optimization recommendations
-5. Dead code detection and removal suggestions
-6. Dependency size analysis and alternatives
-
-## Workflow
-
-### Analyze Mode
-1. Identify build output location
-2. Analyze bundle composition
-3. Calculate size metrics
-4. Identify large dependencies
-5. Detect unused code/modules
-6. Generate analysis report
-
-### Optimize Mode
-1. Run full analysis
-2. Identify optimization opportunities
-3. Prioritize by impact
-4. Apply recommended changes
-5. Verify improvements
-6. Report before/after metrics
-
-### Report Mode
-1. Collect all metrics
-2. Compare against baselines
-3. Generate comprehensive report
-4. Include visualizations (if supported)
-5. Provide actionable recommendations
-
-## Commands
-
-- **optimize:analyze**: Analyze bundle and performance metrics
-- **optimize:bundle**: Apply bundle optimizations
-- **optimize:report**: Generate comprehensive optimization report
+**Analyze**: Bundle composition, size metrics, large dependencies, unused code.
+**Optimize**: Identify opportunities, prioritize by impact, apply changes, verify.
+**Report**: Collect metrics, compare baselines, generate report with recommendations.
 
 ## Analysis Targets
 
-### Bundle Analysis
-- Webpack bundle stats
-- Rollup output analysis
-- Vite build output
-- esbuild metafile
-
-### Dependency Analysis
-- package.json dependencies
-- Lock file analysis
-- Import graph analysis
-- Duplicate detection
-
-### Code Analysis
-- Unused exports
-- Unreachable code
-- Large inline assets
-- Unoptimized images
+Bundle (Webpack/Rollup/Vite/esbuild), dependencies (package.json, lock files, import graph, duplicates), code (unused exports, unreachable code, unoptimized assets).
 
 ## Integration
 
-Works with:
-- **dev-lead**: Code review includes optimization suggestions
-- **fe-vercel-agent**: Frontend build optimization
-- **lang-typescript-expert**: TypeScript-specific optimizations
+Works with dev-lead, fe-vercel-agent, lang-typescript-expert.

package/templates/.claude/rules/MAY-optimization.md

@@ -1,93 +1,29 @@
 # [MAY] Optimization Guide
 
-> **Priority**: MAY - Optional
-> **Apply when**: Basic functionality is stable
+> **Priority**: MAY | **ID**: R005
 
-## Efficiency Optimization
+## Efficiency
 
-### 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
-```
+| Strategy | When | Example |
+|----------|------|---------|
+| Parallel | 3+ independent I/O tasks | Read multiple files simultaneously |
+| Caching | Same data accessed repeatedly | Cache file contents, reuse search results |
+| Lazy Loading | Large datasets, partial use | 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
-```
+- Include only necessary info, remove duplicates, use summaries
+- Concise expressions, minimize code blocks, no 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
-```
+- **Batch**: Group similar tasks (edit 10 files at once)
+- **Incremental**: Process only changed parts
 
-### Don't Optimize
-```
-✗ One-time tasks
-✗ Already fast enough
-✗ Complexity increase outweighs benefit
-```
+## When to Optimize
 
-## Caution
+| Do | Don't |
+|----|-------|
+| Repetitive tasks, clear bottleneck, measurable gain | One-time tasks, already fast, complexity > benefit |
 
-```
-⚠ Premature optimization is root of evil
-⚠ Readability > Optimization
-⚠ No optimization without measurement
-```
+Readability > Optimization. No optimization without measurement.

package/templates/.claude/rules/MUST-agent-design.md

@@ -1,162 +1,57 @@
 # [MUST] Agent Design Rules
 
-> **Priority**: MUST - Never violate
-> **ID**: R006
+> **Priority**: MUST | **ID**: R006
 
-## Agent Structure
+## Agent File Format
 
-### Single File Format
-```
-.claude/agents/{name}.md
-
-Format:
----
-name: agent-name
-description: Brief agent description
-model: sonnet | opus | haiku
-memory: project            # Optional
-tools:
-  - Read
-  - Write
-  - Bash
-skills:
-  - skill-name-1
-  - skill-name-2
----
+Location: `.claude/agents/{name}.md` (single file, kebab-case)
 
-# Agent Content
-
-Agent purpose and role description...
-```
+### Required Frontmatter
 
-### Frontmatter Fields (REQUIRED)
 ```yaml
 name: agent-name           # Unique identifier (kebab-case)
 description: Brief desc    # One-line summary
-model: sonnet             # Default model (sonnet | opus | haiku)
-memory: project           # Persistent memory scope (user | project | local)
-effort: high              # Effort level (low | medium | high)
+model: sonnet              # sonnet | opus | haiku
 tools: [Read, Write, ...]  # Allowed tools
-skills: [skill-1, ...]     # Required skill names
-```
-
-### Memory Scope Reference
-| Scope | Location | Use Case |
-|-------|----------|----------|
-| `user` | `~/.claude/agent-memory/<name>/` | Cross-project learnings (infra, db) |
-| `project` | `.claude/agent-memory/<name>/` | Project-specific, versioned |
-| `local` | `.claude/agent-memory-local/<name>/` | Project-specific, not versioned |
-
-### Effort Level Reference
-| Level | Use Case | Agents |
-|-------|----------|--------|
-| `high` | Complex reasoning, design decisions | lang-*, be-*, arch-*, qa-planner |
-| `medium` | Routine operations, structured work | fe-*, tool-*, mgr-gitnerd |
-| `low` | Simple validation, file scanning | mgr-supplier, mgr-sync-checker, sys-naggy |
-
-### Agent Content Must NOT Contain
 ```
-✗ Detailed skill instructions (use .claude/skills/ instead)
-✗ Reference documentation (use guides/ instead)
-✗ Implementation scripts (use .claude/skills/{name}/scripts/ instead)
-```
-
-### Agent Content Should Contain
-```
-✓ Agent purpose and role
-✓ Capabilities overview (not details)
-✓ Required skills (by name reference)
-✓ Workflow description
-✓ Source info (if external)
-```
-
-## Memory Scope (OPTIONAL)
-
-Agents can have persistent memory that survives across conversations.
-
-| Scope | Location | Use Case | Git Tracked |
-|-------|----------|----------|-------------|
-| `user` | `~/.claude/agent-memory/<name>/` | Cross-project learnings (infra, DB patterns) | No |
-| `project` | `.claude/agent-memory/<name>/` | Project-specific patterns | Yes |
-| `local` | `.claude/agent-memory-local/<name>/` | Local-only knowledge | No |
-
-When enabled:
-- First 200 lines of MEMORY.md loaded into agent's system prompt
-- Read/Write/Edit tools automatically enabled for memory directory
-- Agent builds knowledge across conversations
 
-Agents that should NOT have memory (stateless by design):
-- Manager agents for one-time operations (mgr-creator, mgr-updater, mgr-supplier)
-- Validation agents (mgr-sync-checker, mgr-claude-code-bible)
-- Meta-agents (sys-memory-keeper, sys-naggy)
+### Optional Frontmatter
 
-## External Agent Requirements
-
-External agents (from GitHub, npm, etc.) MUST include source information in frontmatter:
-
-### Frontmatter Source Fields
 ```yaml
-source:
+memory: project            # user | project | local
+effort: high               # low | medium | high
+skills: [skill-1, ...]     # Skill name references
+source:                    # For external agents
   type: external
-  origin: github | npm | other
-  url: https://github.com/org/repo
+  origin: github | npm
+  url: https://...
   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
 
-### .claude/agents/
-```
-Purpose: Define WHAT the agent does
-Content: Role, capabilities, workflow
-Format: Single .md file with YAML frontmatter
-NOT: How to do it (that's skills/)
-```
+## Memory Scopes
 
-### .claude/skills/
-```
-Purpose: Define HOW to do tasks
-Content: Instructions, scripts, rules
-Location: .claude/skills/{name}/SKILL.md
-```
+| Scope | Location | Git Tracked |
+|-------|----------|-------------|
+| `user` | `~/.claude/agent-memory/<name>/` | No |
+| `project` | `.claude/agent-memory/<name>/` | Yes |
+| `local` | `.claude/agent-memory-local/<name>/` | No |
 
-### guides/
-```
-Purpose: Reference documentation
-Content: Best practices, tutorials
-Location: guides/{topic}/
-```
+When enabled: first 200 lines of MEMORY.md loaded into system prompt.
 
-## Agent → Skill References
+## Separation of Concerns
 
-### In Frontmatter
-```yaml
----
-name: agent-name
-skills:
-  - react-best-practices
-  - web-design-guidelines
----
-```
+| Location | Purpose | Contains |
+|----------|---------|----------|
+| `.claude/agents/` | WHAT the agent does | Role, capabilities, workflow |
+| `.claude/skills/` | HOW to do tasks | Instructions, scripts, rules |
+| `guides/` | Reference docs | Best practices, tutorials |
 
-Skills are referenced by name only. The system automatically discovers skills in `.claude/skills/` by scanning for `SKILL.md` files.
+Agent body: purpose, capabilities overview, workflow. NOT detailed instructions or reference docs.
 
-## Naming Conventions
+## Naming
 
 | Type | Pattern | Example |
 |------|---------|---------|
-| Agent file | `kebab-case.md` | `.claude/agents/fe-vercel-agent.md` |
-| Skill directory | `kebab-case/` | `.claude/skills/react-best-practices/` |
-| Guide directory | `kebab-case/` | `guides/web-design/` |
-| Agent filename | lowercase | `{name}.md` |
+| Agent file | `kebab-case.md` | `fe-vercel-agent.md` |
+| Skill dir | `kebab-case/` | `react-best-practices/` |
 | Skill file | UPPERCASE | `SKILL.md` |

package/templates/.claude/rules/MUST-agent-identification.md

@@ -1,22 +1,10 @@
 # [MUST] Agent Identification Rules
 
-> **Priority**: MUST - ENFORCED, NO EXCEPTIONS
-> **ID**: R007
-> **Violation**: Immediate correction required
+> **Priority**: MUST - ENFORCED | **ID**: R007
 
-## CRITICAL
+## Core Rule
 
-**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:
+Every response MUST start with agent identification:
 
 ```
 ┌─ Agent: {agent-name} ({agent-type})
@@ -24,85 +12,18 @@ Every response MUST start with an agent identification block:
 └─ Task: {brief-task-description}
 ```
 
-## Examples
+Default (no specific agent): `┌─ Agent: claude (default)`
 
-### Single Agent Response
-```
-┌─ Agent: mgr-creator (manager)
-└─ Task: Creating new agent
-
-[Response content...]
-```
-
-### With Skill Usage
-```
-┌─ Agent: fe-vercel-agent (worker)
-├─ Skill: react-best-practices
-└─ Task: Optimizing React component
+## Simplified Format
 
-[Response content...]
-```
-
-### Multiple Skills
-```
-┌─ Agent: fe-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...]
-```
+For brief responses: `[mgr-creator] Creating agent structure...`
+With skill: `[fe-vercel-agent → react-best-practices] Analyzing...`
 
 ## When to Display
 
 | Situation | Display |
 |-----------|---------|
-| Agent-specific task | Full header with agent |
+| Agent-specific task | Full header |
 | Using skill | Include skill name |
 | General conversation | "claude (default)" |
-| Multiple agents | Show primary agent |
-
-## Agent Types
-
-| Type | Symbol | Example |
-|------|--------|---------|
-| manager | 🔧 | mgr-creator, mgr-updater |
-| worker | ⚙️ | fe-vercel-agent |
-| orchestrator | 🎯 | (future) |
-| default | 💬 | claude |
-
-## Simplified Format (Optional)
-
-For brief responses, use inline format:
-
-```
-[mgr-creator] Creating agent structure...
-```
-
-Or with skill:
-
-```
-[fe-vercel-agent → react-best-practices] Analyzing performance...
-```
-
-## Status Updates
-
-During long tasks, show progress with agent context:
-
-```
-┌─ Agent: mgr-updater (manager)
-└─ Task: Checking external updates
-
-[Progress] Scanning .claude/agents/ (1/3)
-[Progress] Scanning .claude/skills/ (2/3)
-[Progress] Scanning .claude/guides/ (3/3)
-
-[Done] Found 2 updates available
-```
+| Long tasks | Show progress with agent context |