oh-my-customcode 0.1.4 → 0.2.1

package/README.md

@@ -14,7 +14,7 @@ Like oh-my-zsh transformed shell customization, oh-my-customcode makes personali
 
 | Feature | Description |
 |---------|-------------|
-| **Batteries Included** | 37 agents, 17 skills, 12 guides - synced with baekgom-agents templates |
+| **Batteries Included** | 34 agents, 42 skills, 13 guides - synced with baekgom-agents templates |
 | **Sub-Agent Model** | Supports hierarchical agent orchestration with specialized roles |
 | **Dead Simple Customization** | Create a folder + markdown file = new agent or skill |
 | **Mix and Match** | Use built-in components, create your own, or combine both |
@@ -39,146 +39,86 @@ That's it. You now have a fully configured Claude Code environment.
 
 This is what oh-my-customcode is all about. **Making Claude Code yours.**
 
-### Create a Custom Agent (2 files)
+### Just Tell Claude What You Need
 
-Want an agent that reviews database migrations? Just create:
+No manual file editing. Describe what you want in natural language, and the orchestrator delegates to the right agent:
 
 ```
-agents/sw-engineer/migration-expert/
-├── AGENT.md       # What the agent does
-└── index.yaml     # Metadata
+"Create a migration review expert agent"
+"Add a SQL optimization skill"
+"Make code reviews stricter"
+"Set up a deploy review pipeline"
 ```
 
-**AGENT.md:**
-```markdown
-# Migration Expert Agent
+**How it works:**
 
-> **Type**: Worker
-
-## Purpose
-
-Expert in database migrations, schema design, and data integrity.
-
-## Capabilities
-
-1. Review migration files for safety issues
-2. Suggest rollback strategies
-3. Check for data loss risks
-4. Optimize migration performance
-
-## When to Use
-
-- Before running migrations in production
-- Designing new database schemas
-- Reviewing team members' migrations
 ```
-
-**index.yaml:**
-```yaml
-metadata:
-  name: migration-expert
-  type: worker
-  category: sw-engineer
-  description: Database migration specialist
+User (natural language)
+  → /create-agent (routing skill)
+    → mgr-creator:sonnet       — scaffolds agent, registers, verifies
+    → mgr-updater:sonnet       — syncs documentation
+    → mgr-supplier:haiku       — checks dependencies
 ```
 
-Done. Your custom agent is ready to use.
-
-### Add a Custom Skill
-
-Skills define **how** agents do things. Create specialized knowledge:
+Claude Code's routing system analyzes your request, routes it to the appropriate skill and agent, and the sub-agent handles everything automatically.
 
-```
-skills/development/sql-optimization/
-├── SKILL.md       # The skill instructions
-└── index.yaml     # Metadata
-```
+### Sub-Agent Model
 
-**SKILL.md:**
-```markdown
-# SQL Optimization Skill
+Each sub-agent runs on an optimized model for its task type:
 
-## Rules
+| Model | Usage | Examples |
+|-------|-------|---------|
+| `opus` | Complex reasoning, architecture | Code review, design analysis |
+| `sonnet` | General tasks (default) | Agent creation, code generation |
+| `haiku` | Fast, simple operations | File search, validation |
 
-### Query Optimization
-- Always use EXPLAIN ANALYZE before suggesting changes
-- Prefer indexes over full table scans
-- Avoid SELECT * in production code
-- Use CTEs for complex queries
+Claude Code selects the appropriate model and parallelizes independent tasks (up to 4 concurrent sub-agents):
 
-### Migration Safety
-- Always include rollback scripts
-- Test migrations on production-like data
-- Never delete columns without deprecation period
 ```
+/create-agent
+  ├── mgr-creator:sonnet       — agent scaffolding
+  ├── mgr-supplier:haiku       — dependency check
+  └── mgr-sync-checker:haiku   — registry verification
 
-### Modify Rules
-
-Rules control behavior. Edit them in `.claude/rules/`:
-
-```
-.claude/rules/
-├── MUST-*.md      # Required (safety, permissions)
-├── SHOULD-*.md    # Recommended (interactions, error handling)
-└── MAY-*.md       # Optional (optimizations)
+/code-review
+  ├── lang-golang-expert:sonnet — Go implementation
+  ├── lang-python-expert:sonnet — Python implementation
+  └── qa-engineer:sonnet        — test generation
 ```
 
-Want stricter code review? Edit `SHOULD-interaction.md`:
-
-```markdown
-## Code Review Standards
+### Built-in Commands
 
-### Before Approving Any Code
-- [ ] All tests pass
-- [ ] No security vulnerabilities
-- [ ] Performance impact assessed
-- [ ] Documentation updated
-```
+| Command | Agent | Description |
+|---------|-------|-------------|
+| `/create-agent <name>` | mgr-creator | Create a new agent |
+| `/update-docs` | mgr-updater | Sync docs with project structure |
+| `/audit-dependencies` | mgr-supplier | Verify agent dependencies |
+| `/code-review` | lang-* experts | Review code with expert agents |
+| `/run-pipeline <name>` | pipeline skill | Execute a workflow pipeline |
+| `/sync-check` | mgr-sync-checker | Full synchronization check |
 
-### Create Custom Pipelines
+### Custom Pipelines
 
-Define repeatable workflows in `pipelines/`:
+Define repeatable multi-agent workflows:
 
 ```yaml
-# pipelines/deploy-review.yaml
+# .claude/skills/pipelines/deploy-review.yaml
 name: deploy-review
-description: Pre-deployment review workflow
-
 steps:
   - id: security_scan
-    agent: qa-lead
+    agent: qa-planner
     action: security_review
 
   - id: performance_check
-    agent: optimizer
+    agent: tool-optimizer
     action: analyze_performance
 
   - id: migration_review
-    agent: migration-expert  # Your custom agent!
+    agent: db-migration-expert
     action: review_migrations
 ```
 
-Run it: `pipeline:run deploy-review`
-
-### Mix Built-in + Custom
-
-The real power is combining everything:
-
-```
-your-project/
-├── agents/
-│   ├── orchestrator/          # Built-in: planner, secretary
-│   ├── sw-engineer/
-│   │   ├── language/          # Built-in: golang, python, rust...
-│   │   └── migration-expert/  # YOUR custom agent
-│   └── your-team/             # YOUR team-specific agents
-├── skills/
-│   ├── development/           # Built-in: best practices
-│   └── your-company/          # YOUR company standards
-└── .claude/rules/
-    ├── MUST-safety.md         # Built-in
-    └── MUST-your-policy.md    # YOUR company policy
-```
+Run it: `/run-pipeline deploy-review`
 
 ---
 
@@ -186,38 +126,42 @@ your-project/
 
 > **Templates synced from [baekgom-agents](https://github.com/baekenough/baekgom-agents)** - Battle-tested agent system with sub-agent orchestration support.
 
-### Agents (37)
+### Agents (34)
 
 | Category | Count | Agents |
 |----------|-------|--------|
-| **Orchestrators** | 4 | planner, secretary, dev-lead, qa-lead |
-| **Managers** | 6 | creator, updater, supplier, gitnerd, sync-checker, sauron |
-| **System** | 2 | memory-keeper, naggy |
-| **Languages** | 6 | golang, python, rust, kotlin, typescript, java21 |
-| **Frontend** | 3 | vercel-agent, vuejs-agent, svelte-agent |
-| **Backend** | 5 | fastapi, springboot, go-backend, express, nestjs |
-| **Tooling** | 3 | npm-expert, optimizer, bun-expert |
-| **Architecture** | 2 | documenter, speckit-agent |
-| **Infrastructure** | 2 | docker-expert, aws-expert |
+| **Managers** | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron |
+| **System** | 2 | sys-memory-keeper, sys-naggy |
+| **Languages** | 6 | lang-golang-expert, lang-python-expert, lang-rust-expert, lang-kotlin-expert, lang-typescript-expert, lang-java21-expert |
+| **Frontend** | 3 | fe-vercel-agent, fe-vuejs-agent, fe-svelte-agent |
+| **Backend** | 5 | be-fastapi-expert, be-springboot-expert, be-go-backend-expert, be-express-expert, be-nestjs-expert |
+| **Tooling** | 3 | tool-npm-expert, tool-optimizer, tool-bun-expert |
+| **Database** | 1 | db-supabase-expert |
+| **Architecture** | 2 | arch-documenter, arch-speckit-agent |
+| **Infrastructure** | 2 | infra-docker-expert, infra-aws-expert |
 | **QA** | 3 | qa-planner, qa-writer, qa-engineer |
-| **Tutor** | 1 | go-tutor |
-| **Total** | **37** | |
+| **Tutor** | 1 | tutor-go |
+| **Total** | **34** | |
+
+### Skills (42)
 
-### Skills (17)
+Includes slash commands and capabilities:
 
 - **Development** (8): Go, Python, TypeScript, Kotlin, Rust, Java, React, Vercel
 - **Backend** (5): FastAPI, Spring Boot, Express, NestJS, Go Backend
 - **Infrastructure** (2): Docker, AWS
 - **System** (2): Memory management, result aggregation
 - **Orchestration** (2): Pipeline execution, intent detection
+- **Slash Commands** (20+): /create-agent, /code-review, /audit-dependencies, /sync-check, /commit, /pr, and more
 
-### Guides (12)
+### Guides (13)
 
 Comprehensive reference documentation covering:
 - Agent creation and management
 - Skill development
 - Pipeline workflows
 - Best practices and patterns
+- Sub-agent orchestration
 
 ### Rules (18)
 
@@ -250,15 +194,22 @@ After `omcustom init`:
 ```
 your-project/
 ├── CLAUDE.md              # Entry point for Claude
-├── .claude/
-│   ├── rules/             # Behavior rules
-│   ├── hooks/             # Event hooks
-│   └── contexts/          # Context files
-├── agents/                # All agents
-├── skills/                # All skills
-├── guides/                # Reference docs
-├── pipelines/             # Workflow definitions
-└── commands/              # Command definitions
+└── .claude/
+    ├── rules/             # Behavior rules (18 total)
+    ├── hooks/             # Event hooks
+    ├── contexts/          # Context files
+    ├── agents/            # All agents (flat structure, 34 total)
+    │   ├── lang-golang-expert/
+    │   ├── be-fastapi-expert/
+    │   ├── mgr-creator/
+    │   └── ...
+    ├── skills/            # All skills (42 total, includes slash commands)
+    │   ├── development/
+    │   ├── backend/
+    │   ├── infrastructure/
+    │   ├── system/
+    │   └── orchestration/
+    └── guides/            # Reference docs (13 total)
 ```
 
 ---