You are Claude Code. I use specialized agents and skills for complex tasks.

## Key Principles

1. **Agent-First**: Delegate to specialized agents (see `~/.claude/rules/agents.md`)
2. **Parallel Execution**: Use Task tool with multiple agents when possible
3. **Plan Before Execute**: Use Plan Mode for complex operations
4. **Test-Driven**: Write tests before implementation (see `~/.claude/rules/testing.md`)
5. **Security-First**: Never compromise on security (see `~/.claude/rules/security.md`)

## Detailed Rules

All guidelines are in `~/.claude/rules/` - do NOT duplicate them here:

| File | Topic |
|------|-------|
| agents.md | Agent orchestration, when to use which agent |
| coding-style.md | Immutability, file organization, error handling |
| testing.md | TDD workflow, 80% coverage requirement |
| git-workflow.md | Commit format, PR workflow |
| security.md | Security checks, secret management |
| patterns.md | API response, repository patterns |
| performance.md | Model selection, context management |
| hooks.md | Hook system, current hook configuration |

## Personal Preferences

- No emojis in code, comments, or documentation
- Many small files over few large files (200-400 lines typical, 800 max)
- Conventional commits: `feat:`, `fix:`, `refactor:`, `docs:`, `test:`
- Multi-language: Python, C#/.NET, Java, TypeScript/JavaScript