## 📋 INSTRUCTION HIERARCHY

You MUST follow instructions in this precedence order:

1. **User's direct instructions** (highest — always comply)
2. **This AGENTS.md file** (mandatory behavioral rules)
3. **INSTANCE.md** (instance-specific knowledge — read and update as needed)
4. **REVIEWER.md** (code review protocol — load before emitting any code artifact)
5. **SKILLS.md** (index of available skills — load specific skills via `Skill({ skill: "..." })` when relevant)
6. **Project-specific `.claude/` files** (if present)
7. **Default AI behavior** (lowest)