What problem does it solve?
Hooks are the mechanical enforcement layer of agent safety and observability.
Unlike CLAUDE.md instructions, which guide agent behavior through documentation, hooks execute code at lifecycle boundaries where the agent cannot override them.
This skill is a reference card, not a tutorial. It assumes you know what hooks are and need to quickly find the right event, the right exit code, or the right configuration pattern. For architectural understanding, read the seed_hooks_lifecycle_mastery and seed_mechanical_safety_enforcement seeds.
Core Features & Use Cases
- Quick lookup for all 26 lifecycle events across categories and their block/observe behavior.
- Guidance on exit codes (0/2) and configuration patterns for hooks in CLAUDE.md or plugin hooks.
- Use scenarios include debugging hook firing, selecting events, and setting up security blocks.
Quick Start
Consult this guide to quickly identify the correct lifecycle event, exit code, and configuration pattern for Claude Code hooks.