# Claude Code Hooks

Writes, tests, registers and debugs Claude Code hooks (PreToolUse, PostToolUse...

- Repository: https://github.com/daymade/claude-code-skills (1509 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add daymade/claude-code-skills --skill claude-code-hooks -g -a claude-code -y`
Codex: `npx skills add daymade/claude-code-skills --skill claude-code-hooks -g -a codex -y`
Cursor: `npx skills add daymade/claude-code-skills --skill claude-code-hooks -g -a cursor -y`
Gemini CLI: `npx skills add daymade/claude-code-skills --skill claude-code-hooks -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add daymade/claude-code-skills`

## Description

Writes, tests, registers and debugs Claude Code hooks (PreToolUse, PostToolUse, SessionStart, Stop) that turn a rule the model keeps breaking into a hard gate. Use when the user wants to block or intercept a tool call, add a guard rail, fix a misfiring hook, or says 拦截 / 守卫 / 钩子, including "make it stop doing X".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Claude Code Hooks

Claude Code fires **hooks** at tool-call boundaries. A hook is a shell command
that receives a JSON event on stdin and, for blocking hooks, decides via its
**exit code** whether the tool call proceeds. This is the only mechanism that
*structurally* stops a behavior, a prose rule in CLAUDE.md is a suggestion the
completion drive can override; a hook is a wall.

## When a hook is the right tool (and when it isn't)

Write a hook when **a rule keeps getting violated even though it's already
written down**. The tell: you added the prose rule, it read clearly, and the
behavior recurred anyway, because at the moment of action, attention is 100%
on "get the thing done" and the reminder loses. That recurrence is the signal
to move the rule from prose (advisory) to a hook (enforced). Governance rule of
thumb: *Tier-0 irreversible action + only prose, no hook → it should be a hook.*
(**Tier-0** here = an action whose damage cannot be undone from inside the session:
destroying uncommitted work, pushing secrets to a remote, deleting files, publishing
something outward. The test is reversibility, not severity.)

Do **not** reach for a hook when: the rule has never actually recurred (don't
pre-build guards for hypothetical mistakes, cost with no proven benefit), or
the "rule" is a judgment call with no mechanical signature (a hook can only
match tokens/patterns; it can't judge whether a design is good).

If the symptom is “it keeps reviewing / waiting / retrying,” do not assume the
answer is another hook. First complete the **Loop Contract** in rule 7 and read
[pitfall #36](references/hook_pitfalls.md#36-a-self-applied-review-rule-can-loop-without-any-hook).
The loop may be created entirely by an agent repeatedly applying a prose rule.

## Hook types and what the exit code means

The rest: https://github.com/daymade/claude-code-skills/blob/HEAD/daymade-claude-code/claude-code-hooks/SKILL.md