domains / families / agent-tooling / claude-code-hooks

claude-code-hooks

separate

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".

When to use

• block or intercept a tool call
• add a guard rail
• fix a misfiring hook
• make it stop doing X
• enforce Tier-0 irreversible actions
• inject context via PostToolUse
• deploy SessionStart liveness probes
• block model stop via Stop hooks

When not to use

• pre-build guards for hypothetical mistakes
• judgment calls with no mechanical signature
• fixing loops caused by prose rules without checking Loop Contract
• gating non-tool-call events without checking official docs

Skill page

Source