更像是构建某个工作流

hooks are deterministic — they always run.

Why Use Hooks

• CLAUDE.md
• Most of the time it will. But sometimes it won't. 
• A hook makes it happen every single time, no exceptions.

Common use cases include:

• Auto-formatting after file edits
• Logging all executed commands for compliance
• Blocking dangerous operations like modifying production files
• Sending yourself notifications when Claude finishes a task

How They Work

Configured in your settings.json.

You pick an event, optionally set a matcher for which tools it applies to, and provide a command to run. 

• PreToolUse — runs before a tool call
• PostToolUse — runs after a tool call completes
• UserPromptSubmit — runs when you submit a prompt, before Claude processes it
• Stop — runs when Claude finishes responding
• Notification — runs when Claude sends a notification

/hooks command or editing settings.json

A Practical Example

Set a PostToolUse hook with a matcher of "Edit|MultiEdit|Write"

Blocking with PreToolUse

• Exit code 0 — proceed normally.
• Exit code 2 — block the action. The stderr message gets fed back to Claude as feedback so it knows why it was blocked and can adjust.
• Any other exit code — a non-blocking error that gets shown to you but doesn't stop anything.

This is how you enforce hard rules. Block writes to a production config directory. Block bash commands that contain rm -rf. Block commits to main. Whatever your team needs to be guaranteed, not suggested

Sharing Hooks with Your Team

Hooks configured in .claude/settings.json 

 team gets the same hooks automatically.

CLAUDE_PROJECT_DIR environment variable