Claude Code Hook Architect Reference FAQs

Question 1

What is the primary advantage of using Hooks over Skills in Claude Code?

Accepted Answer

Hooks offer a 100% execution guarantee because they are event-based and do not rely on Claude's judgment, whereas Skills or Agents are triggered based on Claude's decision-making, which has variable reliability.

Question 2

Can Claude Code hooks modify tool inputs before they execute?

Accepted Answer

Yes, specifically during the PreToolUse and PermissionRequest events, a hook can return an 'updatedInput' to modify the command or parameters before they are processed.

Question 3

How is session data passed to a hook script?

Accepted Answer

Session data, including session_id, cwd, and transcript_path, is passed to the hook script via stdin in JSON format. Hooks must read stdin (e.g., using cat or jq) to access this data.

Question 4

Which hook event is best for injecting project-specific context?

Accepted Answer

The UserPromptSubmit event is ideal for context injection because any output to stdout during this event is automatically injected into Claude's prompt context.

Question 5

What does Exit Code 2 signify in the hook system?

Accepted Answer

Exit Code 2 acts as a 'Block' or 'Special Action' signal. Its behavior depends on the event; for example, in PreToolUse it blocks execution, while in the Stop event it forces Claude to continue working.

Claude Code Hook Architect Reference

关于

主要功能

使用场景

Claude Code Hook Architect Reference

关于

主要功能

使用场景