Hook Development for Claude Code FAQs

Question 1

How do I persist environment variables across a session?

Accepted Answer

You can use a SessionStart hook to append export commands to the $CLAUDE_ENV_FILE, which Claude Code sources to maintain environment state throughout the active session.

Question 2

Where should plugin-specific hooks be defined?

Accepted Answer

Plugin-specific hooks should be defined in a hooks/hooks.json file within your plugin directory, using the specific wrapper format that includes a 'hooks' field.

Question 3

Can I use hooks to block access to specific files?

Accepted Answer

Yes, you can implement a PreToolUse hook with a matcher for file operations (like Write or Edit) to validate file paths and block access to sensitive files like .env or system directories.

Question 4

What is the difference between Stop and SubagentStop hooks?

Accepted Answer

The Stop hook triggers when the primary agent considers its task complete, while the SubagentStop hook is specific to when a spawned subagent attempts to finish its delegated task.

Question 5

What is a prompt-based hook in Claude Code?

Accepted Answer

A prompt-based hook uses Claude's natural language reasoning capabilities to evaluate a tool call or state, allowing for flexible, context-aware validation without complex bash scripting.

Hook Development for Claude Code

주요 기능

사용 사례

Hook Development for Claude Code

주요 기능

사용 사례