What are Claude Code hooks?

Hooks are event-driven scripts or LLM prompts that execute in response to specific events within the Claude Code CLI environment, such as tool usage or session starts.

Can hooks block actions?

Yes, 'Pre' events like PreToolUse or UserPromptSubmit can return a 'block' decision to prevent a specific command from executing based on custom logic.

How do I debug my hooks?

Run Claude Code with the 'claude --debug' flag to see which hooks are matching, the execution output of commands, and detailed error logs.

Where are hook configurations stored?

Hooks can be configured at the project level in .claude/hooks.json or at the user level in ~/.claude/hooks.json for global automation.

What is the difference between command and prompt hooks?

Command hooks execute standard shell scripts for logging or external tools, while prompt hooks use the LLM to make complex, context-aware decisions using natural language.

Claude Code Hooks Creator

Name: Claude Code Hooks Creator
Author: glittercowboy

byglittercowboy

•

770

Productivity & Workflow

Automates and customizes Claude Code behavior through event-driven shell commands and LLM-powered prompt hooks.

About

The create-hooks skill provides comprehensive guidance for implementing event-driven automation within Claude Code. It enables developers to configure custom triggers for tool usage, session events, and user interactions, allowing for advanced workflows such as automated code formatting, safety checks for destructive commands, desktop notifications, and project-specific context injection. By leveraging both shell commands and LLM-evaluated prompts, this skill empowers users to build a personalized, efficient, and secure development environment without modifying the core Claude Code application.

Key Features

Support for multiple event types including PreToolUse, PostToolUse, and SessionStart
770 GitHub stars
Action-blocking capabilities for safety checks and command validation
Dynamic context injection using project-level or user-level configuration
Regex-based tool matching for granular control over hook triggers
Implementation of both shell-based command hooks and LLM-powered prompt hooks

Use Cases

Preventing destructive git operations like force pushes or hard resets
Automatically running linters or formatters after file edits
Setting up desktop notifications to alert when Claude requires manual input

About

Key Features

Support for multiple event types including PreToolUse, PostToolUse, and SessionStart
770 GitHub stars
Action-blocking capabilities for safety checks and command validation
Dynamic context injection using project-level or user-level configuration
Regex-based tool matching for granular control over hook triggers
Implementation of both shell-based command hooks and LLM-powered prompt hooks

Use Cases

Preventing destructive git operations like force pushes or hard resets
Automatically running linters or formatters after file edits
Setting up desktop notifications to alert when Claude requires manual input