Are multiple hooks for the same event executed in order?

No, all matching hooks for a specific event are executed in parallel. This improves performance but means hooks should be designed to function independently of one another.

What is the difference between Prompt and Command hooks?

Prompt hooks use LLM-driven reasoning for flexible, context-aware validation using natural language, while Command hooks execute bash scripts for fast, deterministic checks and file system operations.

Can hooks block Claude from executing a command?

Yes, PreToolUse hooks can return a 'deny' decision to stop a tool from running, and Stop hooks can 'block' Claude from finishing a session until specific criteria are met.

What events can I trigger hooks on in Claude Code?

Supported events include SessionStart, SessionEnd, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStop, PreCompact, and Notification.

How do I ensure my hooks work across different environments?

Always use the ${CLAUDE_PLUGIN_ROOT} environment variable in your hook configurations to reference scripts relative to the plugin's installation directory rather than using absolute paths.

Hook Development for Claude Code

Name: Hook Development for Claude Code
Author: arlenagreer

byarlenagreer

0•

Developer Tools

Provides comprehensive guidance and implementation patterns for building event-driven automation hooks in the Claude Code environment.

Hook Development enables developers to extend Claude Code's capabilities through sophisticated event-driven automation. This skill provides the architectural blueprints for implementing hooks across the entire session lifecycle, from SessionStart to PostToolUse and Stop events. It covers both high-level LLM-driven prompt hooks for nuanced reasoning and high-performance bash-based command hooks for deterministic validations. By using this skill, developers can enforce security policies, automate context loading, and create custom guardrails that ensure Claude operates safely and efficiently within specific project constraints.

Key Features

01Standardized JSON output formats for permission decisions and system messages

020 GitHub stars

03Environment variable management using CLAUDE_PLUGIN_ROOT and CLAUDE_ENV_FILE

04Guidance for both Prompt-Based and Command-Based hook architectures

05Detailed event lifecycle mapping including PreToolUse, Stop, and SessionStart

06Security patterns for path traversal prevention and input validation

Use Cases

01Automating project-specific context loading and environment setup at the start of every session

02Implementing security guardrails to block dangerous shell commands or sensitive file access

03Creating validation layers that ensure tests pass or builds succeed before Claude can complete a task

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add arlenagreer/claude_configuration_docs hook-development

For use in Claude.ai and ChatGPT

Download Skill