hook-development

Design Claude Code plugin hooks with JSON outputs and security guardrails.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/Wizarck/eligia-skills --skill hook-development-wizarck
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hook-development
Source: https://github.com/Wizarck/eligia-skills/tree/main/claude-plugins-official/plugins/plugin-dev/skills/hook-development
Command: npx skills add https://github.com/Wizarck/eligia-skills --skill hook-development-wizarck

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, timeout, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you design, implement, and validate Claude Code plugin hooks without guessing at event formats, safety rules, or portable paths.

Core Features & Use Cases

  • Prompt-based and command-based hook patterns for PreToolUse, PostToolUse, Stop, SessionStart, SessionEnd, PreCompact, Notification, and UserPromptSubmit.
  • Ready-made validation, testing, linting, and schema-checking workflows for safer deployment.
  • Practical use cases for blocking dangerous commands, loading session context, and enforcing completion checks across plugin workflows.

Quick Start

Ask the skill to create or review a Claude Code hook for your target event and safety requirement, and it will draft the configuration plus supporting validation guidance.

Frequently Asked Questions about hook-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create Claude Code hooks for PreToolUse and PostToolUse events?

You can design Claude Code hooks for PreToolUse and PostToolUse by defining event-specific matchers and structured JSON outputs. This skill drafts both prompt-based and command-based automation patterns along with validation guidance.

How do I block dangerous commands using Claude Code command hooks?

Blocking dangerous commands requires implementing validation workflows and security guardrails within your command hooks. This skill provides practical use cases for preventing unsafe operations and enforcing completion checks across plugin workflows.

Do I need jq and timeout installed to build Claude Code plugin hooks?

Yes, jq and timeout are required dependencies. They support the structured JSON hook output processing and timeout controls needed to validate and test safer Claude Code plugin deployments.

What is the best way to validate Claude Code hooks before deployment?

The best way to validate Claude Code hooks is using schema-checking, linting, and testing workflows. This skill generates validation guidance to ensure plugin hooks satisfy portable plugin-root path usage and security guardrails.

Can I use Claude Code hooks for SessionStart and SessionEnd to load context?

Yes, SessionStart and SessionEnd hooks support loading session context and enforcing completion checks. This skill covers prompt-based and command-based automation patterns for these scenarios along with structured JSON outputs.

Why are my Claude Code hooks failing due to non-portable plugin paths?

Claude Code hooks fail when paths are not portable across environments. This skill ensures your hook configurations satisfy portable plugin-root path usage and structured JSON output requirements for safer deployment.