claude-hook-review

Audit Claude Code hook scripts and settings for safe execution.

4|1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/jcdendrite/claude-config --skill claude-hook-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-hook-review
Source: https://github.com/jcdendrite/claude-config/tree/main/plugins/claude-hook-review/skills/claude-hook-review
Command: npx skills add https://github.com/jcdendrite/claude-config --skill claude-hook-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you reliably review Claude Code hook scripts and hook-related settings so you can catch configuration drift, unsafe command paths, and hook logic errors before they impact commit, push, or PR workflows.

Core Features & Use Cases

  • Systematic hook audit for safety and determinism: Reviews PreToolUse/PostToolUse/SessionStart hooks and verifies matcher/if dispatch coverage.
  • Correct path resolution enforcement: Ensures each command resolves to a stable absolute path using $CLAUDE_PROJECT_DIR, ${CLAUDE_PLUGIN_ROOT}, or an appropriate user-level prefix rather than brittle relative paths.
  • Fail-closed parsing guidance for gate hooks: Validates that hook scripts use the canonical JSON parsing pattern and deny on malformed or missing tool-input data.
  • Operational-footprint hardening checklist: Highlights latency and timeout risks for external commands and calls out potential indefinite hangs.

Quick Start

Ask your AI to review your Claude Code hook script .claude/hooks/<name>.sh and your .claude/settings.json hook entries for correct dispatch matching, fail-closed parsing, and safe command path resolution.

Frequently Asked Questions about claude-hook-review

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

FAQPage Schema
How do I review Claude Code hook scripts for safe command path resolution?

Fail-closed JSON parsing for PreToolUse deny gates requires hook scripts to use canonical JSON parsing patterns that deny execution on malformed or missing tool-input data. This prevents unsafe behavior when gate logic encounters invalid input.

How do I check configuration drift in Claude Code settings.json hook matchers?

Checking configuration drift in Claude Code settings.json hook matchers involves auditing matcher/if dispatch entries against internal hook script regex patterns. This verifies dispatch coverage and catches logic errors before they impact workflows.

What are the operational latency safeguards for Claude Code external hook commands?

Operational latency safeguards for Claude Code external hook commands involve hardening checklists that highlight timeout risks and call out potential indefinite hangs. This ensures external commands do not stall commit, push, or PR workflows.

How do I enforce strict permissionDecision JSON requirements in PreToolUse hooks?

Enforcing strict permissionDecision JSON requirements in PreToolUse hooks involves validating that gate scripts output correctly structured permission decision objects. This maintains deterministic hook execution and prevents unauthorized tool actions.