hook-development

Agent SkillsFreeOpen Source

Guidance for creating Claude Code hooks (PreToolUse/PostToolUse/Stop, etc.) to validate tool use and automate events.

🛡️ AgentReady threat assessment

MAESTRO 7-layer threat model + OWASP AIVSS risk score for hook-development, derived from its capabilities.

AIVSS 7.7 · High

Overview

Part of the plugin-dev plugin, this skill teaches creating Claude Code plugin hooks across all events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart/End, UserPromptSubmit, PreCompact, Notification), with emphasis on the prompt-based hooks API for validating tool use and blocking dangerous commands. It ships example hooks (validate-bash.sh, validate-write.sh, load-context.sh) and linter/test scripts run via bash.

Key features

All hook event types incl. prompt-based hooks
Example validators: validate-bash.sh, validate-write.sh
hook-linter.sh and test-hook.sh scripts

Use cases

Block dangerous bash commands via a PreToolUse hook
Auto-load context on SessionStart