agentsclimarketplace

Claude code hooks

Skill bg-szy/TOP-SKILLS/skills/marketplace/claude-code-hooks

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.From its SKILL.md

Install
npx -y skills add bg-szy/TOP-SKILLS --skill claude-code-hooks

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.9 KB, 670 tokens by cl100k_base, as published. Nobody here has run it

Claude Code Hooks

Execute custom scripts before/after Claude Code tool invocations.

Quick Reference

EventWhenHas Matcher
PreToolUseBefore tool executionYes
PostToolUseAfter tool completesYes
PermissionRequestPermission dialog shownYes
NotificationNotifications sentYes
UserPromptSubmitUser submits promptNo
StopAgent finishesNo
SubagentStopSubagent finishesNo
PreCompactBefore context compactionNo
SessionStartSession begins/resumesNo
SessionEndSession endsNo

Basic Configuration

Add to ~/.claude/settings.json or .claude/settings.local.json:

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "Bash",
      "hooks": [{
        "type": "command",
        "command": "$CLAUDE_PROJECT_DIR/hooks/validate.sh",
        "timeout": 5000
      }]
    }]
  }
}

Matcher Patterns

PatternMatches
"Write"Only Write tool
"*" or ""All tools
"mcp__*"All MCP tools
"Bash"Bash commands

Hook Script Requirements

#!/bin/bash
# Receives JSON via stdin: { "tool_name": "...", "tool_input": {...} }
INPUT=$(cat)
TOOL=$(echo "$INPUT" | jq -r '.tool_name')

# Exit codes:
# 0 = Success (continue)
# 2 = Block with error (stderr shown to Claude)
# Other = Non-blocking error

Common Use Cases

Use CaseEventExample
Validate inputsPreToolUseBlock dangerous commands
Audit loggingPostToolUseLog all tool usage
Custom approvalPermissionRequestSlack notification
Session initSessionStartLoad project context

Security Checklist

  • Quote all variables: "$VAR" not $VAR
  • Validate paths (no .. traversal)
  • Use $CLAUDE_PROJECT_DIR for paths
  • Set reasonable timeouts
  • Handle jq parsing errors

Troubleshooting

# Debug hook loading
claude --debug

# List registered hooks
/hooks

# Test script manually
echo '{"tool_name":"Bash"}' | ./hooks/validate.sh

Official Documentation

Additional Resources

  • ./references/hook-events.md - All events with input/output schemas
  • ./references/configuration.md - Advanced config patterns
  • ./references/security-patterns.md - Production security

See Also: claude-code-debug for troubleshooting, claude-code-headless for CLI automation

What ships with it: 1 file

105.8 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,286. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.