본문으로 건너뛰기
cccskills
무료GitHub에 공개

creating-claude-hooks

Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md10.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Creating Claude Code Hooks

Use this skill when creating, improving, or publishing Claude Code hooks. Provides essential guidance on hook format, event handling, I/O conventions, and package structure.

When to Use This Skill

Activate this skill when:

  • User asks to create a new Claude Code hook
  • User wants to publish a hook as a PRPM package
  • User needs to understand hook format or events
  • User is troubleshooting hook execution
  • User asks about hook vs skill vs command differences

Quick Reference

Hook File Format

AspectRequirement
Location.claude/hooks/<event-name>
FormatExecutable file (shell, TypeScript, Python, etc.)
PermissionsMust be executable (chmod +x)
ShebangRequired (#!/bin/bash or #!/usr/bin/env node)
InputJSON via stdin
OutputText via stdout (shown to user)
Exit Codes0 = success, 2 = block, other = error

Available Events

EventWhen It FiresCommon Use Cases
session-startNew session beginsEnvironment setup, logging, checks
user-prompt-submitBefore user input processesValidation, enhancement, filtering
tool-callBefore tool executionPermission checks, logging, modification
assistant-responseAfter assistant respondsFormatting, logging, cleanup

Hook Format Requirements

File Location

Project hooks:

.claude/hooks/session-start
.claude/hooks/user-prompt-submit

User-global hooks:

~/.claude/hooks/session-start
~/.claude/hooks/tool-call

Executable Requirements

Every hook MUST:

  1. Have a shebang line:
#!/bin/bash
# or
#!/usr/bin/env node
# or
#!/usr/bin/env python3
  1. Be executable:
chmod +x .claude/hooks/session-start
  1. Handle JSON input from stdin:
#!/bin/bash
INPUT=$(cat)
FILE=$(echo "$INPUT" | jq -r '.input.file_path // empty')
  1. Exit with appropriate code:
exit 0  # Success
exit 2  # Block operation
exit 1  # Error (logs but continues)

Input/Output Format

JSON Input Structure

Hooks receive JSON via stdin with event-specific data:

{
  "event": "tool-call",
  "timestamp": "2025-01-15T10:30:00Z",
  "session_id": "abc123",
  "current_dir": "/path/to/project",
  "input": {
    "file_path": "/path/to/file.ts",
    "command": "npm test",
    "old_string": "...",
    "new_string": "..."
  }
}

Stdout Output

  • Normal output shows in transcript
  • Empty output runs silently
  • Use stderr (>&2) for errors

Exit Codes

CodeMeaningBehavior
0SuccessContinue normally
2BlockStop operation, show error
1 or otherErrorLog error, continue

Schema Validation

Hooks should validate against the JSON schema:

Schema URL: https://github.com/pr-pm/prpm/blob/main/packages/converters/schemas/claude-hook.schema.json

Required frontmatter fields:

  • name - Hook identifier (lowercase, hyphens only)
  • description - What the hook does
  • event - Event type (optional, inferred from filename)
  • language - bash, typescript, javascript, python, binary (optional)
  • hookType: "hook" - For round-trip conversion

Common Mistakes

MistakeProblemSolution
Not quoting variablesBreaks on spacesAlways use "$VAR"
Missing shebangWon't executeAdd #!/bin/bash
Not executablePermission deniedRun chmod +x hook-file
Logging to stdoutClutters transcriptUse stderr: echo "log" >&2
Wrong exit codeDoesn't block when neededUse exit 2 to block
No input validationSecurity riskAlways validate JSON fields
Slow operationsBlocks ClaudeRun in background or use PostToolUse
Absolute paths missingCan't find scriptsUse $CLAUDE_PLUGIN_ROOT

Basic Hook Examples

Shell Script Hook

#!/bin/bash
# .claude/hooks/session-start

# Log session start
echo "Session started at $(date)" >> ~/.claude/session.log

# Check environment
if ! command -v node &> /dev/null; then
  echo "Warning: Node.js not installed" >&2
fi

# Output to user
echo "Development environment ready"
exit 0

TypeScript Hook

#!/usr/bin/env node
// .claude/hooks/user-prompt-submit

import { readFileSync } from 'fs';

// Read JSON from stdin
const input = readFileSync(0, 'utf-8');
const data = JSON.parse(input);

// Validate prompt
if (data.prompt.includes('API_KEY')) {
  console.error('Warning: Prompt may contain secrets');
  process.exit(2); // Block
}

console.log('Prompt validated');
process.exit(0);

Best Practices

1. Keep Hooks Fast

Target < 100ms for PreToolUse hooks:

  • Cache results where possible
  • Run heavy operations in background
  • Use specific matchers, not wildcards

2. Handle Errors Gracefully

# Check dependencies exist
if ! command -v jq &> /dev/null; then
  echo "jq not installed, skipping" >&2
  exit 0
fi

# Validate input
FILE=$(echo "$INPUT" | jq -r '.input.file_path // empty')
if [[ -z "$FILE" ]]; then
  echo "No file path provided" >&2
  exit 1
fi

3. Use Shebangs

Always start with shebang:

#!/bin/bash
#!/usr/bin/env node
#!/usr/bin/env python3

4. Secure Sensitive Files

BLOCKED=(".env" ".env.*" "*.pem" "*.key")
for pattern in "${BLOCKED[@]}"; do
  case "$FILE" in
    $pattern)
      echo "Blocked: $FILE is sensitive" >&2
      exit 2
      ;;
  esac
done

5. Quote All Variables

# WRONG - breaks on spaces
prettier --write $FILE

# RIGHT - handles spaces
prettier --write "$FILE"

6. Log for Debugging

LOG_FILE=~/.claude-hooks/debug.log

# Log to file
echo "[$(date)] Processing $FILE" >> "$LOG_FILE"

# Log to stderr (shows in transcript)
echo "Hook running..." >&2

Publishing as PRPM Package

Package Structure

my-hook/
├── prpm.json          # Package manifest
├── HOOK.md            # Hook documentation
└── hook-script.sh     # Hook executable

prpm.json

{
  "name": "@username/hook-name",
  "version": "1.0.0",
  "description": "Brief description shown in search",
  "author": "Your Name",
  "format": "claude",
  "subtype": "hook",
  "tags": ["automation", "security", "formatting"],
  "main": "HOOK.md"
}

HOOK.md Format

---
name: session-logger
description: Logs session start/end times for tracking
event: SessionStart
language: bash
hookType: hook
---

# Session Logger Hook

Logs Claude Code session activity for tracking and debugging.

## Installation

This hook will be installed to `.claude/hooks/session-start`.

## Behavior

- Logs session start time to `~/.claude/session.log`
- Displays environment status
- Runs silent dependency checks

## Requirements

- bash 4.0+
- write access to `~/.claude/`

## Source Code

\`\`\`bash
#!/bin/bash
echo "Session started at $(date)" >> ~/.claude/session.log
echo "Environment ready"
exit 0
\`\`\`

Publishing Process

# Test locally first
prpm test

# Publish to registry
prpm publish

# Version bumps
prpm publish patch  # 1.0.0 -> 1.0.1
prpm publish minor  # 1.0.0 -> 1.1.0
prpm publish major  # 1.0.0 -> 2.0.0

Security Requirements

Input Validation

# Parse JSON safely
INPUT=$(cat)
if ! FILE=$(echo "$INPUT" | jq -r '.input.file_path // empty' 2>&1); then
  echo "JSON parse failed" >&2
  exit 1
fi

# Validate field exists
[[ -n "$FILE" ]] || exit 1

Path Sanitization

# Prevent directory traversal
if [[ "$FILE" == *".."* ]]; then
  echo "Path traversal detected" >&2
  exit 2
fi

# Keep in project directory
if [[ "$FILE" != "$CLAUDE_PROJECT_DIR"* ]]; then
  echo "File outside project" >&2
  exit 2
fi

User Confirmation

Claude Code automatically:

  • Requires confirmation before installing hooks
  • Shows hook source code to user
  • Warns about hook execution
  • Displays hook output in transcript

Hooks vs Skills vs Commands

FeatureHooksSkillsCommands
FormatExecutable codeMarkdownMarkdown
TriggerAutomatic (events)Automatic (context)Manual (/command)
LanguageAny executableN/AN/A
Use CaseAutomation, validationReference, patternsQuick tasks
SecurityRequires confirmationNo special permissionsInherits from session

Examples:

  • Hook: Auto-format files on save
  • Skill: Reference guide for testing patterns
  • Command: /review-pr quick code review

Related Resources

  • claude-hook-writer skill - Detailed hook development guidance
  • typescript-hook-writer skill - TypeScript-specific hook development
  • Claude Code Docs
  • Schema

Checklist for New Hooks

Before publishing:

  • Shebang line included
  • File is executable (chmod +x)
  • Validates all stdin input
  • Quotes all variables
  • Handles missing dependencies gracefully
  • Uses appropriate exit codes
  • Logs errors to stderr or file
  • Tests with edge cases (spaces, Unicode, missing fields)
  • Documents dependencies in HOOK.md
  • Includes installation instructions
  • Source code included in documentation
  • Clear description and tags in prpm.json
  • Version number is semantic

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and terminals.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentWorkforce/relay8872026년 10월 18일 업데이트

Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentWorkforce/relay8872026년 10월 18일 업데이트

Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate SDK/YAML examples.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentWorkforce/relay8872026년 10월 18일 업데이트

Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentWorkforce/relay8872026년 10월 18일 업데이트

Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentWorkforce/relay8872026년 10월 18일 업데이트

Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like alwaysApply

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AgentWorkforce/relay8872026년 10월 18일 업데이트

AgentWorkforce의 스킬 모두 보기

이 스킬의 문제 신고