Creating Claude Hooks logo

Creating Claude Hooks

Organization
AgentWorkforce
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

Overview

PublisherAgentWorkforce
Repositoryrelay
Skill namecreating-claude-hooks
Stars
875
Forks
73
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AgentWorkforce on GitHub. Read the source before you install it.

Installation

Install the Creating Claude Hooks AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AgentWorkforce/relay/tree/main/.claude/skills/creating-claude-hooks-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AgentWorkforce/relay.git /tmp/relay
mkdir -p .claude/skills
cp -r /tmp/relay/.claude/skills/creating-claude-hooks-skill .claude/skills/creating-claude-hooks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Creating Claude Hooks in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Creating Claude Hooks on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Creating Claude Hooks is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:
bash
#!/bin/bash
# or
#!/usr/bin/env node
# or
#!/usr/bin/env python3
  1. Be executable:
bash
chmod +x .claude/hooks/session-start
  1. Handle JSON input from stdin:
bash
#!/bin/bash
INPUT=$(cat)
FILE=$(echo "$INPUT" | jq -r '.input.file_path // empty')
  1. Exit with appropriate code:
bash
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:

json
{
  "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

bash
#!/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

typescript
#!/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

bash
# 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:

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

4. Secure Sensitive Files

bash
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

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

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

6. Log for Debugging

bash
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

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

markdown
---
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

bash
# 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

bash
# 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

bash
# 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

Frequently asked questions

What does the Creating Claude Hooks AI skill do?

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

Why use Creating Claude Hooks on TypingMind?

Because you install it once and use it with any model. Creating Claude Hooks is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Creating Claude Hooks in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgentWorkforce/relay/tree/main/.claude/skills/creating-claude-hooks-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Creating Claude Hooks?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Creating Claude Hooks?

As many as you like. As long as a model supports skills, you can use Creating Claude Hooks with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Creating Claude Hooks AI skill free?

Yes. It is published on GitHub by AgentWorkforce under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇