Agent skill

julien-dev-hook-creator

Guide for creating Claude Code hooks - shell commands that execute at specific lifecycle events (SessionStart, SessionEnd, PreToolUse, PostToolUse, etc.). Use when users want to automate actions, add validation, logging, or integrate external tools into Claude Code workflows.

Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/julien-dev-hook-creator

Metadata

Additional technical details for this skill

author
Julien
version
1.0.0
category
development

SKILL.md

Hook Creator

This skill guides the creation of Claude Code hooks - deterministic shell commands or LLM prompts that execute at specific points in Claude's lifecycle.

What Are Hooks?

Observability

First: At the start of execution, display:

πŸ”§ Skill "julien-dev-hook-creator" activated

Hooks provide deterministic control over Claude's behavior. Unlike skills (which Claude chooses to use), hooks always execute at their designated lifecycle event.

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                    HOOKS vs SKILLS                              β”‚
β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
β”‚  HOOKS: Deterministic, always run at lifecycle events           β”‚
β”‚  SKILLS: Model-invoked, Claude decides when to use              β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Available Hook Events

Event When It Runs Common Use Cases
SessionStart Session begins/resumes Load context, sync data, set env vars
SessionEnd Session ends Cleanup, save state, push changes
PreToolUse Before tool execution Validate, block, modify tool input
PostToolUse After tool completes Format output, log, trigger actions
PermissionRequest Permission dialog shown Auto-approve or deny permissions
UserPromptSubmit User submits prompt Add context, validate requests
Notification Claude sends notification Custom alerts
Stop Claude finishes responding Decide if Claude should continue
SubagentStop Subagent completes Evaluate task completion

Hook Configuration

Hooks are configured in ~/.claude/settings.json (global) or .claude/settings.json (project).

Basic Structure

json
{
  "hooks": {
    "EventName": [
      {
        "matcher": "ToolPattern",
        "hooks": [
          {
            "type": "command",
            "command": "your-command-here",
            "timeout": 60
          }
        ]
      }
    ]
  }
}

Configuration Fields

Field Required Description
matcher For tool events Pattern to match tool names (regex supported)
type Yes "command" (shell) or "prompt" (LLM)
command For type:command Shell command to execute
prompt For type:prompt LLM prompt for evaluation
timeout No Seconds before timeout (default: 60, max: 300)

Matcher Patterns

json
"matcher": "Write"           // Exact match
"matcher": "Edit|Write"      // OR pattern (regex)
"matcher": "Notebook.*"      // Wildcard pattern
"matcher": "*"               // All tools (or omit matcher)

Hook Input (stdin)

Hooks receive JSON via stdin with context about the event:

json
{
  "session_id": "abc123",
  "transcript_path": "/path/to/transcript.jsonl",
  "cwd": "/current/working/directory",
  "hook_event_name": "PreToolUse",
  "tool_name": "Write",
  "tool_input": {
    "file_path": "/path/to/file.txt",
    "content": "file content"
  }
}

Hook Output (Exit Codes)

Exit Code Behavior
0 Success - continue normally
2 Block - stderr fed to Claude, action blocked
Other Non-blocking error (shown in verbose mode)

Advanced JSON Output (exit 0)

json
{
  "continue": true,
  "stopReason": "message if continue=false",
  "suppressOutput": true,
  "systemMessage": "warning shown to user"
}

PreToolUse Decision Control

json
{
  "hookSpecificOutput": {
    "hookEventName": "PreToolUse",
    "permissionDecision": "allow|deny|ask",
    "permissionDecisionReason": "Reason here",
    "updatedInput": {
      "field": "modified value"
    }
  }
}

Creating a Hook - Step by Step

Step 1: Identify the Use Case

Ask:

  • When should this run? (which event)
  • What should it do? (validate, log, transform, block)
  • Scope: Global (~/.claude/settings.json) or project (.claude/settings.json)?

Step 2: Write the Script

Create script in ~/.claude/scripts/ or .claude/scripts/:

bash
#!/bin/bash
# ~/.claude/scripts/my-hook.sh

# Read input from stdin
INPUT=$(cat)

# Parse with jq
TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name // empty')
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')

# Your logic here
if [[ "$FILE_PATH" == *".env"* ]]; then
    echo "Blocked: Cannot modify .env files" >&2
    exit 2  # Block the action
fi

exit 0  # Allow the action

Important: Make executable with chmod +x

Step 3: Configure the Hook

Add to settings.json:

json
{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "bash ~/.claude/scripts/my-hook.sh",
            "timeout": 10
          }
        ]
      }
    ]
  }
}

Step 4: Test

bash
# Test script directly
echo '{"tool_name":"Write","tool_input":{"file_path":"/test/.env"}}' | bash ~/.claude/scripts/my-hook.sh
echo "Exit code: $?"

Real-World Example: Terminal Title Restoration

Problem: happy.cmd and claude.cmd contain title %COMSPEC% which overwrites terminal title to "C:\WINDOWS\system32\cmd.exe"

Solution: SessionStart hook that restores the title after launch

Script: ~/.claude/scripts/restore-terminal-title-on-start.ps1

powershell
# Restore terminal title on Claude Code SessionStart
# This runs AFTER Claude has potentially overwritten the title
try {
    # Get current directory name
    $dirName = if ($PWD.Path -eq $HOME) {
        "~"
    } else {
        Split-Path $PWD -Leaf
    }

    # Restore title using multiple methods for maximum compatibility

    # Method 1: PowerShell native
    $Host.UI.RawUI.WindowTitle = $dirName

    # Method 2: ANSI escape sequence (more reliable with Windows Terminal)
    Write-Host "$([char]27)]0;$dirName$([char]7)" -NoNewline

    # Exit with success
    exit 0
} catch {
    # Silent fail - don't break Claude startup
    exit 0
}

Configuration: ~/.claude/settings.json (NOT repo .claude/settings.json)

json
{
  "hooks": {
    "SessionStart": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "node \"%USERPROFILE%\\.claude\\scripts\\session-start-banner.js\"",
            "timeout": 5
          },
          {
            "type": "command",
            "command": "powershell.exe -NoProfile -File \"%USERPROFILE%\\.claude\\scripts\\restore-terminal-title-on-start.ps1\"",
            "timeout": 2
          }
        ]
      }
    ]
  }
}

Timeline:

  1. happy.cmd executes β†’ title becomes "C:\WINDOWS\system32\cmd.exe"
  2. Happy/Claude starts
  3. SessionStart hook: session-start-banner.js displays banner
  4. SessionStart hook: restore-terminal-title-on-start.ps1 fixes the title

Result: Title restored to directory name despite npm CLI wrapper interference

Lesson: Hooks can fix issues caused by external tools (npm wrappers, shell scripts)!

Hook Languages: JavaScript vs Python vs PowerShell

JavaScript Hooks (Fastest Startup)

Pros:

  • Node.js already loaded by Claude Code
  • No interpreter startup cost
  • Faster execution (~50-200ms faster than Python)
  • Great async support

Cons:

  • Limited system integration compared to PowerShell
  • JSON parsing requires external library or built-in JSON

Examples:

  • session-start-banner.js - Fast banner display
  • track-skill-invocation.js - Performance-critical tracking
  • fast-skill-router.js - Routing must be instant

When to use: Performance-critical hooks (SessionStart, UserPromptSubmit)

Python Hooks (Rich Ecosystem)

Pros:

  • Rich libraries (json, pathlib, subprocess)
  • Better for complex data processing
  • Easier multiline string handling
  • Great for ML/data tasks

Cons:

  • Python interpreter startup cost (~100-300ms)
  • May not be installed on all systems

Examples:

  • session-end-delete-reserved.py - Complex file operations
  • save-session-for-memory.py - Data processing
  • cleanup-null-files.py - File system traversal

When to use: Complex logic, data processing, non-time-critical tasks

PowerShell Hooks (Windows Native)

Pros:

  • Native Windows API access
  • Can modify environment directly
  • Better integration with Windows Terminal
  • Access to .NET framework

Cons:

  • Windows-only
  • Slower than JavaScript (~50-150ms startup)
  • CRLF line ending issues

Examples:

  • restore-terminal-title-on-start.ps1 - Terminal manipulation
  • cleanup-null-files.ps1 - Windows file operations
  • set-terminal-title.ps1 - Environment modification

When to use: Windows-specific tasks, terminal manipulation, .NET integration

Choosing the Right Language

Need speed? β†’ JavaScript
Need Python libraries? β†’ Python
Need Windows integration? β†’ PowerShell
Need to modify terminal? β†’ PowerShell
Need to call .NET APIs? β†’ PowerShell
Need async operations? β†’ JavaScript

Common Hook Patterns

1. File Protection (PreToolUse)

bash
#!/bin/bash
INPUT=$(cat)
FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')

PROTECTED=(".env" "package-lock.json" ".git/" "credentials")
for pattern in "${PROTECTED[@]}"; do
    if [[ "$FILE_PATH" == *"$pattern"* ]]; then
        echo "Protected file: $pattern" >&2
        exit 2
    fi
done
exit 0

2. Auto-Format on Save (PostToolUse)

json
{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "FILE=$(cat | jq -r '.tool_input.file_path') && npx prettier --write \"$FILE\" 2>/dev/null || true"
          }
        ]
      }
    ]
  }
}

3. Command Logging (PostToolUse)

bash
#!/bin/bash
INPUT=$(cat)
CMD=$(echo "$INPUT" | jq -r '.tool_input.command // empty')
DESC=$(echo "$INPUT" | jq -r '.tool_input.description // "No description"')
echo "$(date +%Y-%m-%d_%H:%M:%S) | $CMD | $DESC" >> ~/.claude/logs/bash-commands.log
exit 0

4. Session Sync (SessionStart/SessionEnd)

json
{
  "hooks": {
    "SessionStart": [
      {
        "hooks": [{
          "type": "command",
          "command": "bash ~/.claude/scripts/sync-marketplace.sh",
          "timeout": 30
        }]
      }
    ],
    "SessionEnd": [
      {
        "hooks": [{
          "type": "command",
          "command": "bash ~/.claude/scripts/push-marketplace.sh",
          "timeout": 30
        }]
      }
    ]
  }
}

5. Add Context to Prompts (UserPromptSubmit)

bash
#!/bin/bash
# stdout is added as context to the prompt
echo "Current git branch: $(git branch --show-current 2>/dev/null || echo 'not a git repo')"
echo "Node version: $(node -v 2>/dev/null || echo 'not installed')"
exit 0

6. LLM-based Stop Decision (Stop)

json
{
  "hooks": {
    "Stop": [
      {
        "hooks": [{
          "type": "prompt",
          "prompt": "Review if all tasks are complete. Check: 1) All todos marked done 2) Tests passing 3) No pending questions. Respond with decision: approve (stop) or block (continue).",
          "timeout": 30
        }]
      }
    ]
  }
}

Best Practices

Do's

  • βœ… Always quote shell variables: "$VAR" not $VAR
  • βœ… Use absolute paths for scripts
  • βœ… Handle errors gracefully (exit 0 if non-critical)
  • βœ… Set appropriate timeouts
  • βœ… Test scripts independently before configuring
  • βœ… Use tr -d '\r' for Windows CRLF compatibility

Don'ts

  • ❌ Don't block critical operations without good reason
  • ❌ Don't use long timeouts (blocks Claude)
  • ❌ Don't trust input blindly - validate paths
  • ❌ Don't expose secrets in logs
  • ❌ Don't use interactive commands (no stdin available)

Debugging Hooks

bash
# Run with debug output
bash -x ~/.claude/scripts/my-hook.sh

# Test with sample input
echo '{"tool_name":"Write","tool_input":{"file_path":"/test/file.txt"}}' | bash ~/.claude/scripts/my-hook.sh

# Check hook errors in Claude Code
# Look for "hook error" messages in the UI

For detailed troubleshooting of common errors (timeout, CRLF, jq not found, etc.), see references/troubleshooting.md.

Environment Variables

Available in hooks:

  • CLAUDE_PROJECT_DIR - Current project directory
  • CLAUDE_CODE_REMOTE - Remote mode indicator
  • CLAUDE_ENV_FILE - (SessionStart only) File path for persisting env vars

File Locations - CRITICAL INFORMATION

Location Scope Usage
~/.claude/settings.json Global (REAL FILE) File USED by Claude Code
.claude/settings.json Project (versioning) Committed to repo, NOT used directly
.claude/settings.local.json Local overrides Not committed
~/.claude/scripts/ Global scripts Used by hooks
.claude/scripts/ Project scripts Versioned with repo

⚠️ CRITICAL WARNING

Claude Code uses ~/.claude/settings.json (home directory) NOT the repo .claude/settings.json

These files are DIFFERENT and must be synchronized manually!

Best Practice:

  1. Modify ~/.claude/settings.json first (real file)
  2. Copy changes to .claude/settings.json (for versioning)
  3. Commit repo version for documentation

Never assume the repo version is active!

Verification:

bash
# Check what Claude Code actually uses
cat ~/.claude/settings.json | grep -A 5 "SessionStart"

# Compare with repo version
diff ~/.claude/settings.json .claude/settings.json

Quick Reference

Event Flow:
SessionStart β†’ UserPromptSubmit β†’ PreToolUse β†’ [Tool] β†’ PostToolUse β†’ Stop β†’ SessionEnd

Exit Codes:
0 = Success (continue)
2 = Block (stop action, feed stderr to Claude)
* = Non-blocking error

Matcher:
"Write"        = exact match
"Edit|Write"   = OR
"Notebook.*"   = regex
"*" or omit    = all tools

πŸ”— Skill Chaining

Skills Required Before

  • Aucun (skill autonome)
  • Optionnel: Connaissance de base de bash/shell scripting

Input Expected

  • Use case description: Quel Γ©vΓ©nement dΓ©clencher, quelle action effectuer
  • Scope decision: Global (~/.claude/settings.json) ou project (.claude/settings.json)
  • Prerequisites: jq installΓ© pour parsing JSON

Output Produced

  • Format:
    • Script bash dans ~/.claude/scripts/ ou .claude/scripts/
    • Configuration JSON dans settings.json
  • Side effects:
    • CrΓ©ation/modification de fichiers scripts
    • Modification de settings.json
    • Hooks actifs au prochain Γ©vΓ©nement
  • Duration: 2-5 minutes pour un hook simple

Compatible Skills After

RecommandΓ©s:

  • sync-personal-skills: Si le hook modifie des fichiers du marketplace
  • skill-creator: Si crΓ©ation d'un skill qui intΓ¨gre des hooks

Optionnels:

  • Git workflow: Committer les scripts et settings

Called By

  • Direct user invocation: "CrΓ©e un hook pour...", "Je veux automatiser..."
  • Part of skill/workflow development

Tools Used

  • Read (lecture settings.json existant)
  • Write (crΓ©ation scripts bash)
  • Edit (modification settings.json)
  • Bash (test du hook, chmod +x)

Visual Workflow

User: "Je veux protΓ©ger les fichiers .env"
    ↓
hook-creator (this skill)
    β”œβ”€β–Ί Step 1: Identify event (PreToolUse)
    β”œβ”€β–Ί Step 2: Write script (protect-files.sh)
    β”œβ”€β–Ί Step 3: chmod +x script
    β”œβ”€β–Ί Step 4: Configure settings.json
    └─► Step 5: Test with sample input
    ↓
Hook active βœ…
    ↓
[Next: Test in real session]

Usage Example

Scenario: CrΓ©er un hook de logging des commandes bash

Input: "Log toutes les commandes bash exΓ©cutΓ©es"

Process:

  1. Event identifiΓ©: PostToolUse avec matcher Bash
  2. Script créé: ~/.claude/scripts/log-bash.sh
  3. Settings.json mis Γ  jour avec hook config
  4. Test avec sample JSON input

Result:

  • Script logging actif
  • Commandes loguΓ©es dans ~/.claude/logs/bash-commands.log

Didn't find tool you were looking for?

Be as detailed as possible for better results