name: claude-hooks-reference-2026 description: Complete reference for Claude Code hooks system (January 2026). Use when creating hooks, understanding hook events, matchers, exit codes, JSON output control, environment variables, plugin hooks, or implementing hook scripts.

Claude Code Hooks System - Complete Reference (January 2026)

Hooks execute custom commands or prompts in response to Claude Code events. Use for automation, validation, formatting, and security.

All Hook Events

Configuration

Configuration Locations (Precedence highest to lowest)

1. Managed - managed-settings.json (enterprise)
2. Local - .claude/settings.local.json (gitignored)
3. Project - .claude/settings.json (shared via git)
4. User - ~/.claude/settings.json (personal)
5. Plugin - hooks/hooks.json or frontmatter
6. Capability - Skill/Command/Agent frontmatter

Note: Enterprise administrators can use allowManagedHooksOnly to block user, project, and plugin hooks.

Structure

Hooks are organized by matchers, where each matcher can have multiple hooks:

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

Fields:

• matcher: Pattern to match tool names, case-sensitive (only for PreToolUse, PermissionRequest, PostToolUse)
  • Simple strings match exactly: Write matches only the Write tool
  • Supports regex: Edit|Write or Notebook.*
  • Use * to match all tools. Also accepts empty string ("") or omit matcher
• hooks: Array of hooks to execute when pattern matches
  • type: "command" for bash commands or "prompt" for LLM evaluation
  • command: (For type: "command") The bash command to execute
  • prompt: (For type: "prompt") The prompt to send to the LLM
  • timeout: (Optional) Seconds before canceling (default: 60 for commands, 30 for prompts)

Project-Specific Hook Scripts

Use $CLAUDE_PROJECT_DIR to reference scripts in your project:

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/check-style.sh"
          }
        ]
      }
    ]
  }
}

Events Without Matchers

For UserPromptSubmit, Stop, SubagentStop, and SessionEnd, omit the matcher:

{
  "hooks": {
    "UserPromptSubmit": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "/path/to/prompt-validator.py"
          }
        ]
      }
    ]
  }
}

Plugin Hooks

Plugins can provide hooks that integrate with user and project hooks.

How Plugin Hooks Work

• Plugin hooks defined in hooks/hooks.json or custom path via hooks field
• When plugin enabled, its hooks merge with user and project hooks
• Multiple hooks from different sources can respond to same event
• Plugin hooks run alongside custom hooks in parallel

Plugin Hook Configuration

{
  "description": "Automatic code formatting",
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PLUGIN_ROOT}/scripts/format.sh",
            "timeout": 30
          }
        ]
      }
    ]
  }
}

Plugin Environment Variables

• ${CLAUDE_PLUGIN_ROOT}: Absolute path to the plugin directory
• ${CLAUDE_PROJECT_DIR}: Project root directory
• All standard environment variables available

Hooks in Skills, Agents, and Slash Commands

Hooks can be defined in frontmatter. These are scoped to the component's lifecycle.

Supported events: PreToolUse, PostToolUse, Stop

Skill Example

---
name: secure-operations
description: Perform operations with security checks
hooks:
  PreToolUse:
    - matcher: "Bash"
      hooks:
        - type: command
          command: "./scripts/security-check.sh"
---

Agent Example

---
name: code-reviewer
description: Review code changes
hooks:
  PostToolUse:
    - matcher: "Edit|Write"
      hooks:
        - type: command
          command: "./scripts/run-linter.sh"
---

once Option

Set once: true to run hook only once per session. After first successful execution, hook is removed.

Note: Only supported for skills and slash commands, not agents.

Event-Specific Matchers

PreToolUse / PermissionRequest / PostToolUse Common Matchers

SessionStart Matchers

PreCompact Matchers

Notification Matchers

Hook Input (JSON via stdin)

Common Fields (All Events)

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "cwd": "/current/working/directory",
  "permission_mode": "default",
  "hook_event_name": "PreToolUse"
}

permission_mode values: "default", "plan", "acceptEdits", "dontAsk", "bypassPermissions"

PreToolUse Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "cwd": "/path/to/project",
  "permission_mode": "default",
  "hook_event_name": "PreToolUse",
  "tool_name": "Bash",
  "tool_input": {
    "command": "psql -c 'SELECT * FROM users'",
    "description": "Query the users table",
    "timeout": 120000
  },
  "tool_use_id": "toolu_01ABC123"
}

Tool-specific tool_input fields:

PostToolUse Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "cwd": "/path/to/project",
  "permission_mode": "default",
  "hook_event_name": "PostToolUse",
  "tool_name": "Write",
  "tool_input": {
    "file_path": "/path/to/file.txt",
    "content": "file content"
  },
  "tool_response": {
    "filePath": "/path/to/file.txt",
    "success": true
  },
  "tool_use_id": "toolu_01ABC123"
}

Notification Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "cwd": "/path/to/project",
  "permission_mode": "default",
  "hook_event_name": "Notification",
  "message": "Claude needs your permission to use Bash",
  "notification_type": "permission_prompt"
}

UserPromptSubmit Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "cwd": "/path/to/project",
  "permission_mode": "default",
  "hook_event_name": "UserPromptSubmit",
  "prompt": "Write a function to calculate factorial"
}

Stop / SubagentStop Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "permission_mode": "default",
  "hook_event_name": "Stop",
  "stop_hook_active": true
}

stop_hook_active: True when Claude is already continuing due to a stop hook. Check this to prevent infinite loops.

PreCompact Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "permission_mode": "default",
  "hook_event_name": "PreCompact",
  "trigger": "manual",
  "custom_instructions": ""
}

SessionStart Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "permission_mode": "default",
  "hook_event_name": "SessionStart",
  "source": "startup"
}

SessionEnd Input

{
  "session_id": "abc123",
  "transcript_path": "/path/to/session.jsonl",
  "cwd": "/path/to/project",
  "permission_mode": "default",
  "hook_event_name": "SessionEnd",
  "reason": "exit"
}

reason values: clear, logout, prompt_input_exit, other

Hook Output

Exit Codes

Important: Claude Code does not see stdout if exit code is 0, except for UserPromptSubmit and SessionStart where stdout is added to context.

Exit Code 2 Behavior Per Event

JSON Output Control

Important: JSON output only processed with exit code 0. Exit code 2 uses stderr only.

Common JSON Fields (All Events)

{
  "continue": true,
  "stopReason": "Message shown when continue is false",
  "suppressOutput": false,
  "systemMessage": "Optional warning message shown to user"
}

Precedence: continue: false takes precedence over any decision: "block" output.

PreToolUse JSON Output

{
  "hookSpecificOutput": {
    "hookEventName": "PreToolUse",
    "permissionDecision": "allow",
    "permissionDecisionReason": "Auto-approved documentation file",
    "updatedInput": {
      "field_to_modify": "new value"
    },
    "additionalContext": "Current environment: production. Proceed with caution."
  }
}

Note: decision and reason fields are deprecated. Use hookSpecificOutput.permissionDecision and hookSpecificOutput.permissionDecisionReason. Deprecated "approve" and "block" map to "allow" and "deny".

PermissionRequest JSON Output

Allow with modified input:

{
  "hookSpecificOutput": {
    "hookEventName": "PermissionRequest",
    "decision": {
      "behavior": "allow",
      "updatedInput": {
        "command": "npm run lint"
      }
    }
  }
}

Deny with message:

{
  "hookSpecificOutput": {
    "hookEventName": "PermissionRequest",
    "decision": {
      "behavior": "deny",
      "message": "Command not allowed by policy",
      "interrupt": true
    }
  }
}

PostToolUse JSON Output

{
  "decision": "block",
  "reason": "Explanation for decision",
  "hookSpecificOutput": {
    "hookEventName": "PostToolUse",
    "additionalContext": "Additional information for Claude"
  }
}

• "block" automatically prompts Claude with reason
• undefined does nothing, reason is ignored

UserPromptSubmit JSON Output

{
  "decision": "block",
  "reason": "Prompt contains sensitive data",
  "hookSpecificOutput": {
    "hookEventName": "UserPromptSubmit",
    "additionalContext": "My additional context here"
  }
}

Two ways to add context (exit code 0):

1. Plain text stdout: Any non-JSON text is added as context
2. JSON with additionalContext: More structured control

Blocking prompts:

• "decision": "block" prevents prompt processing, erases prompt from context
• "reason" shown to user but not added to context

Stop / SubagentStop JSON Output

{
  "decision": "block",
  "reason": "Must be provided when Claude is blocked from stopping"
}

• "block" prevents Claude from stopping. Must populate reason
• undefined allows Claude to stop. reason is ignored

SessionStart JSON Output

{
  "hookSpecificOutput": {
    "hookEventName": "SessionStart",
    "additionalContext": "Project context loaded successfully"
  }
}

Note: Multiple hooks' additionalContext values are concatenated.

Prompt-Based Hooks

LLM-evaluated decisions using a fast model (Haiku).

How Prompt-Based Hooks Work

1. Send the hook input and your prompt to Haiku
2. The LLM responds with structured JSON containing a decision
3. Claude Code processes the decision automatically

Configuration

{
  "type": "prompt",
  "prompt": "Evaluate if Claude should stop: $ARGUMENTS. Check if all tasks are complete.",
  "timeout": 30
}

Response Schema

The LLM must respond with JSON:

{
  "ok": true,
  "reason": "Explanation for the decision"
}

$ARGUMENTS Placeholder

Use $ARGUMENTS in prompt to include hook input JSON. If omitted, input is appended to the prompt.

Example: Intelligent Stop Hook

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "prompt",
            "prompt": "You are evaluating whether Claude should stop working. Context: $ARGUMENTS\n\nAnalyze the conversation and determine if:\n1. All user-requested tasks are complete\n2. Any errors need to be addressed\n3. Follow-up work is needed\n\nRespond with JSON: {\"ok\": true} to allow stopping, or {\"ok\": false, \"reason\": \"your explanation\"} to continue working.",
            "timeout": 30
          }
        ]
      }
    ]
  }
}

Example: SubagentStop Validation

{
  "hooks": {
    "SubagentStop": [
      {
        "hooks": [
          {
            "type": "prompt",
            "prompt": "Evaluate if this subagent should stop. Input: $ARGUMENTS\n\nCheck if:\n- The subagent completed its assigned task\n- Any errors occurred that need fixing\n- Additional context gathering is needed\n\nReturn: {\"ok\": true} to allow stopping, or {\"ok\": false, \"reason\": \"explanation\"} to continue."
          }
        ]
      }
    ]
  }
}

Best Use Cases

Comparison with Command Hooks

Best Practices for Prompt Hooks

1. Be specific in prompts - Clearly state what you want the LLM to evaluate
2. Include decision criteria - List the factors the LLM should consider
3. Test your prompts - Verify the LLM makes correct decisions for your use cases
4. Set appropriate timeouts - Default is 30 seconds, adjust if needed
5. Use for complex decisions - Bash hooks are better for simple, deterministic rules

Environment Variables

SessionStart Environment Persistence

Example: Setting individual environment variables

#!/bin/bash
if [ -n "$CLAUDE_ENV_FILE" ]; then
  echo 'export NODE_ENV=production' >> "$CLAUDE_ENV_FILE"
  echo 'export API_KEY=your-api-key' >> "$CLAUDE_ENV_FILE"
  echo 'export PATH="$PATH:./node_modules/.bin"' >> "$CLAUDE_ENV_FILE"
fi
exit 0

Example: Persisting all environment changes (e.g., nvm use)

#!/bin/bash
ENV_BEFORE=$(export -p | sort)

# Run setup commands that modify environment
source ~/.nvm/nvm.sh
nvm use 20

if [ -n "$CLAUDE_ENV_FILE" ]; then
  ENV_AFTER=$(export -p | sort)
  comm -13 <(echo "$ENV_BEFORE") <(echo "$ENV_AFTER") >> "$CLAUDE_ENV_FILE"
fi
exit 0

Variables in $CLAUDE_ENV_FILE are sourced before each Bash command.

Working with MCP Tools

Claude Code hooks work with Model Context Protocol (MCP) tools.

MCP Tool Naming

MCP tools follow the pattern mcp__<server>__<tool>:

• mcp__memory__create_entities - Memory server's create entities tool
• mcp__filesystem__read_file - Filesystem server's read file tool
• mcp__github__search_repositories - GitHub server's search tool

Configuring Hooks for MCP Tools

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "mcp__memory__.*",
        "hooks": [
          {
            "type": "command",
            "command": "echo 'Memory operation initiated' >> ~/mcp-operations.log"
          }
        ]
      },
      {
        "matcher": "mcp__.*__write.*",
        "hooks": [
          {
            "type": "command",
            "command": "/home/user/scripts/validate-mcp-write.py"
          }
        ]
      }
    ]
  }
}

Execution Details

Output Handling by Event

Security Considerations

Disclaimer

USE AT YOUR OWN RISK: Claude Code hooks execute arbitrary shell commands on your system automatically. By using hooks, you acknowledge that:

• You are solely responsible for the commands you configure
• Hooks can modify, delete, or access any files your user account can access
• Malicious or poorly written hooks can cause data loss or system damage
• Anthropic provides no warranty and assumes no liability for any damages
• You should thoroughly test hooks in a safe environment before production use

Security Best Practices

1. Validate and sanitize inputs - Never trust input data blindly
2. Always quote shell variables - Use "$VAR" not $VAR
3. Block path traversal - Check for .. in file paths
4. Use absolute paths - Specify full paths for scripts (use $CLAUDE_PROJECT_DIR)
5. Skip sensitive files - Avoid .env, .git/, keys, etc.

Configuration Safety

Direct edits to hooks in settings files don't take effect immediately:

1. Hooks snapshot captured at startup
2. Snapshot used throughout the session
3. Warns if hooks are modified externally
4. Requires review in /hooks menu for changes to apply

This prevents malicious hook modifications from affecting your current session.

Debugging

Enable Debug Mode

claude --debug
claude --debug "hooks"  # Filter to hooks only

Debug Output Example

[DEBUG] Executing hooks for PostToolUse:Write
[DEBUG] Getting matching hook commands for PostToolUse with query: Write
[DEBUG] Found 1 hook matchers in settings
[DEBUG] Matched 1 hooks for query "Write"
[DEBUG] Found 1 hook commands to execute
[DEBUG] Executing hook command: <Your command> with timeout 60000ms
[DEBUG] Hook command completed with status 0: <Your stdout>

Basic Troubleshooting

1. Check configuration - Run /hooks to see if your hook is registered
2. Verify syntax - Ensure your JSON settings are valid
3. Test commands - Run hook commands manually first
4. Check permissions - Make sure scripts are executable
5. Review logs - Use claude --debug to see hook execution details

Common Issues

Test Commands Manually

echo '{"tool_name":"Write","tool_input":{"file_path":"test.txt"}}' | ./your-hook.sh

Code Examples

Python: Bash Command Validation (Exit Code)

#!/usr/bin/env python3
import json
import re
import sys

# Define validation rules as (regex pattern, message) tuples
VALIDATION_RULES = [
    (
        r"\bgrep\b(?!.*\|)",
        "Use 'rg' (ripgrep) instead of 'grep' for better performance",
    ),
    (
        r"\bfind\s+\S+\s+-name\b",
        "Use 'rg --files -g pattern' instead of 'find -name'",
    ),
]

def validate_command(command: str) -> list[str]:
    issues = []
    for pattern, message in VALIDATION_RULES:
        if re.search(pattern, command):
            issues.append(message)
    return issues

try:
    input_data = json.load(sys.stdin)
except json.JSONDecodeError as e:
    print(f"Error: Invalid JSON input: {e}", file=sys.stderr)
    sys.exit(1)

tool_name = input_data.get("tool_name", "")
tool_input = input_data.get("tool_input", {})
command = tool_input.get("command", "")

if tool_name != "Bash" or not command:
    sys.exit(0)

issues = validate_command(command)

if issues:
    for message in issues:
        print(f"• {message}", file=sys.stderr)
    # Exit code 2 blocks tool call and shows stderr to Claude
    sys.exit(2)

Python: UserPromptSubmit Context and Validation (JSON Output)

#!/usr/bin/env python3
import json
import sys
import re
import datetime

try:
    input_data = json.load(sys.stdin)
except json.JSONDecodeError as e:
    print(f"Error: Invalid JSON input: {e}", file=sys.stderr)
    sys.exit(1)

prompt = input_data.get("prompt", "")

# Check for sensitive patterns
sensitive_patterns = [
    (r"(?i)\b(password|secret|key|token)\s*[:=]", "Prompt contains potential secrets"),
]

for pattern, message in sensitive_patterns:
    if re.search(pattern, prompt):
        # Use JSON output to block with a specific reason
        output = {
            "decision": "block",
            "reason": f"Security policy violation: {message}. Please rephrase without sensitive information."
        }
        print(json.dumps(output))
        sys.exit(0)

# Add current time to context
context = f"Current time: {datetime.datetime.now()}"
print(context)

# Equivalent JSON approach:
# print(json.dumps({
#   "hookSpecificOutput": {
#     "hookEventName": "UserPromptSubmit",
#     "additionalContext": context,
#   },
# }))

sys.exit(0)

Python: PreToolUse Auto-Approval (JSON Output)

#!/usr/bin/env python3
import json
import sys

try:
    input_data = json.load(sys.stdin)
except json.JSONDecodeError as e:
    print(f"Error: Invalid JSON input: {e}", file=sys.stderr)
    sys.exit(1)

tool_name = input_data.get("tool_name", "")
tool_input = input_data.get("tool_input", {})

# Auto-approve file reads for documentation files
if tool_name == "Read":
    file_path = tool_input.get("file_path", "")
    if file_path.endswith((".md", ".mdx", ".txt", ".json")):
        output = {
            "hookSpecificOutput": {
                "hookEventName": "PreToolUse",
                "permissionDecision": "allow",
                "permissionDecisionReason": "Documentation file auto-approved"
            },
            "suppressOutput": True
        }
        print(json.dumps(output))
        sys.exit(0)

# Let normal permission flow proceed
sys.exit(0)

Node.js: SessionStart Context Injection

#!/usr/bin/env node

const output = {
  hookSpecificOutput: {
    hookEventName: "SessionStart",
    additionalContext: `<project-context>
Environment: ${process.env.NODE_ENV || "development"}
Node version: ${process.version}
Working directory: ${process.cwd()}
</project-context>`,
  },
};

console.log(JSON.stringify(output));

Examples

Code Formatting (PostToolUse)

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "prettier --write \"$CLAUDE_PROJECT_DIR\"/**/*.{js,ts,json}"
          }
        ]
      }
    ]
  }
}

File Protection (PreToolUse)

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "./scripts/check-protected-files.sh"
          }
        ]
      }
    ]
  }
}

Custom Notifications

{
  "hooks": {
    "Notification": [
      {
        "matcher": "permission_prompt",
        "hooks": [
          {
            "type": "command",
            "command": "/path/to/permission-alert.sh"
          }
        ]
      },
      {
        "matcher": "idle_prompt",
        "hooks": [
          {
            "type": "command",
            "command": "/path/to/idle-notification.sh"
          }
        ]
      }
    ]
  }
}

Task Verification (Stop)

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "prompt",
            "prompt": "Verify task completion. Check edge cases. Return {\"ok\": true} or {\"ok\": false, \"reason\": \"...\"}."
          }
        ]
      }
    ]
  }
}

Sources

• Hooks Reference (January 2026)
• Hooks Guide
• Settings Reference
• Plugin Components Reference