Skip to main content
command official · Anthropic

help · anthropics — Claude Code command: hookify plugin reference

Prints the hookify plugin reference: which events it hooks, how rule files are shaped, and what else the plugin can do.

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin install hookify@claude-plugins-official
Open on GitHub

What help does

/hookify:help is the built-in reference for the hookify plugin. It reads and explains — it does not touch your rules or your project.

The help text lays out the machinery. Hookify installs generic hooks on PreToolUse, PostToolUse, Stop and UserPromptSubmit, and those hooks read rule files from .claude/hookify.*.local.md. A rule carries name, enabled, event and pattern in its frontmatter, with the pattern written as a Python regex. Whatever sits in the message body is what Claude sees when the rule fires. Edits apply on the next tool call, so no restart is involved.

One thing worth knowing before you write rules: the help page tells you to test a pattern on its own with python3 -c "import re; print(re.search('your_pattern', 'test_text'))". Without Python 3 on the machine that check is unavailable, and a pattern that never matches is hard to debug. Keep the rule files out of version control — they are local to your setup.

What it helps with

  • recall the frontmatter fields a hookify rule needs
  • find out which events the plugin hooks into
  • test a regex before a rule starts blocking work
  • locate the other plugin commands for listing and configuring rules

Example prompts for the agent

  • /hookify:help
  • /hookify:help — explain the stop and prompt events
  • /hookify:help, my rule never triggers

How to install help

1Plugin marketplace

/plugin install hookify@claude-plugins-official

2Manually: put the files in place

.claude/commands/hookify-help.md

The built-in /help overrides a file with the same name, so the file is renamed. Call it with /hookify-help. For all projects use ~/.claude/commands/

Questions about help

How do I install help in Claude?

Add the marketplace first, then install the plugin: /plugin install hookify@claude-plugins-official. The command is then available as /hookify:help.

What does the help command do?

It prints the hookify plugin reference: how the hooks work, the rule file format, the available commands and common failure modes.

Do I need to restart Claude after editing a rule?

No. The .local.md files are read dynamically, so a rule takes effect on the next tool use.

Source text

help.md · Apache-2.0
---
description: Get help with the hookify plugin
allowed-tools: ["Read"]
---

# Hookify Plugin Help

Explain how the hookify plugin works and how to use it.

## Overview

The hookify plugin makes it easy to create custom hooks that prevent unwanted behaviors. Instead of editing `hooks.json` files, users create simple markdown configuration files that define patterns to watch for.

## How It Works

### 1. Hook System

Hookify installs generic hooks that run on these events:
- **PreToolUse**: Before any tool executes (Bash, Edit, Write, etc.)
- **PostToolUse**: After a tool executes
- **Stop**: When Claude wants to stop working
- **UserPromptSubmit**: When user submits a prompt

These hooks read configuration files from `.claude/hookify.*.local.md` and check if any rules match the current operation.

### 2. Configuration Files

Users create rules in `.claude/hookify.{rule-name}.local.md` files:

```markdown
---
name: warn-dangerous-rm
enabled: true
event: bash
pattern: rm\s+-rf
---

⚠️ **Dangerous rm command detected!**

This command could delete important files. Please verify the path.
```

**Key fields:**
- `name`: Unique identifier for the rule
- `enabled`: true/false to activate/deactivate
- `event`: bash, file, stop, prompt, or all
- `pattern`: Regex pattern to match

The message body is what Claude sees when the rule triggers.

### 3. Creating Rules

**Option A: Use /hookify command**
```
/hookify Don't use console.log in production files
```

This analyzes your request and creates the appropriate rule file.

**Option B: Create manually**
Create `.claude/hookify.my-rule.local.md` with the format above.

**Option C: Analyze conversation**
```
/hookify
```

Without arguments, hookify analyzes recent conversation to find behaviors you want to prevent.

## Available Commands

- **`/hookify`** - Create hooks from conversation analysis or explicit instructions
- **`/hookify:help`** - Show this help (what you're reading now)
- **`/hookify:list`** - List all configured hooks
- **`/hookify:configure`** - Enable/disable existing hooks interactively

## Example Use Cases

**Prevent dangerous commands:**
```markdown
---
name: block-chmod-777
enabled: true
event: bash
pattern: chmod\s+777
---

Don't use chmod 777 - it's a security risk. Use specific permissions instead.
```

**Warn about debugging code:**
```markdown
---
name: warn-console-log
enabled: true
event: file
pattern: console\.log\(
---

Console.log detected. Remember to remove debug logging before committing.
```

**Require tests before stopping:**
```markdown
---
name: require-tests
enabled: true
event: stop
pattern: .*
---

Did you run tests before finishing? Make sure `npm test` or equivalent was executed.
```

## Pattern Syntax

Use Python regex syntax:
- `\s` - whitespace
- `\.` - literal dot
- `|` - OR
- `+` - one or more
- `*` - zero or more
- `\d` - digit
- `[abc]` - character class

**Examples:**
- `rm\s+-rf` - matches "rm -rf"
- `console\.log\(` - matches "console.log("
- `(eval|exec)\(` - matches "eval(" or "exec("
- `\.env$` - matches files ending in .env

## Important Notes

**No Restart Needed**: Hookify rules (`.local.md` files) take effect immediately on the next tool use. The hookify hooks are already loaded and read your rules dynamically.

**Block or Warn**: Rules can either `block` operations (prevent execution) or `warn` (show message but allow). Set `action: block` or `action: warn` in the rule's frontmatter.

**Rule Files**: Keep rules in `.claude/hookify.*.local.md` - they should be git-ignored (add to .gitignore if needed).

**Disable Rules**: Set `enabled: false` in frontmatter or delete the file.

## Troubleshooting

**Hook not triggering:**
- Check rule file is in `.claude/` directory
- Verify `enabled: true` in frontmatter
- Confirm pattern is valid regex
- Test pattern: `python3 -c "import re; print(re.search('your_pattern', 'test_text'))"`
- Rules take effect immediately - no restart needed

**Import errors:**
- Check Python 3 is available: `python3 --version`
- Verify hookify plugin is installed correctly

**Pattern not matching:**
- Test regex separately
- Check for escaping issues (use unquoted patterns in YAML)
- Try simpler pattern first, then refine

## Getting Started

1. Create your first rule:
   ```
   /hookify Warn me when I try to use rm -rf
   ```

2. Try to trigger it:
   - Ask Claude to run `rm -rf /tmp/test`
   - You should see the warning

4. Refine the rule by editing `.claude/hookify.warn-rm.local.md`

5. Create more rules as you encounter unwanted behaviors

For more examples, check the `${CLAUDE_PLUGIN_ROOT}/examples/` directory.

© Anthropic · Apache-2.0 · anthropics/claude-plugins-official

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

help by other authors comes first.

help official Anthropic Explains the Ralph Loop technique, its iterative cycle, and the commands for starting or cancelling it. Useful when a task needs repeated passes toward a clear result. ★ 44,635repo stars setup-development-environment davila7 A slash command that builds out a dev environment: runtimes, tooling, build setup, linters, configs. Handy when you spin up a project on a fresh machine. 651installs perl-security affaan-m Enforces Perl security practices: taint mode handling, allowlist input validation, three-argument open, safe execution, and DBI placeholders. CX Codex +1 4,800installs caveman-help JuliusBrussee A quick reference for Caveman modes and commands in Claude Code and other supported hosts. Use it when you need to control response style or find related skills. CX Codex +1 402,900installs kql microsoft This skill helps agents write, debug, and review KQL queries. Use it for ADX, Log Analytics, Sentinel, and other Microsoft data services. 58installs ponytail-help DietrichGebert Shows a quick reference card for ponytail levels, skills, and configuration inside the chat. Useful when you need command triggers without leaving your editor. CX Codex +1 42,900installs security-hardening Seth Hobson This command runs a staged security review: vulnerability scanning, threat modeling, and architecture checks. Use it when a project needs a documented hardening pass. CX Codex 437installs create-architecture-documentation davila7 A Claude slash command that turns your repo into architecture documentation: diagrams, ADRs and component descriptions. 6,136installs refactor-code davila7 A slash command that walks Claude through 17 refactoring steps, from analysis and tests to performance checks and review prep. 4,890installs

From the same set123

The whole set →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor