hookify-rules
Helps your agent create rules to control its behavior. It can block dangerous actions or show warnings, ensuring more safety.
What it does
This tool helps create rules to "watch" what the AI does. It can warn or block specific actions, like running dangerous commands or editing sensitive files, by defining text patterns.
When to use it
- ✓When you want to prevent the AI from running risky commands.
- ✓To stop the AI from modifying important files without permission.
- ✓When you want the AI to show a warning before performing certain actions.
Example of what to ask your AI
“Create a rule to warn if the AI tries to use the 'rm -rf' command.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You write a configuration file with a name, the type of event to watch (like commands or files), a text pattern (using regular expressions), and the message to display. The AI checks if what it's about to do matches this pattern.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add affaan-m/ECC --skill hookify-rulesOr download just the file:
curl -L https://raw.githubusercontent.com/affaan-m/ECC/main/skills/hookify-rules/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Writing Hookify Rules
Overview
ECC evaluates project-local Hookify rules with its built-in Node runtime. No separate Hookify plugin or Python installation is required when ECC hooks are enabled.
Hookify rules are markdown files with YAML frontmatter that define patterns to watch for and messages to show when those patterns match. Rules are stored in .claude/hookify.{rule-name}.local.md files.
Rule File Format
Basic Structure
---
name: rule-identifier
enabled: true
event: bash|file|stop|prompt|all
pattern: regex-pattern-here
---
Message to show Claude when this rule triggers.
Can include markdown formatting, warnings, suggestions, etc.
Frontmatter Fields
| Field | Required | Values | Description |
|---|---|---|---|
| name | Yes | kebab-case string | Unique identifier (verb-first: warn-, block-, require-*) |
| enabled | Yes | true/false | Toggle without deleting |
| event | Yes | bash/file/stop/prompt/all | Which hook event triggers this |
| action | No | warn/block | warn (default) shows message; block prevents operation |
| pattern | Yes* | regex string | Pattern to match (*or use conditions for complex rules) |
Advanced Format (Multiple Conditions)
---
name: warn-env-api-keys
enabled: true
event: file
conditions:
- field: file_path
operator: regex_match
pattern: \.env$
- field: new_text
operator: contains
pattern: API_KEY
---
You're adding an API key to a .env file. Ensure this file is in .gitignore!
Condition fields by event:
- bash:
command - file:
file_path,new_text,old_text,content - prompt:
user_prompt
Operators: regex_match, contains, equals, not_contains, starts_with, ends_with
All conditions must match for rule to trigger.
Event Type Guide
bash Events
Match Bash command patterns:
- Dangerous commands:
rm\s+-rf,dd\s+if=,mkfs - Privilege escalation:
sudo\s+,su\s+ - Permission issues:
chmod\s+777
file Events
Match Edit/Write/MultiEdit operations:
- Debug code:
console\.log\(,debugger - Security risks:
eval\(,innerHTML\s*= - Sensitive files:
\.env$,credentials,\.pem$
stop Events
Completion checks and reminders. Pattern .* matches always.
prompt Events
Match user prompt content for workflow enforcement.
Pattern Writing Tips
Regex Basics
- Escape special chars:
.to\.,(to\( \swhitespace,\ddigit,\wword char+one or more,*zero or more,?optional|OR operator
Common Pitfalls
- Too broad:
logmatches "login", "dialog" — useconsole\.log\( - Too specific:
rm -rf /tmp— userm\s+-rf - YAML escaping: Use unquoted patterns; quoted strings need
\\s
Testing
python3 -c "import re; print(re.search(r'your_pattern', 'test text'))"
Avoid nested quantifiers such as (a+)+. The runtime rejects patterns with
common catastrophic-backtracking shapes because rules run synchronously in the
hook path, and every regex evaluation has a 25 ms hard timeout. Invalid,
symlinked, or oversized local rules fail open and emit a
diagnostic without disabling other Hookify rules.
Git-tracked local rules are disabled by default. Set
ECC_HOOKIFY_ALLOW_TRACKED=1 only after reviewing those files; ordinary
gitignored rules created locally remain active without that override.
Runtime Behavior
warninjects the message as event-specific additional context and does not block.blockdenies matching Bash, PowerShell, Write, Edit, or MultiEdit calls before execution.- On prompt, post-tool, and stop events,
blockuses Claude Code's structured block decision. - Stop rules skip recursive
stop_hook_activeevents to prevent infinite continuation loops.
File Organization
- Location:
.claude/directory in project root - Naming:
.claude/hookify.{descriptive-name}.local.md - Gitignore: Add
.claude/*.local.mdto.gitignore
Commands
/hookify [description]- Create new rules (auto-analyzes conversation if no args)/hookify-list- View all rules in table format/hookify-configure- Toggle rules on/off interactively/hookify-help- Full documentation
Quick Reference
Minimum viable rule:
---
name: my-rule
enabled: true
event: bash
pattern: dangerous_command
---
Warning message here
FAQ
What are 'events'?
Events are the moments when the AI might perform an action you want to watch, such as running a terminal command (bash), editing a file (file), or when it stops processing (stop).
What is a 'pattern'?
It's a text you define for the AI to look for. It can be an exact word or a more complex pattern using something called 'regular expressions' to find variations.
What's the difference between 'warn' and 'block'?
'Warn' shows a message to the AI, but it can continue. 'Block' completely prevents the action.
Details
Original description by the author
Create and configure hookify rules — markdown files with YAML frontmatter that match bash, file, prompt, or stop events by regex or conditions and show warn/block messages to the agent. Use when creating a hookify rule, writing hook rule syntax, configuring hookify, or adding pattern guardrails such as blocking dangerous commands, .env edits, or debug code.
repo: affaan-m/ECC
Popularity
- GitHub stars
- 280k
- Ranking position
- #211
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
accessibility
Helps your agent create interfaces that everyone can use. Ensures websites and apps work well for people with disabilities, like those who are blind or have reduced mobility.
affaan-m/ECC
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC
Similar skills
template-skill
This is a generic template for new skills. It needs a specific description to be useful.
anthropics/skills
shipping-and-launch
Prepares your code to be safely launched into production. Helps ensure everything is ready, monitored, and has a rollback plan.
addyosmani/agent-skills
using-agent-skills
Has your agent discover and use other skills. It's useful for deciding which tool or workflow to use for a specific task.
addyosmani/agent-skills