npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@aman_asmuei/arules

v0.1.0

Published

The portable guardrails layer for AI companions — define what your AI can and cannot do in a single file

Readme

The portable guardrails layer for AI companions.

Define what your AI can and cannot do in a single file. Your AI reads it and respects the boundaries.

npm License: MIT acore


The Problem

Every AI session starts without boundaries. You re-explain the same rules every time: "don't push to main", "ask before deleting", "write tests for new code." Your AI has no persistent understanding of your guardrails.

The Solution

arules lets you define safety rules and permissions in a rules.md file. Your AI reads this file and respects your boundaries consistently.

npx @aman_asmuei/arules init

This creates ~/.arules/rules.md with 6 starter categories. Add it to your AI's system prompt and it follows your rules automatically.


The Ecosystem

aman
├── acore   →  identity     →  who your AI IS
├── amem    →  memory       →  what your AI KNOWS
├── akit    →  tools        →  what your AI CAN DO
├── aflow   →  workflows    →  HOW your AI works
├── arules  →  guardrails   →  what your AI WON'T do
└── aeval   →  evaluation   →  how GOOD your AI is

| Layer | Package | What it does | |:------|:--------|:-------------| | Identity | acore | Personality, values, relationship memory | | Memory | amem | Automated knowledge storage (MCP) | | Tools | akit | 15 portable AI tools (MCP + manual fallback) | | Workflows | aflow | Reusable AI workflows (code review, bug fix, etc.) | | Guardrails | arules | Safety boundaries and permissions | | Evaluation | aeval | Relationship tracking and session logging | | Unified | aman | One command to set up everything |

Each works independently. aman is the front door.


Quick Start

# Create rules.md with starter rules
npx @aman_asmuei/arules init

# List your rule categories
npx @aman_asmuei/arules list

# See rules in a category
npx @aman_asmuei/arules show Coding

# Add a custom rule
npx @aman_asmuei/arules add Security

# Remove a rule interactively
npx @aman_asmuei/arules remove

# Validate your rules.md
npx @aman_asmuei/arules check

# Health check
npx @aman_asmuei/arules doctor

Commands

| Command | What it does | |:--------|:------------| | arules | First run: create rules.md. After: show categories | | arules init | Create ~/.arules/rules.md with starter rules | | arules list | List all rule categories | | arules show <category> | Show rules in a category | | arules add [category] | Add a new rule interactively | | arules remove | Remove a rule interactively | | arules check | Validate rules.md structure | | arules doctor | Health check |

How It Works

rules.md — The Rules Definition

Every rule lives in ~/.arules/rules.md:

# My AI Rules

## Always
- Ask before deleting files or data
- Explain your reasoning before making changes
- Flag security concerns immediately
- Respect code review processes

## Never
- Push directly to main/master without approval
- Expose secrets, API keys, or credentials in code
- Make changes to production systems without confirmation
- Skip tests when fixing bugs

## Coding
- Follow existing code style and conventions
- Prefer simple solutions over clever ones
- Write tests for new functionality
- Keep PRs focused and small

Your AI reads this file and automatically respects the defined boundaries.

Platform Behavior

| Platform | What happens | |:---------|:------------| | Claude Code / Cursor | AI reads rules.md, enforces rules automatically | | ChatGPT / Gemini / Other | AI reads rules.md, follows rules during conversation |

Integration with acore

If you use acore, run acore pull --sync-only to refresh your platform files and pick up rules.md.


Starter Categories

The arules init command includes 6 categories to get started:

| Category | Rules | Examples | |:---------|:------|:---------| | Always | 4 | Ask before deleting, explain reasoning, flag security | | Never | 4 | No pushing to main, no exposed secrets, no skipping tests | | Coding | 4 | Follow code style, prefer simplicity, write tests | | Communication | 4 | Be direct, admit uncertainty, ask before assuming | | Data | 4 | No logging PII, treat data as confidential | | Team | 4 | Follow branching strategy, respect code ownership |

Privacy

All data stays local. ~/.arules/ contains your rule definitions. No telemetry. No accounts. No cloud.

Contributing

Contributions welcome! Add starter rules, improve the parser, or suggest features.

License

MIT


Define boundaries. Enforce always. Every AI.