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

agentcreed

v0.0.0

Published

Methodology for adding AI agents' instructions into SW projects

Readme

AgentCreed

Methodology for adding AI agents' instructions into SW projects

WARNING: This is an early stage WIP and I am not even sure whether it makes it somewhere.

Feedback and help are welcome from day one.

Motivation

I am having multiple SW projects and I am in process of improving their capabilities for AI-driven development using AI agents. Solid set of instructions is required both to improve output quality and to reduce the execution costs. Because I honor DRY principle, I don't like to repeat myself over and over again. So I am collecting the repeating patterns, evaluating what works and what doesn't and I am trying to create some baseline that can be quickly applied to any project.

Goals

To provide a set of instructions that can be quickly applied to any project, either brand new or an existing one, that will help:

  • improving AI responses making them better focused and more helpful
  • speeding up the execution
  • optimizing the credit costs
  • reducing risk of security incidents
  • following good practices to guide less skilled devs

Non-goals

AgentCreed will work best for the short-circuit human prompt -> agent response -> human review workflow.

It is - at least not yet - oriented on fully autonomous agentic systems. It is not imposing boundaries on self-operating agents. This might be a subject of later improvement.

Principles

  • This should be an univeral portable solution applicable to any AI harness tool used
  • Thus the solution is centered around AGENTS.md file which became a de-facto standard lately
  • Repeatable actions and workflows are described using Agent skills which is also a well-established tool
  • On the contrary, this project is less focused on Agents personas as this seems to be fragmented and vendor-specific (as of August 2026)
  • As I am mostly JS/TS dev now, the output will be a NPM CLI tool that can be invoked in Node-like enviroments and help to scaffold everything
  • The project will carry on universal rules and priciples while having project-specific needs in mind (e.g. via a placeholders in instruction files)
  • Instruction sets for specific languages and tools will be gradually added

MORE TBA