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

agentic-discipline

v2.1.0

Published

Install engineering discipline for AI coding agents into any repository. Compiles one canonical rule set into Claude Code, Cursor, Copilot, Windsurf, Antigravity, Gemini and AGENTS.md.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

lreyesm1999lreyesm1999

Keywords

ai-agentsagents-mdclaude-codecursorcopilotquality-gates

Readme

agentic-discipline

Install engineering discipline for AI coding agents into any repository, with one command and no runtime to manage.

npx agentic-discipline init

It detects the agent tools your repository already uses and writes each one's native format:

| Tool | Receives | |---|---| | Claude Code | .claude/skills/agentic-*/SKILL.md | | Cursor | .cursor/rules/agentic-*.mdc, scoped by globs | | GitHub Copilot | .github/instructions/agentic-*.instructions.md, scoped by applyTo | | Windsurf | .windsurf/rules/agentic-*.md, with trigger modes | | Antigravity | .agents/skills/agentic-*/SKILL.md | | Gemini CLI | GEMINI.md | | Codex, Zed, Cline, Aider, Jules | AGENTS.md | | ChatGPT | a paste-ready bundle |

All twelve disciplines are compiled from one canonical source, so the surfaces cannot drift apart, and each carries the activation metadata its host tool needs.

Two files land in your repository root - AGENTS.md and agentic.config.json. Everything else lives in .agentic/.

Usage

npx agentic-discipline init --dry-run           # preview, write nothing
npx agentic-discipline init --adapter cursor    # emit a specific surface
npx agentic-discipline adapters list            # what the compiler supports
npx agentic-discipline adapters sync            # recompile after an update
npx agentic-discipline doctor --check-tools     # verify the installation

The project control plane

The package also provides agentic, the Agentic Discipline 2 control plane: persistent project knowledge, task contracts, checkpoints another agent can resume from, isolated Git workspaces and verification evidence that goes stale when its inputs change.

npx -p agentic-discipline agentic adopt       # index this repository into .agentic/control
npx -p agentic-discipline agentic status      # knowledge, tasks, evidence at a glance
npx -p agentic-discipline agentic mcp         # stdio MCP server for your agent

Its trust boundary is one trusted user on a local filesystem; see LIMITATIONS.md.

Each command reuses the same command already on your PATH, and otherwise downloads the standalone build for your platform once and caches it under ~/.cache/agentic-discipline. Node 18 or newer. Standalone builds exist for Linux x64 and Windows x64; on macOS and other platforms, install with pipx below.

Prefer Python? pipx install agentic-discipline-kit provides both commands.

Documentation: https://github.com/lreyesm1999/agentic-discipline-kit

MIT licensed.