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

agent-vitals

v0.1.0

Published

One command to diagnose your coding-agent setup: context bloat, unused MCP tools, wasted re-reads, plaintext secrets.

Readme

agent-vitals

One command to find out what your coding agent is really costing you.

agent-vitals demo

npx agent-vitals

agent-vitals scans your local Claude Code, Codex and Cursor setups and session history and tells you:

  • 🔑 Plaintext secrets sitting in your MCP config (API tokens in ~/.claude.json)
  • 🧟 MCP servers you never use, but still pay for in every session's context
  • 🥶 Cold-start cost: how many tokens are loaded before your first prompt is even answered
  • 🔁 Wasted re-reads: the same file read again and again with no edit in between
  • 🌊 Context floods: which tools dump the most output into your context window
  • 🪝 Broken hooks and skills that never trigger
  Health score: 35/100

Findings
  ✖ Plaintext secret in MCP server "slack" (env.SLACK_MCP_XOXP_TOKEN = xoxp…9f)
    → Move it to an env var and reference it as ${VAR}
  ▲ 5/11 MCP servers never called in 30 days: github, notion, postgres, …
    → Remove or disable them; each one adds tool schemas to context
  ▲ Median context before your first message is answered: ~60.5K tokens

Privacy

Everything runs locally. No network calls, no telemetry. Secrets are redacted in all output.

Options

| Flag | Default | | |---|---|---| | --days <n> | 30 | How much session history to analyze | | --agent <id> | all found | Limit to claude, codex or cursor (repeatable) | | --share | off | Print a screenshot-ready score card + a one-click post link (counts only, no names or paths) | | --json | off | Machine-readable output (for CI or dashboards) |

Exits with code 1 when a critical finding exists, so you can drop it into CI or a pre-commit hook.

Roadmap

  • [ ] Per-MCP-server context cost (tool schema tokens)
  • [ ] --fix to move plaintext secrets into env vars
  • [ ] Tool name/description collisions across MCP servers

Supported agents

| | Config & MCP | Secrets | Session history | Re-reads | |---|---|---|---|---| | Claude Code | ✅ ~/.claude, ~/.claude.json, .mcp.json | ✅ | ✅ | ✅ | | Codex | ✅ ~/.codex/config.toml, AGENTS.md | ✅ | ✅ | — (reads via shell) | | Cursor | ✅ ~/.cursor/mcp.json, .cursor/rules | ✅ | — (stored in SQLite, no token data) | — |

Requirements

Node.js 18+. Zero dependencies.

License

MIT