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

codex-insights

v0.0.1

Published

Local-first Codex adoption coach for session analytics, friction detection, and workflow insights.

Vulnerabilities

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

Links

Git

Maintainers

rthakorrthakor

Keywords

codexcodex-clitokensusageanalyticsdashboardspendcost

Readme

codex-insights

See whether you are adopting Codex efficiently. Local-first coach, zero telemetry.

What It Is

codex-insights reads your local Codex session logs and opens a localhost dashboard with:

  • Codex adoption score with visible subscores
  • Action-first coaching on what to fix next
  • Repeat-mistake and savings opportunities
  • Supporting analytics by session/day/model with drill-downs

Run Locally

git clone https://github.com/rahthakor/codex-insights.git
cd codex-insights
npm install
npm start

The npm package is not published yet, so the source install above is the supported path today.

Options

npm start -- --no-open       # don't auto-open browser
node src/index.js --summary  # compact JSON totals and exit
node src/index.js --json     # full parsed JSON and exit

codex-insights uses fixed port 39741. If it is busy, the CLI exits and asks you to stop the conflicting service.

Dashboard UX

  • Native date filtering with quick presets (7D, 30D, This Month, All)
  • Previous/next range stepping with [ and ] keyboard shortcuts
  • Fast refresh with clear connection status and resilient fallback to previous snapshot
  • Search shortcuts (/ or k) and native suggestions
  • Codex Adoption Coach: action-first summary, explicit trust labels, confidence-scoped trend calls, and visible score dimensions
  • Supporting analytics: response-time distribution, parallel-session signals, top tool usage, and source-backed optimization playbooks

Data Sources

  • ~/.codex/sessions/**/*.jsonl
  • ~/.codex/archived_sessions/*.jsonl (when present)
  • ~/.codex/history.jsonl (for first prompt text)
  • Respects $CODEX_HOME if set

Pricing Model

Cost uses OpenAI API-equivalent token pricing (input, cached input, output) as an estimate. This is useful for coaching and optimization trends even when you are on a subscription plan.

Privacy

All data stays local. The app only reads local files and serves a dashboard on localhost. It is not an OpenAI account-wide billing dashboard and it does not claim to measure objective code quality.

Credits

Inspired by claude-spend, with parser enhancements informed by CodexBar's Codex usage scanning approach.

License

MIT