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

ai-session-analytics

v1.1.5

Published

Analyze Codex session logs and generate actionable usage, performance, and workflow analytics

Downloads

80

Readme

AI Session Analytics

Analyze your Codex sessions and discover where your time and tokens are really spent.

ai-session-analytics is a CLI tool that reads one or more Codex session logs and generates a detailed Markdown report with usage statistics, workflow insights, model breakdowns, and token analytics.

No setup required—just run it with npx.

Usage

npx ai-session-analytics

Options

| Option | Default | Description | | -------- | --------- | ------------- | | --codexPath | ~/.codex/sessions/ | Path to the Codex sessions directory. | | --currentPath | true | Analyze only sessions belonging to the current working directory. | | --resultFile | ia_session_analytics_<date> | Name of the generated report. | | --analyzeTools | [] | Tool names to analyze. Empty means all registered tools found in src/tools. | | --outputOptions | codex | Output format. More formats will be available in future releases. | | --codexModel | gpt-5.4-mini | Codex model used to generate the report when outputOptions is codex. | | --codexReasoning | low | Codex reasoning effort when outputOptions is codex. Allowed values: minimal, low, medium, high. |

Configuration is loaded with rc, so the same values can be passed as CLI flags or saved in a .codex_session_statsrc file:

{
  "codexPath": "C:/Users/you/.codex/sessions",
  "currentPath": true,
  "resultFile": "ia_session_analytics_custom",
  "analyzeTools": ["codex"],
  "outputOptions": "codex",
  "codexModel": "gpt-5.4-mini",
  "codexReasoning": "low"
}

When analyzeTools is empty, every registered tool is executed. To limit the run, set it to the tool type values you want, for example ["codex"].

Output

The generated report includes:

  • Session summary
  • Token consumption
  • Model usage
  • Workflow phases
  • Skill usage
  • Top token consumers
  • Top duration consumers
  • Executive summary

Perfect for understanding how your Codex sessions evolve, where resources are spent, and how to optimize future AI-assisted development sessions.

Roadmap

Future versions will include:

  • Additional output formats
  • Charts and visualizations
  • Multi-session comparisons
  • Cost estimation
  • Team analytics

License

MIT