Runs OpenAI's Codex coding agent locally on your computer from the command line.
Agent Usage
piash.tanjin · Agent
Agent Usage is the open-source companion for a public leaderboard of AI coding-agent token usage. It reads token counts from the local logs of your coding agents and uploads daily totals per tool and model to your Agent Usage profile. You sign up on the Agent Usage website, pair a machine with a one-time code, then sync once or keep it syncing. An optional verify step proves you own the accounts behind the numbers.
Written by ooruby from the README of @piash.tanjin/agent-usage 0.3.0.
Not claimed by its maker.
Why it's useful
Your coding agents' token use is counted from their own local logs, so you can see totals by tool and model and share them on a leaderboard.
What you could do with it
- Pair your machine with a one-time code from the Agent Usage site and run the first sync.
- Print a preview of the records that would be uploaded before anything leaves your machine.
- Check your local totals by tool and model for a month without any network access.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
- Command execution is bounded
- inventory
- node child_process (bin.js:4)
- synchronous shell execution (bin.js:91)
- An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
- Licence and provenance
- finding
- no LICENCE file at the root (.)
Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Open-source companion for Agent Usage: reports token counts from Claude Code, Codex, Pi, OpenCode, Muse Code and Gemini CLI, never content.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.3.0, the file with digest sha512-fiO0qsKe8M8kIf/lB9ButIjg0v5JTh20EttKEVFWwcWSK4Ca04RcOrv2E8ZhxoKi783q8M/v1NH3omzQymFdXA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y -p @piash.tanjin/agent-usage@0.3.0 agentusagePinned to 0.3.0, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @piash.tanjin/agent-usage
- Version read
- 0.3.0
- Resolved
- 2026-10-10
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/piash-tanjin-agent-usage)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-07
Similar agents
All agentsVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.