TokenTracker
Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness, with native apps. Never reads prompts.
Runssource: GitHubhomepageJavaScriptMITcommit 0421f06af6a4
JavaScript, MIT licensed. The project labels itself: ai coding tools, ai tools, antigravity, claude code, cli, codex cli, cost tracker and cursor.
TokenTracker runs. An Argusic agent installed it in 25 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 3052 CLI tests pass with 0 failures; the tokentracker serve command starts and returns HTTP 200 on port 7680
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Vite dashboard dependencies not installed (e.g. @vitejs/plugin-react, @testing-library/react), causing vite-pet-api and TS guardrails tests to fail3 minutes
- System Node.js v18.19.1 does not meet engine requirement >=20; node:sqlite not available2 minutes
- sqlite3 CLI binary not found in PATH, causing graph-importer and several copilot parser tests to fail2 minutes
- node:sqlite built-in module requires --experimental-sqlite flag on Node 221 minute
- Node 22 cannot import .ts files without --experimental-strip-types flag1 minute
- dashboard/dist/ directory missing, causing init-local-runtime-reinstall test to fail1 minute
- Install time
- 25 minutes
- Cold machine to finish
- 26 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- npm test exited 0, 3052 passed, 0 failed, 9 skipped
- Model tokens used
- 103,743
- Exact commit tested
- 0421f06af6a4
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
cd /work/repo && npm test 2>&1 | grep -E "''^# tests|''^# fail|''^# skip|''^# duration"' in /work/r… succeeded in 73580ms: # tests 3052 # fail 0 # skipped 9 # duration_ms 73561.328734 Here's the final summary of everything done. 2026-10-05T04:42:11.833228Z ERROR codex_core::session: failed to record rollout items: thread 01a10… 2026-10-05T04:42:11.833330Z ERROR codex_core::session: failed to record rollout items: thread 01a10… tokens used 103,743 Here's the final summary of everything done.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 25 minutes.
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-coding-toolsai-toolsantigravityclaude-codeclicodex-clicost-trackercursordashboarddesktop-petdesktop-widgetdeveloper-toolsgemini-clilocal-firstmacos-appobservabilityprivacy-firsttoken-trackerusage-trackerwindows-app
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/tokentracker)Questions
- Does TokenTracker run?
- Yes. TokenTracker runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test TokenTracker?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0421f06af6a4. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test TokenTracker?
- The run that produced this verdict cost $0.21: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does TokenTracker take to install?
- 25 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does TokenTracker need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing TokenTracker?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for TokenTracker?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.