open source · MIT★ star it on GitHubfound a bug, or want an agent supported?open an issuebuilt in the open, receipts included
skip to content
tokenchitv0.10.0 · MIT

Supported agent

Your Codex usage, as a file in your repo.

tokenchit reads the Codex logs already on your machine and renders one embeddable card straight into your repository. The card is a file you commit, not a URL you depend on — nothing to rate-limit, nothing to go down.

$ npx -y @tokenchit/cli@latest generate

Free and MIT. No account is needed to read your own numbers — publishing to the board is a separate, opt-in command.

[ 01 ]

What it reads

Codex writes one rollout file per session, under a dated directory tree. Token counts come from the same usage records the API returned.

Source~/.codex/sessions/**/rollout-*.jsonl

Nothing else is read, and nothing is sent. tokenchit sync and tokenchit recap make no network request at all; five tests in the repo fail on every push if that stops being true.

[ 02 ]

What it cannot tell you

There is no cumulative cache to fall back on

Unlike Claude Code, Codex keeps no running total outside the transcripts. That makes the figure straightforward while the files are there, and unrecoverable once they are gone: a number derived from logs cannot include logs that no longer exist. tokenchit banks each day it sees in a local ledger so a later rotation does not erase history it has already read.

Equivalent cost is not what you paid either. It is what these tokens would cost at list API rates, and most agent usage runs under a subscription where no per-token charge ever happens.

[ 03 ]

On the board, by codex

Developers who chose to publish, ranked by codex tokens over the last year. Figures are self-reported and bounded for plausibility, not audited.

RankDevelopercodex tokensEquiv. cost
1@Rupam-M138B$64,573
2@bucharitesh19.6B$5,709
3@VinayakRai514.7B$5,123
4@manishreddy1237.57B$3,435
5@iyashjayesh4.55B$35
6@NVJKKartik2.26B$505
7@crazyparadox1.61B$365
8@MridulaSivanandan1.39B$687
9@praveenMalagudi1.14B$863
10@veerLakshya787M$362
See the full board →
[ 04 ]

The other agents

One command covers all of them at once, and the card shows the mix.

Detected and deliberately unsupported: Copilot CLI records only a live context gauge, so there is no per-call token count to read.

Read your own numbers

One command. It finds your agents, shows your stats and writes the card. Publishing is a separate step you have to ask for.

$ npx -y @tokenchit/cli@latest generate

Or tokenchit sync on its own to see the figures without writing anything. Source at github.com/iyashjayesh/tokenchit.

Who is burning the most?

Ranked by tokens, from developers who chose to publish. The two windows disagree on purpose — one rewards the last month, the other the whole history.

Last 30 days

All time

Top 8 of each. A means the GitHub identity was proved; everything else is self-reported.

See the full board →