Supported agent
Your Gemini CLI usage, as a file in your repo.
tokenchit reads the Gemini CLI 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 --no-publishFree and MIT · Node.js 22+ · Local stats need no account.
This command sends nothing: --no-publish returns before any networking code loads. Bare generate ends by publishing — at a terminal it asks first, in a script or CI it does not. Publishing sends daily totals by agent and model, plus your handle, and never prompts, replies or file paths.
What it reads
Gemini CLI records each model turn in a chat recording, one JSON object per line. Only turns written by recent versions carry a tokens object; the rest of the line — the prompt, the reply, the project hash — is never read.
~/.gemini/tmp/*/chats/*.jsonlNothing else is read. tokenchit sync and tokenchit recap send nothing — they make no network request at all, and five tests in the repo fail on every push if that stops being true. tokenchit publish holds the only code that uploads, and tokenchit generate ends by calling it: at a terminal it asks first, in a script or CI it does not. That is what --no-publish is for.
What it cannot tell you
Older sessions carry no counts at all
Token recording is a recent addition upstream, so an installation whose recordings predate it is genuinely uncountable rather than empty. Measured on one machine while the adapter was written: 2 of 2,141 session files carried any token field. tokenchit reports that as a partial state rather than showing a confident zero, and counts what it can actually read. Gemini's own models have no public per-token price yet, so they contribute tokens and no cost.
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.
On the board, by gemini
Developers who chose to publish, ranked by gemini tokens over the last year. Figures are self-reported and bounded for plausibility, not audited.
| Rank | Developer | gemini tokens | Equiv. cost |
|---|---|---|---|
| 1 | @Sanket758 | 142M | $42 |
The other agents
One command covers all of them at once, and the card shows the mix.
- Claude Code
~/.claude*/projects/**/*.jsonl - Codex
~/.codex/sessions/**/rollout-*.jsonl - OpenCode
~/.local/share/opencode/opencode.db
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. The command shown cannot publish. Bare generate can, and in a script or CI it does so without asking, so keep the flag for a guaranteed local run.
$ npx -y @tokenchit/cli@latest generate --no-publishOr tokenchit sync on its own to see the figures without writing anything. Source at github.com/iyashjayesh/tokenchit.