Aireceipts

Your AI coding agent used millions of tokens. Here is the observable cost floor.

not a mockup — a real receipt on a merged PR of this repo. The screenshot predates the current ≥ $X notation.
Read it live.

The meter runs while the agent drives · the receipt prints when the ride ends · and sticks with the PR

Why this exists. AI coding-agent usage is usually invisible — you see the diff,
not the token ledger. aireceipts reconstructs an observable Standard-API list-price
floor: live in your status bar, itemized when the session ends, attached to the PR.
It is not an invoice or subscription allocation. Local and deterministic —
transcripts never leave your machine, and a shared receipt carries figures plus the
session's one-line title (drawn from your opening prompt, truncated) — never your
diff, file contents, or transcript (how).

Start here — the meter, the receipt, the PR

Try it in ten seconds: npx aireceipts-cli — no install, no account (--demo shows a bundled example if you have no sessions yet). Then let it run like a cab ride:

1 · While the agent works — the meter. One settings line (setup)
pins aireceipts statusline under Claude Code's input box — and tmux, starship, or
PowerShell give Codex and OpenCode the same bar — ticking up as the session runs:

The line, segment by segment:

When a detector finds a stuck retry loop, a heuristic pattern flag appears right
on the line; it is evidence to inspect, not a proven savings claim.

2 · When the session ends — the receipt. npx aireceipts-cli prints the itemized
receipt — cited floors on priceable tool rows, tokens-only buckets where evidence
is insufficient, heuristic patterns flagged (loops, context thrash, trivial spans), and the
cheaper-model line as arithmetic, not a prediction. The exact bytes:

The final…