메뉴
Teaches an agent how to drive the aireceipts CLI against real sessions — the dogfood skill. Use when asked to generate a receipt for a session, attach a cost receipt to a PR, or demonstrate/dogfood aireceipts on real transcripts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | use-aireceipts |
| description | Teaches an agent how to drive the aireceipts CLI against real sessions — the dogfood skill. Use when asked to generate a receipt for a session, attach a cost receipt to a PR, or demonstrate/dogfood aireceipts on real transcripts. |
| trigger | /use-aireceipts |
npm run build (tsup → dist/cli.js). Don't run against src/ directly — the shipped
CLI is what users get, so dogfood the built artifact.
Point the CLI at the real transcript for the session you want a receipt for — the
current Claude Code session's own log under ~/.claude/projects/**, or a Codex session
log, matching whatever adapters exist. Don't fabricate a transcript to demo against.
node dist/cli.js receipt <path-to-transcript>
Read the output: per-tool breakdown, any waste lines, the cheaper-model lines (if a comparison model was requested), and the handoff block.
$ figure trace to a matched price-table row (I2)? If the receipt shows
tokens instead of a dollar figure for part of the session, that's correct behavior for
an unmatched model/date — not a bug to "fix" by guessing a price.If the PR being reviewed was built by an agent, paste the handoff block into the PR description — this is the dogfood loop: every agent-authored PR can carry its own session's receipt as provenance.
If the receipt looks wrong (an FP waste line, a fabricated-looking number, a confusing
cheaper-model line), that's a real bug — file it via /fix-issue, don't quietly ignore it.
File an issue on this repo's GitHub tracker (anandgupta42/receipts) via `gh issue create`. Use when the user asks to file, add, or track an issue for aireceipts. This repo's issues live on GitHub — do not file them into any local or external issue tracker.
Cut an aireceipts release: verify the version tag matches the manifest, generate a changelog from conventional commits, and prep for npm publish (human clicks). Use when the user asks to release, cut a version, or publish a new version.
Adversarially validate a draft spec BEFORE the maintainer sees it. Use after write-spec finishes, or when the user asks to validate/review a spec. A draft without a validation record cannot be approved or built.
Implement an approved spec end-to-end for aireceipts, including agent-team waves for milestone (M-file) specs. Use when the user says implement/build/ship a spec (e.g. 'build SPEC-0001', 'ship M1').
Critically review an aireceipts PR as an independent critic — different model family from whoever built it, audits test-diffs hardest. Use when asked to review a PR, act as the critic, or before landing/merging any change.
Multi-persona release vetting board — PM, EM, Designer, QA personas deeply analyze the release candidate; produces the signed verdict file WITHOUT which /release refuses to proceed. Use before any release, when asked to vet a release, or when cutting a version.