aireceipts

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.

Multi-agent review of user-facing docs (README, docs/**, --help text) for simplicity and correctness. Use before any release, after any feature PR that touched docs, or when asked to review docs.

Autonomous CI repair loop for aireceipts: categorize the failure, fix it in an isolated worktree, iterate up to a hard cap. Use when CI is red and needs fixing, or when asked to repair a failing build/workflow.

Autonomous self-improvement loop for aireceipts: research the field, build one proven increment, prove it on a corpus the agent didn't author, land it on an integration branch. Never touches main. Use for 'keep improving aireceipts', 'run the improve loop', or /loop /improve.

Draft a new spec (SPEC-NNNN) for aireceipts. Use when the user asks to spec a feature, write/create a spec, or turn an idea into a milestone spec. Runs an interview gate before drafting — never drafts on a vague ask.

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.

Add support for a new AI coding-agent transcript format to aireceipts (e.g. a new agent besides Claude Code / Codex). Use when the user asks to support a new agent/vendor, add a transcript adapter, or parse a new log format.

Add a new waste line (a detector for a specific waste pattern, e.g. a retry loop or a needless model upgrade) to the aireceipts receipt. Use when the user asks to detect a new waste pattern, add a waste check, or flag a specific inefficiency.

Triage and fix a reported bug in aireceipts, with a red-then-green test as proof. Use when the user reports a bug, points at a failing issue, or asks to fix something broken (e.g. via an agent:fix label).

Refresh a model vendor's price table in data/prices/ with cited sources. This is the daily price-freshness loop body — use when the user asks to update prices, check for price changes, or refresh a vendor's rates.