Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it.
Kernighan's Law
AI agents are rats in a maze. They reach for what they know. And unless you show them better, what they know is slop: most software is garbage, and they'll happily imitate it.
actual issues, tells the coding agent exactly how + what to fix more catches, on real PRs →
Your taste, not the model's. Code is judged against aCORPUS.md
: ataste pack("code like dtolnay / DHH / antirez …") or your own best filesOn your personal Codex plan. stupify reviews withCodex, running on the $20-$200/month plan. API usage is roughly 50x more expensive, enjoy the subsidized tokens while they lastSlop, named. Code review is cheap. Taste is expensive. Codify the goodies, let the LLM pattern match
npx @stupify/cli
┌ stupify
◇ using integration acme-widgets
◇ VM stupify-acme-widgets created
└ stupify is provisioned for acme/widgets 👀
stupify rides on exe.dev with no keys or servers to run. Setup takes about two minutes and doesn't require payment.
npx @stupify/cli <owner/repo> # provision for a specific repo
npx @stupify/cli setup # run the reviewer on this machine instead of a VM
npx @stupify/cli status # show the latest sweep as a workflow
ssh exe.dev rm stupify-<owner>-<repo> # tear it down
Every live sweep also posts a GitHub commit status named stupify/review
on the PR head commit: pending while
queued/running, success when reviewed or policy-skipped, failure when stupify posts findings, and error when the
reviewer itself failed. Set GITHUB_STATUS=0
in ~/.stupify/config.env
to turn that off, or
GITHUB_STATUS_CONTEXT=your/context
to rename it.
The reviews run on Codex. On exe.dev that's a keyless LLM integration: it fronts your ChatGPT/Codex plan, so the VM holds no API key and your plan is billed instead. Link one once at exe.dev/integrations and provisioning attaches it for you
Don't have a corpus yet? Borrow one. Pick a programmer whose code you'd point a new hire at and review and write like them, or compose several:
dtolnay · DHH · antirez · Sindre Sorhus · Rich Harris · zod · Mitchell Hashimoto · Tanner Linsley · Simon Willison · devshorts · Jarred Sumner · browse all →
Each pack is concrete principles plus commit-pinned exemplar files. Or bring your own: point stupify at the
files you wish all your code looked like, and it scaffolds a .review/
in your repo:
npx @stupify/cli init src/best.ts src/clean-service.ts # inlines them; you add one line of "why" each
MIT © Noah Lindner. Built by the team at Bevyl. stupif.ai
, read it "stupify". PRs welcome, it'll review them 😈