DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to check commit messages and staged changes against AGENTS.md with Jev Lint

Judge each commit message against its diff and each change against repo instructions.

Who it is forA developer or agent working in a repository that has an AGENTS.md file and wants commits and staged edits checked against those written rules before they are pushed.

The problemCommit messages can describe something other than the diff, and changes can break instructions the repository wrote for itself.

The outcomeA per-commit report of message-versus-diff and change-versus-instruction findings, plus a check of staged work before the commit is made.

What you need first

  • Node 24 or newer with npx
  • A TYPESAFE_API_KEY from https://typesafe.ai, set in the environment (the code being judged is sent to the API)
  • A repository with code to lint, such as a TypeScript src folder

Steps

  1. export TYPESAFE_API_KEY=...
  2. npx jev-lint commits --base main (inferred, check the README)
  3. npx jev-lint commits --staged (inferred, check the README)

Prompt for your agent

In the repository <repo-path>, with TYPESAFE_API_KEY set, run `npx jev-lint commits --base main` and then `npx jev-lint commits --staged`. Report each finding that cites an AGENTS.md instruction or a commit message mismatch, and confirm each cited instruction exists in the file.

Caveat. The README says only instructions a diff can be held against are judged, so vague guidance such as 'develop test-first' will not produce findings.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page