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

How to ship one approved feature with a second-agent check with Pullboard

File a spec-linked item, let a builder claim and submit it, then have a verifier accept or reject the exact commit.

Who it is forA developer with an approved requirement who wants a builder agent to implement it and a separate agent to check the result.

The problemAgent output is often merged on trust, and no one checks it against the requirement it was supposed to meet.

The outcomeThe feature lands only after a different agent verifies the submitted commit against the approved row, with evidence recorded.

What you need first

  • Git installed
  • Node 22.13 or newer
  • A git repository to work in (the tour uses a throwaway repo)
  • npm, to install the pullboard package

Steps

  1. pullboard add web "Checkout" --specs G1 --criterion "card payment takes one step"
  2. pullboard worktree web --model "$PULLBOARD_MODEL", then cd into the worktree it prints and run pullboard next and pullboard submit 1.
  3. pullboard worktree review --model "$PULLBOARD_MODEL", then cd into that worktree and run pullboard next --verify.
  4. pullboard verify 1 accept --note "paid in one step; without the fix the test fails"

Prompt for your agent

In the repo <path>, file a Pullboard item linked to approved spec row G1, have a builder agent claim and submit it, then have a separate verifier agent run `pullboard verify <id> accept` or reject with a reason. Report the verdict and the note. Verify that the verifier checked out the exact submitted commit before deciding.

Caveat. The example commands use placeholder names like web and G1, and the gate in Pullboard.json must run your real tests, or submits will not be green.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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