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

How to get a second-model review of a pull request with Agy Staff

Run agy's reviewer persona on a PR to get severity-ranked findings before merging.

Remote script. The install step pipes a script from antigravity.google straight into bash, so read the script first if your policy requires it.

Who it is forA developer using Claude Code or Codex who wants coverage from a second model family before merging a pull request.

The problemA single model reviewing its own or a teammate's change can miss issues that a different model family would catch.

The outcomeA severity-ranked list of review findings for the PR, delivered when the agy job finishes.

What you need first

  • Antigravity CLI (agy) installed and authenticated
  • Node.js installed
  • Claude Code or OpenAI Codex (Pi and OpenCode are also supported per the README)

Steps

  1. Install the Antigravity CLI with curl -fsSL https://antigravity.google/cli/install.sh | bash, then confirm with agy --version.
  2. In Claude Code, run claude plugin marketplace add keli-wen/agy-staff and then claude plugin install agy@agy-staff. In Codex, run codex plugin marketplace add https://github.com/keli-wen/agy-staff and then codex plugin add agy@agy-staff.
  3. Restart Claude Code or Codex.
  4. Run /agy:reviewer Review PR #730 in Claude Code, or $agy:reviewer Review PR #730 in Codex, replacing 730 with your PR number. (inferred, check the README)
  5. Wait for the job with the wait command the plugin prints, then read the report.

Prompt for your agent

Using the keli-wen/agy-staff plugin, run the reviewer persona on PR <PR number> in <repo>. Expect a severity-ranked list of findings. Verify that each finding names a file or line from the PR diff.

Caveat. The reviewer is prompt-based, so agy gathers the evidence itself with tools such as gh pr view and git diff, which must work in your environment.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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