DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to watch Codex and subagent code reviews run live with Claude Code Mods

See each running code review as a line above the prompt, with its findings when it ends.

Who it is forA developer who starts Codex reviews or review subagents and wants to follow progress without switching windows.

The problemCode reviews run in the background, and it is hard to tell which one is still going, which model it uses, or what it has found so far.

The outcomeEach running review shows one live line with its model, target, elapsed time and Codex's latest output, and a toast lists the findings when it ends.

What you need first

  • Claude Code 2.1.287 or newer
  • npx available on your computer (the README installs with npx claude-code-mods@latest)
  • Chrome, a terminal that shows images, and the Spotify app only for the mods that need them (md-preview, now-playing)
  • An OpenAI organization Admin key only for openai-balance

Steps

  1. Run npx claude-code-mods@latest, tick review-watch in the checklist, and press Enter.
  2. Restart Claude Code.
  3. Start a code review with Codex or a review subagent in Claude Code.
  4. Watch the live line above the prompt for the model, target, elapsed time and latest output.
  5. When the review ends, read the toast that lists the findings.

Prompt for your agent

In the hamzafer/claude-code-mods repo, install review-watch and start a code review of <target-branch> in Claude Code. Expect one live line per running review showing model, target and elapsed time, followed by a findings toast when it finishes; verify the toast appears.

Caveat. The README says review-watch works with Codex or a review subagent, so a review started some other way will not show a line.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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