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

How to get a code review from the other vendor's model with Agents Can Communicate

Have Codex review a change that Claude Code just wrote, and send findings back.

Who it is forA developer who wants a second opinion from a different model on a change their Claude Code session just made.

The problemThe session that wrote the code is the only one that reviews it, and asking another model usually means copying files and findings manually.

The outcomeThe session that made the change requests a review of named files through ACC, and the other session sends its findings back to it.

What you need first

  • macOS, Linux or Windows 10/11
  • Node.js 24 or newer
  • Claude Code and/or Codex installed on the same machine and operating-system user
  • A project directory both clients can open

Steps

  1. Run npm install -g agents-can-communicate to install ACC.
  2. Run acc install, follow its activation instructions, and review any required hook or plugin trust.
  3. Restart Claude Code and Codex from the project directory, then open both in the same project.
  4. In the session that made the change, ask it to request a review from the other session in ACC, naming the files.
  5. Ask the other session to answer the review request, then check the findings in the session that wrote the code.
  6. If a peer is missing or delivery is not what you expect, run acc doctor from the project.

Prompt for your agent

In the agents-can-communicate repo (https://github.com/automatis-tools/agents-can-communicate), set up ACC so the session in <project-path> that wrote the change can request a review of <file-list> from a Codex session. Expected output: the review findings returned to the author session. Verify that the request and the answer both appear in ACC before accepting the findings.

Caveat. ACC carries the review request and answer, but the quality of the review depends on the model and the session that receives it.

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer