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

How to split one feature between Claude Code and Codex with Agents Can Communicate

Run two sessions on one feature and let them ask each other for shared details.

Who it is forA developer with Claude Code and Codex open in the same project who wants both to work on one feature at once.

The problemEach client works in its own session, so details like an API request shape have to be copied between them by hand.

The outcomeEach session builds its own part, and the session that needs a detail asks the other one through ACC and gets the answer at its next turn.

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.
  4. Ask Codex for the backend part, such as an account-registration endpoint, and ask Claude Code for the matching screen.
  5. When a session needs a shared detail, let it ask the other session through ACC, and check whether the question was delivered and answered.

Prompt for your agent

In the agents-can-communicate repo (https://github.com/automatis-tools/agents-can-communicate), install ACC and connect Claude Code and Codex in the project at <project-path>. Give each session one part of <feature-name> and report the answer from the session that needed a shared detail. Verify that the question sent between the two sessions shows as delivered and answered.

Caveat. The agents decide when to coordinate, and ACC does not guarantee they will notice every dependency.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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