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

How to pair one agent with a reviewer that checks each turn with Tellurion

Have one agent write changes while another approves them or returns findings, round by round.

Who it is forA developer who wants a second agent to check every change a writing agent makes before accepting the work.

The problemA single agent reviews its own output poorly, and checking each turn by hand is tedious.

The outcomeEach finished writer turn goes to the reviewer, which answers APPROVED or CHANGES NEEDED, and its findings go back to the writer until approval or a round limit.

What you need first

  • An Apple silicon Mac running macOS 13 or newer
  • Terminal access to run the install command
  • At least one supported coding agent installed, such as Claude Code or Codex

Steps

  1. Make sure a writer agent is running in the tab you want to review.
  2. Open the tab's ⋮ menu and choose Start a review loop.
  3. Choose the reviewer agent and set a round limit.
  4. Read each review message and click Send, or turn on Send automatically if you trust the loop.
  5. Stop the loop when the reviewer answers APPROVED, then open the review inbox with ⌃⌘I.

Prompt for your agent

Using the Tellurion repo at https://github.com/steventsvik/Tellurion, start a review loop in <project-folder> with Codex as writer and Claude Code as reviewer, with a round limit of 3. Report the reviewer's answer for each round. Verify that no message reached an agent before you clicked Send.

Caveat. The README says messages wait for your Send unless you turn on Send automatically, so review each round before enabling the automatic option.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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