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

How to undo an agent turn that broke your files with Tellurion

Restore project files to the snapshot taken before an agent's last turn, in one click.

Who it is forA developer whose coding agent made a wrong or unwanted set of edits in a repository and needs the files back as they were.

The problemAn agent turn changed several files in a way you did not want, and reverting by hand is slow and error prone.

The outcomeYour files return to the state from before the turn, with a list of the files that will change shown first and the current state saved so the undo can be undone.

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. Let the agent finish its turn in a git repository or any folder.
  2. Open the tab's ⋮ menu and choose Undo last turn, or use Restore to before this on one of your prompts in the agent timeline.
  3. Read the list of files the undo will change.
  4. Confirm the restore.
  5. Open the review inbox with ⌃⌘I to check that it matches the restored files.

Prompt for your agent

Using the Tellurion repo at https://github.com/steventsvik/Tellurion, run an agent turn in <project-folder> that makes a change, then use Undo last turn from the tab's ⋮ menu. Report the list of files the undo listed. Verify that the restored files match their state before the turn.

Caveat. Snapshots are git objects, and the README says staged changes stay as they are, so check the file list before you confirm.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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