# AI use cases for Tellurion (steventsvik/Tellurion)

Repo: [steventsvik/Tellurion](https://github.com/steventsvik/Tellurion) | Use cases: 4 | Page: https://dedupedai.com/use-cases/steventsvik-tellurion/

Tellurion is a free, open source macOS terminal (a fork of Ghostty) that shows live status, edits, diffs and approval prompts for several AI coding agents running across your projects.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Watch every coding agent from one screen: https://dedupedai.com/use-cases/steventsvik-tellurion/watch-several-agents-from-one-screen/
- Undo an agent turn that broke your files: https://dedupedai.com/use-cases/steventsvik-tellurion/undo-a-bad-agent-turn/
- Hand off a stuck task to another agent: https://dedupedai.com/use-cases/steventsvik-tellurion/hand-off-stuck-work-to-another-agent/
- Pair one agent with a reviewer that checks each turn: https://dedupedai.com/use-cases/steventsvik-tellurion/run-a-writer-and-reviewer-loop/

## How to watch every coding agent from one screen with Tellurion

Repo: [steventsvik/Tellurion](https://github.com/steventsvik/Tellurion) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

See each agent's status across all tabs and answer permission prompts without switching windows.

**Who it is for:** A developer running Claude Code, Codex or Gemini CLI in several tabs and projects who loses track of which agent is waiting on them.

**The problem:** Agents in background tabs stop for permission or input, and you only notice when you go looking for them.

**The outcome:** One Mission Control view shows every agent's status, task and last action, with waiting agents at the top, and you can answer them from the card.

### Steps

1. Run `curl -fsSL https://raw.githubusercontent.com/steventsvik/Tellurion/custom/install.sh | bash` in Terminal to install Tellurion.
2. Open Tellurion, then click Connect for Claude Code and Codex in the welcome window, or use Check Setup for other agents it finds.
3. Start an agent in two or more tabs, each in a different project folder.
4. Press ⌃⌘M to open Mission Control and check the status cards.
5. When a card turns amber, click Allow or Deny on the card, or use the notification.

### Prompt to paste into your agent

```text
Using the Tellurion repo at https://github.com/steventsvik/Tellurion, set up live status for Claude Code and Codex, then open Mission Control (⌃⌘M) with two agents running in <project-folder-1> and <project-folder-2>. Report the status shown on each card. Verify that a waiting agent appears first in the list.
```

### Caveat

Tellurion is an unofficial fork of Ghostty, runs on macOS only, and the README lists Apple silicon as the supported hardware.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/steventsvik-tellurion/watch-several-agents-from-one-screen/

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

Repo: [steventsvik/Tellurion](https://github.com/steventsvik/Tellurion) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

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

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

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

**The outcome:** Your 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.

### 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 to paste into your agent

```text
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.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/steventsvik-tellurion/undo-a-bad-agent-turn/

## How to hand off a stuck task to another agent with Tellurion

Repo: [steventsvik/Tellurion](https://github.com/steventsvik/Tellurion) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Pass a session's task, diff and failed commands to a new Claude Code or Codex session.

**Who it is for:** A developer whose Claude Code or Codex session has stalled or gone in the wrong direction and who wants a second agent to continue or check the work.

**The problem:** Restarting an agent loses the context of what it changed, and explaining it again takes time.

**The outcome:** A new session starts with the task, the recent conversation, the diff since the first prompt and any failed commands, so the next agent can continue or review right away.

### Steps

1. Open the pane with the stalled agent session.
2. Choose Hand off from its menu and pick Claude Code or Codex, either in a new split or in a session already running.
3. Read and edit the handoff message before sending it.
4. Pick Continue, Review or Second opinion.
5. Check the new agent's first reply against the diff shown in the handoff.

### Prompt to paste into your agent

```text
Using the Tellurion repo at https://github.com/steventsvik/Tellurion, hand off the Claude Code session in <project-folder> to a new Codex session with the Review action. Report the diff size included in the handoff. Verify that the handoff message lists the failed commands from the first session.
```

### Caveat

The README describes handoff only between Claude Code and Codex sessions, so other agents are not covered by this flow.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/steventsvik-tellurion/hand-off-stuck-work-to-another-agent/

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

Repo: [steventsvik/Tellurion](https://github.com/steventsvik/Tellurion) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

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

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

**The problem:** A single agent reviews its own output poorly, and checking each turn by hand is tedious.

**The outcome:** Each 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.

### 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 to paste into your agent

```text
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.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/steventsvik-tellurion/run-a-writer-and-reviewer-loop/