# AI use cases for Agent Standup (Atoll92/agent-standup)

Repo: [Atoll92/agent-standup](https://github.com/Atoll92/agent-standup) | Use cases: 5 | Page: https://dedupedai.com/use-cases/atoll92-agent-standup/

Agent Standup is a local app that reads the session files written by Claude Code, Codex and Mistral Vibe and shows them as a live animated team call and a board of sessions.

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

- Watch your agent sessions as a live team call: https://dedupedai.com/use-cases/atoll92-agent-standup/watch-live-agent-call/
- Find stuck or looping agents before they waste time: https://dedupedai.com/use-cases/atoll92-agent-standup/spot-stuck-looping-agents/
- Find which sub-agent uses the most tokens: https://dedupedai.com/use-cases/atoll92-agent-standup/track-token-use-per-agent/
- Replay a past session and get a recap: https://dedupedai.com/use-cases/atoll92-agent-standup/replay-session-recap/
- Make a 25-second clip to share without showing code: https://dedupedai.com/use-cases/atoll92-agent-standup/share-clip-with-code-hidden/

## How to watch your agent sessions as a live team call with Agent Standup

Repo: [Atoll92/agent-standup](https://github.com/Atoll92/agent-standup) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Open a live animated call that shows which Claude Code or Codex agent is working and who is waiting on whom.

**Who it is for:** A developer running Claude Code or Codex with a lead agent and sub-agents who wants to see the whole run at a glance.

**The problem:** Multi-agent sessions are hard to follow in a terminal scroll, and it is unclear which sub-agent is doing what.

**The outcome:** A browser view of the session where each agent is a character at its desk, with its current action and the sub-agent tree visible.

### Steps

1. Run `npx @double_geste/agent-standup@latest --open` in a terminal with Node 18 or newer.
2. In the app, open ⚙ → Source → Demo if you have no session yet, and check the demo team plays.
3. Start or continue a Claude Code or Codex session and confirm the newest session appears in the live call.
4. Click any agent to read its prompt, tool usage and reports.

### Prompt to paste into your agent

```text
In the repo Atoll92/agent-standup, run `npx @double_geste/agent-standup@latest --open` and open the live call for my newest Claude Code or Codex session. Report which agents are shown as working and which are waiting. Verify that the sub-agent tree lists the lead and its sub-agents with their status.
```

### Caveat

The app only reads local session files, but it calls Claude only when the call is held in French, Spanish or Brazilian Portuguese or when jokes are turned on.

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/atoll92-agent-standup/watch-live-agent-call/

## How to find stuck or looping agents before they waste time with Agent Standup

Repo: [Atoll92/agent-standup](https://github.com/Atoll92/agent-standup) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Spot agents that are slow, quiet, failing or repeating work using the badges on each tile.

**Who it is for:** A developer who left a coding agent running on a long task and needs to know whether it is making progress.

**The problem:** An agent can sit on a slow command, go silent, or repeat the same read or search without anyone noticing.

**The outcome:** You see amber, quiet, failed and repeated-work badges on the agent tiles and can open the calls behind each one.

### Steps

1. Run `npx @double_geste/agent-standup@latest --open` and open the live call.
2. Look for an amber ⏳ tile, which means a command has run for over a minute.
3. Look for 💤, which means a working agent has been quiet for 3 minutes, and a red ✗ count for failed tool calls.
4. Hover over or tap a ♻ badge to see the repeated reads, searches or failing commands behind it.

### Prompt to paste into your agent

```text
In the repo Atoll92/agent-standup, open the live call for my running Claude Code or Codex session. Report each agent that shows a ⏳, 💤, ✗ or ♻ badge and the calls listed when you hover over that badge. Verify each badge against the session's real tool calls before you act on it.
```

### Caveat

The badges come from the session files on your machine, so they only show what those files record.

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/atoll92-agent-standup/spot-stuck-looping-agents/

## How to find which sub-agent uses the most tokens with Agent Standup

Repo: [Atoll92/agent-standup](https://github.com/Atoll92/agent-standup) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Read the per-agent ⚡ token counter to see which sub-agent is the expensive one in a session.

**Who it is for:** A developer or team lead who needs to control the cost of a multi-agent Claude Code session.

**The problem:** A session with a lead and many sub-agents hides which one spends the most tokens.

**The outcome:** Each agent shows its token count, with the model that spent it when a session mixes models.

### Steps

1. Run `npx @double_geste/agent-standup@latest --open` and open the live call for your session.
2. Read the ⚡ counter in the header and on each agent tile.
3. Hover over the counter to see cache reads, shown separately from input, output and cache writes.
4. Compare the agents list entries to find the sub-agent with the highest count.

### Prompt to paste into your agent

```text
In the repo Atoll92/agent-standup, open the live call for my Claude Code session and list each agent with its ⚡ token count and model. Identify the agent with the highest count. Verify that the figures match the token counts recorded in the session files, noting that they are not an estimate of the bill.
```

### Caveat

The counts are read from the session files as recorded by Claude Code and are not an estimate of your bill.

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/atoll92-agent-standup/track-token-use-per-agent/

## How to replay a past session and get a recap with Agent Standup

Repo: [Atoll92/agent-standup](https://github.com/Atoll92/agent-standup) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Scrub through an earlier session to see who worked when and get a recap of tool calls and files changed.

**Who it is for:** A developer reviewing what an agent team did overnight or last week.

**The problem:** After a long agent session it is hard to reconstruct who did what, in which order, and which files changed.

**The outcome:** A timeline of agent activity and a recap listing agents, tool calls, commands, files changed and busiest agents.

### Steps

1. Run `npx @double_geste/agent-standup@latest --open` and choose a past session in the session list.
2. Scrub the replay to move through the session.
3. Read the timeline to see which agent worked at each point.
4. Open the recap for agents, tool calls, commands, files changed and busiest agents.

### Prompt to paste into your agent

```text
In the repo Atoll92/agent-standup, open a past Claude Code session in replay and produce its recap. Report the agents, tool calls, commands, files changed and busiest agent. Verify the files-changed count against the session's own record before reporting it.
```

### Caveat

Replay only covers sessions that still exist as files on your machine.

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/atoll92-agent-standup/replay-session-recap/

## How to make a 25-second clip to share without showing code with Agent Standup

Repo: [Atoll92/agent-standup](https://github.com/Atoll92/agent-standup) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Record a short shareable clip of the call with commands, file names and screenshots hidden.

**Who it is for:** A developer who wants to post a short video of an agent run to a team channel or social site.

**The problem:** A useful clip of an agent run can expose code, file names and screenshots you do not want to publish.

**The outcome:** An MP4 file called agent-standup-clip.mp4 of about 25 seconds with code and file names masked.

### Steps

1. Open the live call from `npx @double_geste/agent-standup@latest --open`.
2. Open ⚙ → Tools and turn on Hide code & file names in videos.
3. Choose ⚙ → Tools → 🎬 Clip to share (25 s) and wait for the recording to finish.
4. Watch the saved clip and check the spoken lines, since agent speech is not masked.

### Prompt to paste into your agent

```text
In the repo Atoll92/agent-standup, open the live call, enable Hide code & file names in videos, and record a Clip to share. Report the saved file name and length. Verify by playing the clip that code, file names and pictures are masked and that spoken lines contain no secrets before posting.
```

### Caveat

Masking does not cover what agents say aloud, so check the clip for quoted code or names before posting.

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/atoll92-agent-standup/share-clip-with-code-hidden/