Skip to content
TriedPrompts

More in Build apps & tools.

Watch Claude Code agents and spend in an animated office

WorkedEvidence: Described by posterPosted Last checked

Marcelo Lima's AgentDesk shows Claude Code sessions as office robots with live token spend and phone approve/deny.

How to use this

  1. Tap Copy prompt.
  2. Open the tool the case used (or a similar one) and paste the prompt; results may differ from the original.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

Help me ship a local dashboard that visualizes every Claude Code session and automation as an agent in a pixel-art office, shows token spend by day/month/all-time with currency options, surfaces 5-hour and weekly usage bars, and lets me approve or deny permission prompts from my phone without ever auto-approving. Keep prompts and source on my machine.

Try this in:

ChatGPT Gemini Grok Claude

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

The source used Claude Code, which can take actions on your computer or in a browser. These are general chat tools, so results may differ, and a normal chat may only give you a plan.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Build a local AgentDesk-style monitor for Claude Code spend and session control.

Questions to ask me first:
- Docker or bare metal?
- Which currencies and monthly limit?
- Mobile approve/deny requirements?

Inputs (fill in or confirm):
- Runtime: [DOCKER]
- Currency: [USD / BRL / EUR / GBP]
- Limit: [MONTHLY $]
- Control: [PHONE APPROVAL]

Rules:
- Never upload prompts or source.
- Never auto-approve permissions.
- Show cache rate and model mix.
- Encrypt API keys at rest.

Checkpoint: Demo one fake session robot before wiring live collectors.

If you get stuck: If the collector lacks a field, show a clear empty state.

Verify before you finish: Spend totals match the provider metadata you collect.

Output: Running dashboard with office view and spend panels.

Done when: I can see cost and stop a runaway session from my phone.

AI tool

Claude Code

Outcome

Marcelo Lima built and open-sourced AgentDesk so each automation and Claude Code session appears as a named pixel-art robot with a speech bubble of current work. The dashboard shows API tokens and cost for today, the month, and all time (US$, R$, €, or £), live Claude Code usage by project and model, cache rate, 5-hour and weekly windows, and phone controls to approve/deny permissions or stop a session—never auto-approving. It runs with one Docker command; API keys stay encrypted locally.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Source

Posted
by Marcelo Lima
Last checked
Method:
How we verify

https://dev.to/marcelo_lima_021/i-launched-agentdesk-an-animated-office-to-see-what-claude-and-claude-code-is-doing-and-spending-4n71

More in Build apps & tools

Similar cases