- Home
- Skills
- Agents & Orchestration
- Agent Command Center
Agent Command Center
Build a live 3D office dashboard for your AI agents — see who's working, dispatch real work from a desk, and get results written back to the board.
Free
Works with the AI Agents you already use
Agent Command Center
Example session with this skill installed
Create an Agent Command Center for my three agents: a Research Lead (web search API), a Python Dev (local CLI), and a Social Manager (browser worker).
- Read your context and instructions
- Compiled the agent command center
I have generated the architecture and roster for your Agent Command Center. The setup includes the 3D client configuration, the server-side store schema, and the execution channel mappings.
Agent Command Center Configuration
| Workstation | Role | Execution Channel | Honest Status Target |
|---|---|---|---|
| Research Lead | Fact-checking & Synthesis | Search API / Hosted Session | idle / executing |
| Python Dev | Code generation & Testing | Local CLI (Non-interactive) | idle / executing |
| Social Manager | Content publishing | Playwright Browser Worker | idle / executing |
Architecture Implementation Details
// Server-side Dispatch Logic
async function dispatchTask(assignee, taskText) {
// 1. Pre-dispatch probe
const isAlive = await probeSession(assignee);
if (!isAlive) return { status: 'failed', reason: 'Not logged in — re-login required' };
// 2. Create record
const record = await db.dispatches.create({
assignee,
status: 'executing',
startTime: Date.now()
});
// 3. Trigger Executor (Fire-and-forget)
runAgentChannel(assignee, taskText, record.id);
return record;
}
3D Scene Requirements
- Camera: Four modes (Panorama, Boss, Auto-Patrol, Rotate).
- Figures: Three workstations with back-facing figures oriented toward monitors.
- UI: Mobile-optimized bottom sheets for task input and log expansion.
Next steps
- Initialize the Three.js scene with three workstations using the provided coordinate map.
- Securely store the API keys and CLI session tokens in your environment's secret manager.
- Run the first
refreshBoardsync to pull your existing Python scripts and social drafts into the task board.
Connects securely to your tools. The creator never sees your data.
About this skill
Build a live 3D office dashboard for your AI agents. Each agent sits at a desk — see who's actually working and who's idle, click a desk to dispatch real work, and results are written back to the board. Status comes from real task records, never simulated. Full skill (SKILL.md) plus README included. Source and latest version on GitHub — if you like it, please give it a star: https://github.com/lilbridge520-pixel/agent-command-center-skill
Requires pre-existing execution channels; no simulated activity. Mobile requires specific bottom-sheet layouts. Figure orientation must be manually verified across camera views.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
Permissions
No special permissions declared or detected