jhowbhz

Agents Monitor β€” AI skill for Claude Code

AI community

🏒 Your AI coding agents living in a pixel-art office β€” watch Claude Code, Codex, Cursor, Gemini & OpenCode work in real time: tokens, cost, CPU/GPU.

How to install Agents Monitor

This entry records only its repository, not the path inside it, so there is no exact command to give. Open jhowbhz/agents-monitor and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agents Monitor does

🏒 Your AI coding agents living in a pixel-art office β€” watch Claude Code, Codex, Cursor, Gemini & OpenCode work in real time: tokens, cost, CPU/GPU. Zero deps, 100% local.

Alternatives in AI

  • Skill Seekers Roadmap β€” Transform Skill Seekers into the easiest way to create Claude AI skills from any knowledge source - documentat 11.1k β˜…
  • Pixel Agents β€” Compressed Reference β€” VS Code extension with embedded React webview: pixel art office where AI agents (Claude Code terminals) are an 6.5k β˜…
  • Manifest β€” Real-time cost observability for OpenClaw agents β€” track tokens, costs, messages, and model usage 4.1k β˜…

README

🏒 Agents Monitor

Your AI coding agents, living in a pixel-art office.

**Watch Claude Code, Codex, Cursor, Gemini CLI and OpenCode work in real time β€” who's busy, on what, how many tokens they burn and what it costs.**

[![GitHub stars](https://img.shields.io/github/stars/jhowbhz/agents-monitor?style=for-the-badge&logo=github&color=f5c518)](https://github.com/jhowbhz/agents-monitor/stargazers) [![License: MIT](https://img.shields.io/badge/license-MIT-2ea44f?style=for-the-badge)](LICENSE) [![Node 22+](https://img.shields.io/badge/node-22%2B-339933?style=for-the-badge&logo=node.js&logoColor=white)](https://nodejs.org) [![Zero dependencies](https://img.shields.io/badge/dependencies-0-blueviolet?style=for-the-badge)](package.json) [![100% local](https://img.shields.io/badge/data-100%25%20local-informational?style=for-the-badge)](#-privacy)

**English** Β· [PortuguΓͺs](README.pt-BR.md)

Pixel-art office: agents coding at their desks, idle agents sleeping on the couch, the token reservoir and the server room next door

Dashboards full of numbers are boring. So every agent session on your machine becomes a **little pixel character** in an office: it walks in when a session starts, sits at a desk while it works, gets **bigger and more muscular the harder it thinks**, drags its subagents along like ducklings, and crashes on the couch when it goes idle.

Behind the cute part there's a real monitor: **token usage, cost, CPU, RAM and GPU**, read straight from your agents' own logs. Your session data never leaves your machine.

⚑ Quick start

**macOS / Linux**

curl -fsSL https://agent-house.jhon.io/install.sh | bash

**Windows (PowerShell)**

irm https://agent-house.jhon.io/install.ps1 | iex

**Or by hand** β€” no `npm install`, there's nothing to install:

git clone https://github.com/jhowbhz/agents-monitor && cd agents-monitor
npm start        # β†’