Gateton

Pi Usage Live — AI skill for Claude Code

AI community

Always-on subscription usage card for Pi: see how much of your Claude, ChatGPT Codex, OpenCode Zen, DeepSeek, Kimi, MiniMax, Moonshot, Z.AI and OpenRouter allowance you have left, live in your termina.

How to install Pi Usage Live

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

What Pi Usage Live does

Alternatives in AI

Zen MCP Server — The power of Claude Code + Gemini / OpenAI / Grok / OpenRouter / Ollama / Custom Model working as one 11.3k ★
EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
Cc Mirror — Create multiple isolated Claude Code variants with custom providers (Z.ai, MiniMax, OpenRouter, LiteLLM) 2.1k ★

README

pi-usage-live

**Your subscription allowance, always on screen.**

Claude, ChatGPT Codex, OpenCode Zen, DeepSeek, Kimi, MiniMax, Moonshot, Z.AI and OpenRouter — read live while you work, without asking.

[![npm](https://img.shields.io/npm/v/pi-usage-live?label=npm)](https://www.npmjs.com/package/pi-usage-live) [![Pi extension](https://img.shields.io/badge/Pi-extension-19c7d4)](https://github.com/earendil-works/pi-coding-agent) [![Node](https://img.shields.io/badge/node-%3E%3D22-1f8f4d)](package.json) [![License](https://img.shields.io/badge/license-MIT-f5a623)](LICENSE)

`pi-usage-live` adds a usage card to Pi that is simply *there*. No command to remember, no dashboard to open: the card docks in the corner, follows the model you are actually using, and keeps itself current while you work.

Close-up of the usage card: a bordered panel titled OC Go, with three labelled rows — rolling at 2%, wk at 13% and mo at 49% — each drawn as a bar with its percentage and reset countdown right-aligned

Highlights

Zero commands. The number you need is on screen before you think to ask for it. /usage all expands the card when you want the whole picture.
It follows your model. The card shows the allowance behind your next request, so it is always the number that matters. Switch providers and the card switches with you.
Free where the provider allows it. Providers that publish quota in the headers of responses you were already making are read passively, at no extra request cost. Only the rest are polled.
**Claude stays live eve