LaunchKit · 2026
Back to Skills

ag-model-usage

AI & LLMsv1.0.0

Use CodexBar CLI local cost usage to summarize.

0
0 downloads
by @ls18166407597-design

Setup & Installation

openclaw skills install @ls18166407597-design/ag-model-usage

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install ag-model-usage

What This Skill Does

Queries AI model quota usage from Google Cloud Code Assist accounts. Shows remaining quota percentages and next refresh times for Gemini, Claude, and other models. Reads OAuth tokens from auth-profiles.json to authenticate against Google's internal API.

Pulls real-time quota data directly from Google's API instead of relying on dashboard estimates or manual checks.

When to use it

  • Checking remaining Gemini quota before starting a large task
  • Monitoring Claude quota when juggling multiple projects
  • Planning work around upcoming quota refresh windows
  • Quickly checking which model still has headroom after heavy use
  • Confirming quota reset time before a scheduled batch job

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: How much quota do I have left on Gemini and Claude?

AGENT
  1. 1Read OAuth token from auth-profiles.json
  2. 2Send quota query to Google Cloud Code Assist API simulating official IDE client
  3. 3Parse remaining quota percentages per model
  4. 4Convert next refresh timestamps to local timezone
OUTPUT

Per-model quota summary showing remaining percentages for Gemini and Claude, plus next refresh time in local timezone

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Google Cloud Code Assist account with Antigravity OAuth login