Use Case
Model Guard is a powerful AI agent skill that extends your assistant with new capabilities. Monitors Anti-Gravity model quotas and automatically switches to the model with highest quota or falls back to gemini-flash if all are below 20%. This guide walks you through installing Model Guard, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Model Guard: npx clawhub@latest --dir ~/.claude/skills install model-guard
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to developer & devops to trigger Model Guard
Review the output and refine your prompt for better results
Combine Model Guard with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Model Guard
Help me get started with Model Guard
What can Model Guard do for my developer & devops workflow?
Show me an example of using Model Guard
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install model-guardOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install model-guardβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/model-guard/π‘Extract and place the folder at the path above, then restart your agent.