Setup & Installation
openclaw skills install @sarielwang93/model-guard
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install model-guard
What This Skill Does
Monitors Anti-Gravity model quotas and switches the default model to whichever has the highest remaining quota. Falls back to gemini-flash when all Anti-Gravity models drop below 20%. Can run manually or on a schedule via cron or heartbeat.
Automates model switching based on live quota data instead of requiring users to manually track limits and intervene.
When to use it
- Avoiding quota exhaustion during long automated runs
- Automatic model failover without manual intervention
- Keeping overnight agent jobs running uninterrupted
- Balancing usage across multiple Anti-Gravity models
- Scheduled quota checks via cron
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User runs: model-guard
AGENT
- 1Queries remaining quota for each Anti-Gravity model
- 2Identifies the model with the highest remaining quota
- 3Checks if any model is above the 20% threshold
- 4Switches the default model to the highest-quota option, or falls back to gemini-flash if all are below threshold
OUTPUT
Default model updated to the Anti-Gravity model with the most remaining quota, or gemini-flash if all are below the threshold