model-guard
by sarielwang93
AI & LLMsBrief
Automatically monitors Anti-Gravity model quotas and switches the default model to the one with the highest.
Description
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
User runs: model-guard
- 1
Queries remaining quota for each Anti-Gravity model
- 2
Identifies the model with the highest remaining quota
- 3
Checks if any model is above the 20% threshold
- 4
Switches the default model to the highest-quota option, or falls back to gemini-flash if all are below threshold
Default model updated to the Anti-Gravity model with the most remaining quota, or gemini-flash if all are below the threshold
Installation
clawhub install sarielwang93/model-guardRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.