# model-guard

> model-guard — sarielwang93-model-guard. Use this tool when you need to optimize Anti-Gravity model performance and automatically manage quotas. It solves the problem of manual model switching and quota tracking, ensuring the default model is always the one with the highest available quota. The model-guard tool takes Anti-Gravity model quotas as input and outputs the optimal default model, streamlining model management in resource-constrained environments.

Canonical page: https://skillsregistry.net/skills/sarielwang93-model-guard  
JSON: https://api.skillsregistry.net/v1/skills/sarielwang93-model-guard

## Description

Automatically monitors Anti-Gravity model quotas and switches the default model to the one with the highest.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** monitoring
- **Updated:** 2026-09-27

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/sarielwang93-model-guard)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sarielwang93-model-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sarielwang93-model-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sarielwang93-model-guard/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt