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%.

Before installing: (1) confirm you have the 'openclaw' CLI on PATH and test 'openclaw models status' and 'openclaw models set' manually; the package metadata currently omits this required binary. (2) Review the CANDIDATES and FALLBACK_MODEL strings in guard.js to ensure they are models you trust and that switching to them is acceptable. (3) Because the script runs shell commands, prefer running it in a controlled environment and/or review logs/audit for automatic runs; you may restrict autonomous invocation or run it on a cron job you control. (4) Consider hardening the script (use execFile/spawn with args or validate model names strictly) to reduce shell-injection risk if you ever change candidate sources. (5) If provenance matters, seek a published source/homepage or contact the owner before trusting this skill in production.

Type: OpenClaw Skill Name: model-guard Version: 1.0.0 The skill is classified as benign. It uses `child_process.execSync` to interact with the `openclaw` CLI, specifically to query model status and set the default model. While `execSync` is a powerful primitive, the commands executed (`openclaw models status` and `openclaw models set`) are directly related to the skill's stated purpose of managing Anti-Gravity model quotas. Crucially, all arguments passed to `openclaw models set` are derived from hardcoded lists or constants within `guard.js`, preventing command injection from untrusted sources. There is no evidence of data exfiltration, persistence mechanisms, obfuscation, or prompt injection attempts in `SKILL.md`.