Mlx Watch

Name: Mlx Watch
Author: cavi-ai

ASecurity

Digest Hugging Face changes for owned models against a stored baseline.

2 stars
0 votes
0 copies
2 views
Added October 3, 2026

ai-agentspythonshell

Security analysis

A100/100

Scanned October 3, 2026

npx -y skills add cavi-ai/mlx-agent --skill mlx-watch --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mlx Watch?

Add the live security badge to your README. It updates with every re-scan.

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cavi-ai-mlx-watch-9bc6bb6f/badge)](https://www.skillsdirectory.com/skills/cavi-ai-mlx-watch-9bc6bb6f)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: "mlx-watch"
description: "Digest Hugging Face changes for owned models against a stored baseline."
---

# MLX Watch

Resolve `<plugin-root>` as the absolute directory two levels above the directory containing this SKILL.md; it holds `scripts/` and `src/`. Never resolve the bundled executable from the shell working directory.

canonical capability ID: mlx-agent.watch

Record or compare the owned-model baseline:

`python3 <plugin-root>/scripts/mlx-agent watch snapshot --json`
`python3 <plugin-root>/scripts/mlx-agent watch diff --json`

Present the classified findings as returned. Watch writes only its own state file and never downloads model weights or changes configuration.