What is mlx-vlm-skills?

A set of skills for MLX-VLM, a tool for running vision-language models on Apple hardware. Vision-language models work with both images and text.

Use it to run command-line or server inference, convert or reduce models, add models, benchmark them, list cached models, and prepare GitHub issues.

It organizes the project-specific procedures for using models, changing model files, measuring results, and contributing changes.

mlx-vlm-skills — Plugin by Blaizzy

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add Blaizzy/mlx-vlm

agentmods

npx agentmods add plugins/blaizzy/mlx-vlm/skills

Clone the repo

git clone --depth 1 https://github.com/Blaizzy/mlx-vlm

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mlx-vlm-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "name": "mlx-vlm-skills",
  "description": "Skills for MLX-VLM: command-line and server inference, convert/quantize, adding new models, benchmarking, contributing, cached-model listing, and reproducible GitHub issues.",
  "version": "0.1.0",
  "author": {
    "name": "MLX-VLM contributors"
  },
  "keywords": [
    "mlx",
    "mlx-vlm",
    "vision-language-models",
    "apple-silicon"
  ]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 15 lines scan A 56fe58d1ed64

Subscribe to this mod's changes

mlx-vlm-skills is a plugin published in the GitHub repository Blaizzy/mlx-vlm (5,458 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Apple Silicon Data and AI Hardware and IoT LLM idefics llava mlx vision-transformer

localvoxtral-remote

Publishes Claude Code session context from a REMOTE host to localvoxtral on your Mac, over an SSH RemoteForward tunnel. Command hooks running a bundled POSIX-sh shim that POSTs via curl — needs only sh and curl on the remote host, and fails open silently when either is missing.

T0mSIlver/localvoxtral · not measured

mlx-vlm-skills

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

localvoxtral-remote

localvoxtral

localvoxtral

memo

memo

cadence-code-marketplace