What is claude-video?

A video-processing tool that accepts a URL or local video, extracts frames, and creates a local transcript for an AI assistant. It supports sites such as YouTube, Instagram, X, Vimeo, and TikTok.

Use it to download videos, review selected frames, obtain captions or local speech-to-text transcripts, and analyze the result.

It lets an AI assistant inspect both the visual content and spoken words of a video rather than relying on a title or description.

claude-video — Plugin by mathiaschu

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 mathiaschu/watch

agentmods

npx agentmods add plugins/mathiaschu/watch/marketplace

Clone the repo

git clone --depth 1 https://github.com/mathiaschu/watch

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

claude-video 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 yesterday.

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.

.claude-plugin/marketplace.json · 22 lines

What it actually says

{
  "name": "claude-video",
  "metadata": {
    "description": "Give Claude a video input. /watch downloads from any platform, extracts frames, transcribes locally (no API key), and hands it all to Claude."
  },
  "owner": {
    "name": "Mathias Schusterman"
  },
  "plugins": [
    {
      "name": "watch",
      "description": "Watch a video (URL or local path) from YouTube, Instagram, X, Vimeo, TikTok or any yt-dlp site. Downloads with yt-dlp, extracts frames with ffmpeg, transcribes via captions or local mlx-whisper.",
      "author": {
        "name": "Mathias Schusterman"
      },
      "source": "./",
      "category": "productivity",
      "homepage": "https://github.com/mathiaschu/claude-video"
    }
  ]
}

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

plugin.json 712 B

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.

yesterday First seen · 22 lines scan A 6993d6d82522

Subscribe to this mod's changes

claude-video is a plugin published in the GitHub repository mathiaschu/watch (121 stars, last pushed 3mo ago), 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.

Code review claude claude-code claude-skill mlx transcription video

claude-video

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

frameproof

frameproof

video-skills

video-skills

voxpip

voxpip