watch-cli

A plugin marketplace entry for watch-cli. The plugin combines video downloading, audio or video processing, and speech transcription so an AI agent receives a video, selected frames, and transcript text.

In plain words
What is it for?
Preparing social videos for analysis by downloading them, extracting frames, and creating a transcript with yt-dlp, ffmpeg, and Whisper.
Why use it?
It brings the main materials from a social video into one agent-ready result. This avoids gathering the video, images, and spoken words separately.

Plugin for Claude Code

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 sonpiaz/watch-cli
agentmods
npx agentmods add plugins/sonpiaz/watch-cli/marketplace
Clone the repo
git clone --depth 1 https://github.com/sonpiaz/watch-cli

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

watch-cli 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.

.claude-plugin/marketplace.json · 23 lines

What it actually says

{
  "name": "watch-cli",
  "owner": {
    "name": "Son Piaz",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "watch-cli skill marketplace — Claude Code users can /plugin install watch-cli.",
    "version": "0.3.0"
  },
  "plugins": [
    {
      "name": "watch-cli",
      "description": "Compose yt-dlp + ffmpeg + Whisper into a single command that hands an AI agent the raw materials to watch any social video — VIDEO + FRAMES + TRANSCRIPT, ready for an LLM to read frames as images and transcript as text.",
      "source": "./",
      "strict": false,
      "skills": [
        "./skills/watch-cli"
      ]
    }
  ]
}
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.

  1. 2d ago First seen · 23 lines scan A 7ea38485d473

Subscribe to this mod's changes

watch-cli is a plugin published in the GitHub repository sonpiaz/watch-cli (248 stars, last pushed 1mo 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.