watch-video

watch-video is a command for Claude Code from jordanrendric/claude-video-vision. It costs 17 tokens per session (471 once invoked), scanned A, original, MIT.

A command for examining a video file or YouTube video by checking its contents, extracting frames, and using audio or captions when available.

In plain words
What is it for?
Finding scenes, spoken content, on-screen text, visual changes, and other details in short or long videos.
Why use it?
It lets an assistant answer questions about a video without manually watching every moment.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the claude-video-vision plugin — 1 skill, 2 commands, 1 agent shipped together

Good fit Finding scenes, spoken content, on-screen text, visual changes, and other details in short or long videos.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jordanrendric/claude-video-vision/watch-video
About the project

Claude Code Video Vision is a plugin that lets Claude Code inspect videos by extracting image frames and producing timestamped audio transcriptions. It supports YouTube URLs and uses Gemini, local Whisper, or OpenAI processing backends, while the catalogue entries provide its commands, agent, and skill.

jordanrendric/claude-video-vision · 1,296 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/jordanrendric/claude-video-vision

Made for: Claude Code.

Or install claude-video-vision, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for watch-video

README.md
[![agentmods](https://agentmods.dev/badge/commands/jordanrendric/claude-video-vision/watch-video/github.svg)](https://agentmods.dev/commands/jordanrendric/claude-video-vision/watch-video)
Your own site
<a href="https://agentmods.dev/commands/jordanrendric/claude-video-vision/watch-video"><img src="https://agentmods.dev/badge/commands/jordanrendric/claude-video-vision/watch-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for watch-video

Your own site · 80×15
<a href="https://agentmods.dev/commands/jordanrendric/claude-video-vision/watch-video"><img src="https://agentmods.dev/badge/commands/jordanrendric/claude-video-vision/watch-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00471
Opus 5 $0.00009 $0.00235
Sonnet 5 $0.00003 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 12d ago against content hash b29014b1ea43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

watch-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 12d 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.

commands/watch-video.md · 35 lines

What it actually says

Watch Video

Parse the user's input to extract:

  1. Video path — the file path (required)
    • YouTube URLs are also supported; pass the URL directly as path
  2. Prompt — any question or instruction about the video (optional)
  3. Flags--fps <number>, --resolution <number> (optional)

Then follow this workflow in order — do NOT skip step 2:

  1. Call video_info on the path/URL to verify it's a valid video and get duration. For YouTube URLs, the MCP server downloads the video with yt-dlp and uses YouTube subtitles/auto-captions before falling back to the configured audio backend.

  2. REQUIRED for videos > 30s: Call video_analyze BEFORE video_watch. This is NOT optional. Use filters: scene_changes: true, silence: true, transcription: true at minimum. Add other filters based on the user's question (motion, blur, exposure, loudness, etc.). The analysis tells you WHERE to look — use it to plan smart frame extraction.

  3. Call video_watch:

    • Short videos (< 2 min): Use fps: "auto" without view_sample — full coverage to avoid missing brief moments.
    • Long videos (> 2 min): Use segments with variable FPS based on analysis data. Use view_sample to limit initial frames.
  4. If the user asks for more detail on a specific moment, use video_detail to drill in with higher FPS/resolution on a 3-5 second window. Use view_sample: 3 first, then request specific timestamps.

  5. If the user provided a prompt/question, answer it based on the video content.

  6. If no prompt was provided, give a comprehensive summary of what happens in the video.

If video_watch fails with a setup error, call video_setup first, then retry.

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. 12d ago First seen · 35 lines · 17 tokens per session scan A b29014b1ea43

Subscribe to this mod's changes

watch-video is a command published in the GitHub repository jordanrendric/claude-video-vision (1,296 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 471 once invoked, about $0.0001 per session on Opus 5. 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.

Related

Other commands, from other repositories

media

Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file.

yuting0624/antigravity-for-claude-code · 38 tokens

media

Ask a question about an AUDIO, VIDEO or IMAGE file (or a YouTube/remote URL) with Antigravity (agy / Gemini 3.x multimodal). Beyond transcription — "what decisions were made in this meeting?", "what happens at 2:30 in the video?", "what's the tone of this voice note?". Claude Code can't see/hear media; agy can.

MarcosNahuel/antigravity-plugin-cc · 80 tokens

transcribe

Transcribe and summarize an AUDIO or VIDEO file (or a YouTube/remote URL) with Antigravity (agy / Gemini 3.x multimodal) — something Claude can't do natively. Voice notes, meetings, calls, screencasts. Faithful transcript + summary; timestamps for video/URLs. Saves to docs/agy/transcripts/.

MarcosNahuel/antigravity-plugin-cc · 71 tokens

video

WATCH a video and return a structured VISUAL breakdown (not just a transcript) with Antigravity (agy / Gemini 3.x, natively multimodal in video). Scene-by-scene segments with timestamps, on-screen text/OCR (slides, charts, UI, captions), key visual events, and a summary. For screencasts, tutorials, presentations…

MarcosNahuel/antigravity-plugin-cc · 96 tokens

explain-video

Bridge workflow — analyze content with Gemini research tools, then synthesize an explainer video.

Galbaz1/video-research-mcp · 17 tokens

explain-status

Check status of explainer video projects.

Galbaz1/video-research-mcp · 7 tokens