video-perception

video-perception is a skill for Claude Code from jordanrendric/claude-video-vision. It costs 51 tokens per session (1,221 once invoked), scanned A, original, MIT.

A video-analysis skill for understanding local video files and YouTube videos through their images, sound, and spoken content.

In plain words
What is it for?
Use it to review or analyze MP4, MOV, AVI, MKV, WebM, or YouTube content, including scenes, motion, silence, audio, and detailed segments.
Why use it?
It provides a defined process for inspecting video structure, selecting frames, and examining specific sections.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to review or analyze MP4, MOV, AVI, MKV, WebM, or YouTube content, including scenes, motion, silence, audio, and detailed segments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jordanrendric/claude-video-vision/video-perception
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 · 1,295 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.

Any agent
npx skills add jordanrendric/claude-video-vision --skill video-perception
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 video-perception

README.md
[![agentmods](https://agentmods.dev/badge/skills/jordanrendric/claude-video-vision/video-perception/github.svg)](https://agentmods.dev/skills/jordanrendric/claude-video-vision/video-perception)
Your own site
<a href="https://agentmods.dev/skills/jordanrendric/claude-video-vision/video-perception"><img src="https://agentmods.dev/badge/skills/jordanrendric/claude-video-vision/video-perception/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 video-perception

Your own site · 80×15
<a href="https://agentmods.dev/skills/jordanrendric/claude-video-vision/video-perception"><img src="https://agentmods.dev/badge/skills/jordanrendric/claude-video-vision/video-perception.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,221 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00051 $0.01221
Opus 5 $0.00026 $0.00611
Sonnet 5 $0.00010 $0.00244
Haiku 4.5 $0.00005 $0.00122

Measured 11d ago against content hash e4fc6ce4c6f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-perception 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 11d 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/video-perception/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Perception

You have access to video understanding tools via the claude-video-vision MCP server.

Available Tools

  • video_analyze — Analyze video structure with ffmpeg filters (scene changes, silence, motion, etc.). Use this BEFORE extracting frames to plan your strategy.
  • video_watch — Extract frames + process audio from a video. Supports variable FPS/resolution per segment.
  • video_detail — Drill into specific segments. Separates extraction from viewing — extract many frames, view few at a time.
  • video_info — Get video metadata without processing.
  • video_configure — Change settings (backend, resolution, enable_index, etc.).
  • video_setup — Check/install dependencies.

Workflow

IMPORTANT: You MUST follow these steps in order. Do NOT skip step 2.

  1. Always start with video_info to get duration, resolution, and audio presence. If the user gives a YouTube URL, pass the URL directly as path. The MCP server downloads it with yt-dlp, prefers YouTube subtitles/auto-captions for transcription, and falls back to the configured audio backend only when captions are missing, empty, or suspiciously incomplete.

  2. REQUIRED for videos > 30s: Call video_analyze BEFORE extracting any frames. This is NOT optional — it gives you structural data to make smart extraction decisions. Select filters relevant to the user's question:

    User intent Filters to select
    "What happens in this video?" scene_changes, silence, transcription
    "Find the scene transitions" scene_changes, black_intervals
    "Are there frozen/stuck parts?" freeze, blur
    "Is this a talking head or action?" motion
    "When does the music start?" silence, loudness
    "Analyze the lighting" exposure
    "Summarize this lecture" transcription, scene_changes, silence
    General / unclear intent scene_changes, silence, transcription

    Always include transcription: true when the video has audio — the transcription tells you WHERE to look visually.

Read the full file on GitHub · 97 lines

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. 11d ago First seen · 97 lines · 51 tokens per session scan A e4fc6ce4c6f2

Subscribe to this mod's changes

video-perception is a skill published in the GitHub repository jordanrendric/claude-video-vision (1,295 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,221 once invoked, about $0.0003 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 skills, from other repositories