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.
npx agentmods add skills/vusallyv/video-context-plugin/video-contextnpx skills add vusallyv/video-context-plugin --skill video-contextgit clone --depth 1 https://github.com/vusallyv/video-context-pluginWrote 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.
[](https://agentmods.dev/skills/vusallyv/video-context-plugin/video-context)<a href="https://agentmods.dev/skills/vusallyv/video-context-plugin/video-context"><img src="https://agentmods.dev/badge/skills/vusallyv/video-context-plugin/video-context.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00105 | $0.00810 |
| Opus 5 | $0.00053 | $0.00405 |
| Sonnet 5 | $0.00021 | $0.00162 |
| Haiku 4.5 | $0.00011 | $0.00081 |
Grade A, and why
video-context scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Public URL (Loom, YouTube, Vimeo, public CDN, raw mp4) | `yt-dlp` first, falls back to `curl`. | How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-context
Claude reads images, not videos. This skill turns any video into scene-change frames + audio transcript so Claude can reason about it.
Standalone — works on any source: local file, public URL, or private URL with auth.
When to use
User shares a video and wants Claude to understand its content. Examples:
- "Analyze this video: "
- "What does this recording show? /path/to/file.mp4"
- "The bug is in this Loom: https://loom.com/share/..."
- Bug ticket (Jira/Asana/GitHub/Linear) contains a video attachment.
How to use
${CLAUDE_PLUGIN_ROOT}/skills/video-context/extract.sh <url-or-path>
Script auto-resolves the source:
| Source | How it's fetched |
|---|---|
| Local file path | Used directly. |
| Public URL (Loom, YouTube, Vimeo, public CDN, raw mp4) | yt-dlp first, falls back to curl. |
| Private URL needing auth | curl with VIDEO_AUTH_HEADER env var. |
Private URL with auth
Set VIDEO_AUTH_HEADER to whatever the host needs:
# Bearer token
VIDEO_AUTH_HEADER="Authorization: Bearer $TOKEN" \
${CLAUDE_PLUGIN_ROOT}/skills/video-context/extract.sh "https://host.example/asset/123"
# Basic auth (e.g. Atlassian email + API token)
VIDEO_AUTH_HEADER="Authorization: Basic $(echo -n "$EMAIL:$TOKEN" | base64)" \
${CLAUDE_PLUGIN_ROOT}/skills/video-context/extract.sh "https://your-org.atlassian.net/rest/api/3/attachment/content/12345"
If user shares a private URL without a token, ask for one — or tell them to download the video and paste the local path.
After it runs
Script prints WORKDIR, frame paths, transcript path. Then:
Readeach frame — Claude sees JPEGs natively.Readthe transcript at$WORKDIR/transcript.txt.- Combine frames + transcript to answer the user.
Tuning (env vars)
| Var | Default | What |
|---|---|---|
SCENE_THRESHOLD |
0.4 |
Lower = more frames. Screen recordings often need 0.2. |
MAX_FRAMES |
20 |
Hard cap; trimmed evenly across timeline. |
FRAME_WIDTH |
1280 |
Downscale to save tokens. |
WHISPER_MODEL |
/opt/homebrew/share/whisper-cpp/ggml-base.en.bin |
whisper-cpp model path. |
What ships with it
2 files beside SKILL.md 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.
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.
- 3d ago First seen · 76 lines · 105 tokens per session scan A 1e773c48fe72
video-context is a skill published in the GitHub repository vusallyv/video-context-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 105 tokens to every session and 810 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
i-see-you
Take a still photo from the machine's local webcam with ffmpeg, then read/analyze or send the image. Cross-platform — Linux (V4L2), macOS (AVFoundation), Windows (DirectShow). Trigger when the user asks to "看看我", "take a photo", "take a picture", "selfie", "拍照", "自拍", "看看现在的环境/房间", or when the agent needs to visually…
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
product-launch-motion
Use when making, directing or rescuing a product launch video, promo, teaser, demo reel, sizzle, feature-announcement film or animated product explainer built from code — and when an existing one looks basic, reads as a slideshow, has reveals that miss the voiceover, an invisible cursor, an inaudible sound effect, a…
rebuild-site
Rebuild a whole landing page / multi-section website from a screen recording that scrolls or walks through it. Use when the user has a recording of an ENTIRE page (not a single animation) and wants the full page recreated — layout, sections, copy, design system, and scroll animations. Orchestrates analyze (measured…
recreate
Recreate an analyzed animation as working web code — GSAP (JavaScript), CSS/Web Animations, Framer Motion (React), or Lottie/SVG. Use after /motiscope:analyze, or when the user asks to "build/recreate this animation in ". Reads the motiscope animation spec and emits a runnable component.