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/pawvej/vidgrid/agentnpx skills add pawvej/vidgrid --skill agentgit clone --depth 1 https://github.com/pawvej/vidgridWrote 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/pawvej/vidgrid/agent)<a href="https://agentmods.dev/skills/pawvej/vidgrid/agent"><img src="https://agentmods.dev/badge/skills/pawvej/vidgrid/agent.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 | $0.00085 | $0.01454 |
| Opus 5 | $0.00043 | $0.00727 |
| Sonnet 5 | $0.00017 | $0.00291 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
vidgrid 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.
curl -X POST https://api.vidgrid.site/v1/render \ How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vidgrid — let an AI watch a video
LLMs can't watch video, but they can read a single image. vidgrid samples one
frame per second from a video file, tiles them into a numbered storyboard
with timestamps, and (optionally) returns the spoken transcript. The result is
close to "my model just watched a video" for the price of a few image uploads.
Each cell is numbered globally (1, 2, 3…) and tagged with its timestamp, so you can point at an exact moment ("the dialog appears at frame 14, ~0:14").
Input is a local video file you provide. vidgrid does not fetch URLs — if you have a link, download it yourself first, then hand the file to vidgrid.
When to use this
- Summarize a talk / meeting / lecture without anyone watching it
- Find the moment something happens in a screen recording or bug repro
- Read on-screen text, UI state, or slides from a video
- Rank or reject a batch of clips against a shot list
- Any task where you have a video file and need to reason about its content
Setup (one time)
You need a Vidgrid API key. The user can get one in ~20 seconds at
https://vidgrid.site/api (enter an email → click the link → a key
vg_live_… with starter credits arrives by email; or buy credits with the
slider). Then:
export VIDGRID_API_KEY="vg_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
Credits never expire. 1 render = 1 credit. Failed renders are never charged.
Fastest path — the CLI (zero-install)
npx @vidgridapp/cli clip.mp4 # → grid.png (+ grid-transcript.txt), prints credits left
npx @vidgridapp/cli talk.mp4 --grid 4x4 --out talk
npx @vidgridapp/cli screen.mov --no-transcribe
npx @vidgridapp/cli <file> uploads the file to the render API and writes the numbered
grid PNG(s) next to you. Read the PNG(s) to "watch" the video; combine with the
transcript to answer. Needs VIDGRID_API_KEY in the environment.
Or call the API directly
POST https://api.vidgrid.site/v1/render — multipart file upload:
What ships with it
9 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 · 126 lines · 85 tokens per session scan A f801f95b4d2f
vidgrid is a skill published in the GitHub repository pawvej/vidgrid (0 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,454 once invoked, about $0.0004 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
video-editing
Operate Video Agent Runtime projects through structured MCP tools for transcript-first long-form-to-short-form editing, preview review, feedback diagnosis, narration, versioning, and approved export. Use for editing an existing runtime project; do not use for direct FFmpeg or manual project-JSON changes.
claude-real-video
Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.
claude-real-video
幫 Leo 看影片。當 Leo 丟影片連結（YouTube/IG/TikTok）或本機影片檔，要摘要、分析、拆解對標時使用——Claude 不能直接吃影片，先用這個工具抽關鍵幀＋逐字稿＋運鏡節奏＋聲音/語氣/手勢時間軸再讀。.
edit-video
Edit video with FableCut — assemble a cut, add titles and captions, grade, add transitions, keyframe animation, speed ramps, and export. Use whenever the user wants to cut, trim, caption, subtitle, grade, or otherwise edit a video, or asks to open/start the video editor.
remake-reel
Analyze a reference video (a reel, montage, or ad the user likes) into an edit blueprint — shot boundaries, music beats, BPM, energy curve, the drop — and rebuild the same structure with the user's own footage. Use when someone says "make it like this video", "remake this reel with my clips", or asks what makes an…
claude-real-video-for-agents
Install and use crv (claude-real-video) — a tool that lets any AI agent watch videos by extracting scene-aware keyframes, deduplicating them, and transcribing audio. Use when the user shares a video URL or file and wants it analyzed, summarized, or discussed.