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 skills add Orkas-AI/Orkas-VideoStudio --skill video-craftgit clone --depth 1 https://github.com/Orkas-AI/Orkas-VideoStudioWrote 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/orkas-ai/orkas-videostudio/video-craft)<a href="https://agentmods.dev/skills/orkas-ai/orkas-videostudio/video-craft"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-videostudio/video-craft/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.
<a href="https://agentmods.dev/skills/orkas-ai/orkas-videostudio/video-craft"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-videostudio/video-craft.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00093 | $0.03072 |
| Opus 5 | $0.00046 | $0.01536 |
| Sonnet 5 | $0.00019 | $0.00614 |
| Haiku 4.5 | $0.00009 | $0.00307 |
Grade A, and why
video-craft 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.
This is a copy
97% identical to video-craft — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-craft
The difference between a video that merely renders and one that's actually good. Apply these standards while scripting, storyboarding, composing, generating, and editing — and run the self-check before publishing. These are general production-craft norms; the exact numbers are starting points, adjust to the brief.
1. The opening (hook)
- The first 1–3 seconds decide whether anyone keeps watching. Frame 1 must already carry motion or a text hook — no blank intro, no logo sting, no slow build.
- Strong hook shapes: a sharp question, a counter-intuitive claim, the promised outcome ("by the end you'll…"), the stakes, or showing the finished result first ("here's what we'll build").
- On muted autoplay the on-screen text is the hook — assume no sound for the first beat.
- Weak → strong: ✗ "In this video we'll look at caching." (slow build, no stakes) → ✓ frame 1, bold on-screen text "Your API is slow. One line fixes it." (stakes + promised outcome, readable muted).
2. Story structure
- Arc: hook → tension/gap → core idea(s) → proof/example → payoff/close (+ optional CTA). Land the first real payoff early; viewers drop off fast before they get value.
- One new idea per ~30–45 s of explainer. A 3-min video carries 4–6 ideas, no more. Cut "interesting but irrelevant" — it actively lowers comprehension.
- Connect beats with "but" / "therefore", not "and then" — force logical (not just sequential) progression.
- For teaching: show the naive idea, let it half-work, then break it and introduce the one key insight — people remember what they feel they discovered. Surfacing a common misconception first, then correcting it, beats stating the right answer cold.
- Narration cadence: explainer ~150–160 wpm, social/short ~180–200 wpm, cinematic ~140–150 wpm. Leave a 1–3 s silence after a big reveal; avoid dead air > ~1.5 s between sentences.
3. Pacing & timing
- Shot/scene holds by format: explainer ~4–8 s, short-form social ~1–3 s, cinematic/contemplative ~10–20 s. Don't hold the same length three times running — vary it.
- Cutting energy: rapid (15–30 cuts/min) = urgency; moderate (8–15) = standard teaching; slow (3–6) = documentary calm.
- A visual or audio pattern interrupt every ~20–30 s (short-form) / ~45–90 s (long-form) to re-grab attention.
- Completion drops with length (15 s clips finish far more often than 60 s) — keep it as short as the message allows; don't pad.
- Build animation timing to the narration words, not arbitrary beats. Hold a fully-built scene/chart ≥ 2–3 s before moving on.
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.
- 12d ago First seen · 124 lines · 93 tokens per session scan A 68f5f10e0f75
video-craft is a skill published in the GitHub repository Orkas-AI/Orkas-VideoStudio (486 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 3,072 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to video-craft, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
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-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.
video-production
Use when the user wants a finished video out of gflow rather than a single clip — a scripted scene, a talking-head or dialogue piece, an explainer, a product montage, a story sequence, an audition or rehearsal reference, a short film — or asks for consistent actors, a consistent location, a specific prop that must not…
review-video-with-pingfusi
Have any video reviewed by a real human, through iterative pingfusi review rounds. Use when asked to "review this video", "check the rendered video", "does this video match the prompt/brief", "what do people think of this ad/trailer/demo", or after rendering a Remotion composition or AI-generated clip that no test can…
verticals
AI-native vertical video engine with niche intelligence. Takes a one-line topic and a niche profile, and outputs a finished YouTube Short/Reel/TikTok with AI-generated b-roll, voiceover, burned-in captions, background music, and thumbnail. Supports multiple LLM providers (Claude, Gemini, GPT, Ollama), TTS providers…
classical-poem-silk-video
Turn Chinese classical poems and ci into coherent vertical Chinese-art videos with poem-driven scene grouping, GPT ImageGen stills, Docker-only Gemini I2V, retained model-generated ambience, Gemini sparkle-watermark cleanup, brush-calligraphy captions revealed character by character, optional local BGM mixing…