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 stage-generategit 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/stage-generate)<a href="https://agentmods.dev/skills/orkas-ai/orkas-videostudio/stage-generate"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-videostudio/stage-generate/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/stage-generate"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-videostudio/stage-generate.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 | $0.00047 | $0.01458 |
| Opus 5 | $0.00023 | $0.00729 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
stage-generate 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.
This is a copy
86% identical to stage-generate — 36 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stage-generate
How to produce AI-generated footage and execute a bounded semantic video edit already planned by EDIT/AUTO. Designed HTML remains composition work; deterministic cutting remains stage-edit work. The generation tools are ovs image, ovs video, and ovs speak, followed by ovs edit assembly. Every billable call belongs to a signed generate segment.
Pattern A — talking-head / spokesperson
- Character still: generate one image of the presenter / avatar with the intended look. Keep this reference image and reuse it for every shot of the same character.
- Bring it to life: generate a video from that image (image-to-video). When the provider returns speech + built-in audio, that audio is the deliverable voice — it is lip-synced to the mouth in the clip — so keep it and do NOT synthesize a separate narration. Only when the clip comes back silent do you synthesize the narration (
ovs speak) and add it as the audio track. Synthesizing a fresh TTS track over a clip that already speaks is the #1 talking-head defect: the new audio has different wording/timing/length, so the voice no longer matches the lips. - Polish: add captions / a lower-third / a hook by authoring a small composition (stage-compose) and overlaying it onto the clip — visual-only. Preserve the clip's own (lip-synced) audio through assembly; a captions composition must not carry a narration
<audio>track that would replace the clip's voice.
Pattern B — cinematic / AI b-roll montage
- Storyboard the shots (each: prompt, camera motion, duration).
- Generate each shot (one
ovs videocall per shot; reuse a shared reference image / consistent style prompt for visual continuity). Pass the Gate-C-approved--image-urls,--ratio,--duration,--resolution, and--generate-audiovalues exactly; do not let provider defaults silently replace the signed plan. - Assemble: concatenate the shots in order, add transitions, and overlay a title / captions from a composition.
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.
- 11d ago First seen · 66 lines · 47 tokens per session scan A 1bbd00bd8906
stage-generate is a skill published in the GitHub repository Orkas-AI/Orkas-VideoStudio (486 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,458 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to stage-generate, differing in 36 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…