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 Cloudgeni-ai/opengeni --skill opengeni-video-generationgit clone --depth 1 https://github.com/Cloudgeni-ai/opengeniWrote 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/cloudgeni-ai/opengeni/opengeni-video-generation)<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/opengeni-video-generation"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/opengeni-video-generation/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/cloudgeni-ai/opengeni/opengeni-video-generation"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/opengeni-video-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00262 |
| Opus 5 | $0.00017 | $0.00131 |
| Sonnet 5 | $0.00007 | $0.00052 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
opengeni-video-generation 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.
What it actually says
Video generation
Use get_video_generation_capabilities when model or source support matters. Then call generate_video once for each intentionally distinct output.
- Use
textfor a new scene without reference media. - Use
first_frameto animate one exact opening frame. - Use
first_and_last_framesonly when both ordered endpoint frames matter. - Use
image_referencefor semantic/style/character guidance rather than an exact opening frame. - Use
video_referenceto transform or continue the visual language of one existing video. - Pass exact absolute
/workspace/...paths. Never invent a path or pass a URL. - Choose an explicit model only when capability discovery shows it is available; otherwise allow the workspace default.
- Treat an
acceptedresult as asynchronous durable work. Continue other useful work instead of polling or calling again. - A later platform update provides the terminal result and retained sandbox path. Never retry automatically after failure or uncertainty; a retry is another paid generation.
- Do not promise that a file exists in the sandbox until the terminal result supplies its verified path.
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 · 20 lines · 34 tokens per session scan A ce636f8bc574
opengeni-video-generation is a skill published in the GitHub repository Cloudgeni-ai/opengeni (127 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 262 once invoked, about $0.0002 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.
Other skills, from other repositories
ax-java-audio
Use when writing Java code with dev.axllm:ax for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.
live2d_controller
// 读取：system.characterbundle.loadcharacterskillsections -> system.config.buildtier1variables.characterbuiltinskillsprompt.
atet
Use Atet to create, generate, record, edit, and render visual media with a local CLI and coding agent. Trigger for AI image or video generation, screen, camera, microphone, or system-audio recording, non-destructive video editing, silence and filler-word removal, captions or subtitles, speaker framing, screen zooms…
pn-html-to-video
Deterministic, programmatic video from HTML compositions. Covers the HTML composition contract (data-start, data-duration, data-track-index), Frame Adapter pattern (GSAP / Lottie / CSS / Three.js), Puppeteer+FFmpeg capture pipeline, delivery sheet, and tool selection (Hyperframes / Remotion / Motion Canvas). Use when…
pn-transcribe
Speech-to-text transcription for video production — word-level timestamps, SRT/VTT caption track generation, forced alignment, hallucination detection, and caption formatting standards. Use after TTS or screen recording to produce caption tracks for video compositions.
pn-tts
Text-to-speech for video and audio production. Covers tool selection (ElevenLabs, OpenAI, Kokoro/local), voice and model choice, SSML expressivity, caption-track alignment (SRT/VTT), loudness normalization, retry strategy, and accessibility requirements. Use when a composition or generative video needs narration audio…