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 pexoai/pexo-skills --skill videoagent-video-studiogit clone --depth 1 https://github.com/pexoai/pexo-skillsWrote 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/pexoai/pexo-skills/videoagent-video-studio)<a href="https://agentmods.dev/skills/pexoai/pexo-skills/videoagent-video-studio"><img src="https://agentmods.dev/badge/skills/pexoai/pexo-skills/videoagent-video-studio/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/pexoai/pexo-skills/videoagent-video-studio"><img src="https://agentmods.dev/badge/skills/pexoai/pexo-skills/videoagent-video-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00056 | $0.01791 |
| Opus 5 | $0.00028 | $0.00896 |
| Sonnet 5 | $0.00011 | $0.00358 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
videoagent-video-studio 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.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎬 VideoAgent Video Studio
Use when: User asks to generate a video, create a video from text, animate an image, make a short clip, or produce AI video.
Generate short AI videos with 7 backends. This skill picks the right mode (text-to-video or image-to-video), enhances the prompt for best results, and returns the video URL.
Quick Reference
| User Intent | Mode | Typical Duration |
|---|---|---|
| "Make a video of..." (no image) | text-to-video |
4–10 s |
| "Animate this image" / "Make this move" | image-to-video |
4–6 s |
| "Turn this into a video with..." | image-to-video |
4–6 s |
| Cinematic, story, ad | Prefer text-to-video with detailed prompt |
5–10 s |
Generation Modes
| Mode | Description | Models |
|---|---|---|
| text-to-video | Text prompt only → video | minimax, kling, veo, hunyuan, grok, seedance |
| image-to-video | Single image + prompt → animated clip | minimax, kling, veo, pixverse, grok, seedance |
| reference-based | Reference images/video → consistent output | minimax, kling, veo, hunyuan, grok, seedance |
Models (use --model <id>)
| Model ID | T2V | I2V | Reference | Notes |
|---|---|---|---|---|
minimax |
✅ | ✅ | ✅ | Subject reference image, character consistency |
kling |
✅ | ✅ | ✅ | Multi-element / character / keyframe (O3) |
veo |
✅ | ✅ | ✅ | Google Veo 3.1, multiple reference images |
hunyuan |
✅ | — | ✅ | Video-to-video style transfer |
pixverse |
— | ✅ | — | Stylized image-to-video |
grok |
✅ | ✅ | ✅ | Video editing via reference video |
seedance |
✅ | ✅ | ✅ | Seedance 1.5 Pro, synchronized audio, 4–12 s |
Full model details and endpoint reference: references/models.md.
How to Generate a Video
Step 1 — Choose mode and enhance the prompt
- Text-to-video: Expand with subject, action, camera movement, lighting, and style. Be specific about motion (e.g. "camera slowly zooms in", "character walks left to right").
- Image-to-video: Describe the motion to apply to the image (e.g. "gentle breeze in the hair", "camera pans across the scene"). See references/prompt_guide.md for patterns.
What ships with it
22 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.
- package-lock.json 260 B
- package.json 229 B
- proxy/api/generate.js 6.4 KB runs code
- proxy/api/stats.js 7.3 KB runs code
- proxy/api/status.js 1.2 KB runs code
- proxy/api/token.js 2.0 KB runs code
- proxy/models.js 6.3 KB runs code
- proxy/package-lock.json 2.4 KB
- proxy/package.json 176 B
- proxy/README.md 3.9 KB
- proxy/usage-store.js 8.9 KB runs code
- proxy/vercel.json 565 B
- README.md 4.2 KB
- references/calling_guide.md 5.4 KB
- references/models.md 2.9 KB
- references/prompt_guide.md 2.3 KB
- scripts/local-server.cjs 3.0 KB runs code
- scripts/test-api.ps1 10 KB runs code
- scripts/test-generate.ps1 818 B runs code
- scripts/test-generate.sh 845 B runs code
- scripts/test-proxy.cjs 15 KB runs code
- tools/generate.js 4.7 KB runs code
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 · 215 lines · 56 tokens per session scan A d44a8eccb4db
videoagent-video-studio is a skill published in the GitHub repository pexoai/pexo-skills (777 stars, last pushed 22d ago), licensed MIT. It adds 56 tokens to every session and 1,791 once invoked, about $0.0003 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
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.
muapi-director
Turn ONE topic, talking-head video, or photo into a finished Vox-style paper-collage explainer / ad video on the MuAPI platform (api.muapi.ai) + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Three input modalities: a topic (B-roll), a talking-head video (A-roll mode), or…
minimax-video
A video-generation tool for creating short MP4 videos from text, images, video frames, or a subject reference. It uses the MiniMax Hailuo model and saves generated videos locally.
minimax-cli
Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…
open-video
Generate, edit, or direct videos via open-source models (MiniMax H3 baseline; Wan2.2 / LTX future). Use when the user wants to turn a concept, script, or reference image into a finished video or multi-shot film — single shots, image-to-video, first-last-frame interpolation, reference-video/audio styling, or stitched…