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/proxy2021/enso/video_studionpx skills add Proxy2021/Enso --skill video_studiogit clone --depth 1 https://github.com/Proxy2021/EnsoWhat 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 | $0.00029 | $0.00768 |
| Opus 5 | $0.00015 | $0.00384 |
| Sonnet 5 | $0.00006 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a new app based on this card's context: [init:claude-opus-4-6|2.1.63|19|0|bypassPermissions]
Tool Reference
enso_video_studio_generate (primary)
Generate a video from a text prompt using Seedance AI. Supports cinematic, realistic, anime, and 3D styles. Duration 4-12 seconds, up to 1080p resolution with native audio.
Parameters:
prompt(string): Detailed scene description. English recommended. Include camera motion, lighting, and style for best results.duration(number): Video duration in seconds (4-12). Default: 5resolution(string): Output resolution: 480p, 720p, or 1080p. Default: 720pratio(string): Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. Default: 16:9generate_audio(boolean): Generate native audio alongside the video. Default: trueseed(number): Random seed for reproducibility. Optional.
enso_video_studio_animate
Animate a still image into a video using Seedance AI. Provide an image as the first frame and an optional motion description.
Parameters:
image_path(string): Absolute path to the source image to animate (first frame)prompt(string): Optional motion/scene description (e.g., 'camera slowly zooms in, leaves sway gently')duration(number): Video duration in seconds (4-12). Default: 5resolution(string): Output resolution: 480p, 720p, or 1080p. Default: 720pratio(string): Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive. Default: adaptive
enso_video_studio_craft_prompt
Use AI to craft an optimized Seedance video prompt from a rough description, script, or idea. Returns a detailed English prompt with camera directions, lighting, and style notes, plus recommended generation settings.
Parameters:
description(string): Your rough idea, story script, or scene description in any languagestyle(string): Visual style hint: cinematic, anime, realistic, noir, fantasy, sci-fi, documentary. Default: cinematicmood(string): Mood hint: dramatic, serene, mysterious, energetic, melancholic, epic. Optional.
What ships with it
13 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.
- app.json 35 KB
- executors/animate.js 3.2 KB runs code
- executors/batch_generate.js 4.3 KB runs code
- executors/craft_prompt.js 4.9 KB runs code
- executors/gallery.js 3.7 KB runs code
- executors/generate.js 3.3 KB runs code
- executors/history.js 2.1 KB runs code
- executors/photo_story.js 9.3 KB runs code
- executors/script_to_scenes.js 7.2 KB runs code
- executors/short_video.js 7.5 KB runs code
- executors/style_gallery.js 13 KB runs code
- executors/view.js 2.0 KB runs code
- template.jsx 75 KB
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.
- 2d ago First seen · 57 lines · 29 tokens per session scan A 8c29d1c9b086
video_studio is a skill published in the GitHub repository Proxy2021/Enso (5 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 768 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
story-import
逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。.
story-deslop
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。.
story-long-analyze
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 拆文库/{书名}/。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。.
story-review
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。.
story-short-write
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。.
story-long-write
长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。.