Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 zts212653/clowder-ai --skill anime-forgegit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/anime-forge)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/anime-forge"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/anime-forge.svg" alt="Measured on agentmods" 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 | $0.00142 | $0.02118 |
| Opus 5 | $0.00071 | $0.01059 |
| Sonnet 5 | $0.00028 | $0.00424 |
| Haiku 4.5 | $0.00014 | $0.00212 |
Grade A, and why
anime-forge 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anime Forge — AI 动画短片生产线
出生：EP01「醋醋喵诞生记」（2026-06-10~12，docs/videos/cucu-pr-flow/）。本 skill 的每条规则都对应一次真实翻车或一次实测验证，n=1 边界诚实标注——竖屏重制就是第一次 dogfood，踩到新坑回来补 Common Mistakes。
为什么是 skill（价值门禁）
不教"什么是 i2v"。只沉淀：实测分工路由（中文乱码）、prompt 配方（四次翻车打磨）、工程纪律（防 operational cost 跑偏重演）、六个真金白银的坑。
第一性架构：确定性分层
视频模型不能同时当导演、UI 设计、演员和剪辑师。 把确定性按层分配：
| 层 | 负责 | 绝不交给它的 |
|---|---|---|
| 图（关键帧） | 画风、角色一致性、屏幕文字、构图 | — |
| 视频（i2v） | 活气：表情微动、小动作 | 精确文字、节奏、画风决定权 |
| 后期（剪辑） | 节奏卡点、字幕、SFX、时间字卡 | — |
推论：状态卡/信息卡镜头根本不需要 i2v——静帧+剪辑切=零抽卡。EP01 11 镜头只抽了 8 个视频。
流程（每步指向真相源，不复制）
- 立项 charter（operator signoff 的 scope/路线/预算护栏/Non-goals）→ 范例
docs/videos/cucu-pr-flow/episode-brief.md；轻量立项规则见 shared-rules §21（LL-071：先对齐再批量产出） - 分镜表：每镜头唯一验收点（一镜一梗）+ 类型 + 方法 + FM 标签 + 3 连败降级预案 → 范例
shot-plan-v0.1.md - Prompt book：图 prompt + i2v prompt 全部写成可复制块，含 per-shot 翻车修法 → 范例+配方
prompt-book-v0.1.md（§0.5 附图铁则 / §0.6 i2v 五段配方——从实测成功原文最小修改，禁止凭理解重写） - 生产 roll：每 prompt ≤3 roll；roll 判定/FM taxonomy 用
review-protocol-v0.1.md；30 秒人工验收四问（画风像锚图吗/人物比例/文字可读/构图漂没漂） - 素材账本：入库即登记 md5/时长/状态；视频 gitignored 账本作存在证明 → 范例
assets/README.md - Animatic 检查点（行为刹车）：烧贵素材前先用静帧+占位拼粗剪验证节奏；剧本结构问题（见下）必须在这层抓
- EDL 渲染：
animatic/edl-v1.mjs（时长/字幕/段序真相源）+build-animatic.mjs（零 npm 依赖：Chrome 当字幕/字卡渲染器 + ffmpeg）——改数字重渲，画幅参数化 - 交付/预览：最终成片必须在 Console 里内联可看，不要只丢工作区路径。外部直链可直接发 rich block；本地 mp4 先变成
/uploads/...再发kind:"file"+mimeType:"video/mp4"。只有你明确需要autoplay muted且拿到的是外部直链时，才退回html_widget+<video>
实测分工路由（硬约束，不是偏好）
| 任务 | 路由 | 实测依据 |
|---|---|---|
| 含中文文字的图/卡 | GPT 系生图 | Google 系图/视频中文乱码（2026-06-12 实测） |
| i2v 生视频 | Gemini 系 | 时长遵守 prompt 的 N-second 指令（非固定 10s） |
| 字幕/字卡/注解 | 本地 Chrome 渲染 + ffmpeg overlay | 中文完美、零成本、绕开无 libass |
剧本结构（导演层 checklist）
- 喜剧 = 预期 vs 现实，预期端必须拍（任务多小/时间多久）——EP01 初剪"观众看不懂"就是只拍了现实端
- 动机闭环：种子（S00 宣布）→ 潜意识曝光（用自己的头像）→ OS 自白 → 定罪 → true end（爱）
- 真实素材 payoff：片头承诺（"呈堂证供"）片尾兑现（聊天截图证据卷轴）
- 内心 OS 用独立字幕样式（os 参数）；时间跳跃用默片字卡（intertitle.html）
Common Mistakes（全部实测，持续补）
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.
- 8d ago First seen · 83 lines · 142 tokens per session scan A 7a600e492c9b
anime-forge is a skill published in the GitHub repository zts212653/clowder-ai (2,924 stars, last pushed today), licensed MIT. It adds 142 tokens to every session and 2,118 once invoked, about $0.0007 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.