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 sprite-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/sprite-forge)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/sprite-forge"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/sprite-forge/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/zts212653/clowder-ai/sprite-forge"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/sprite-forge.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 | $0.00194 | $0.02321 |
| Opus 5.5 | $0.00078 | $0.00928 |
| Sonnet 5.5 | $0.00039 | $0.00464 |
| Haiku 4.5 | $0.00019 | $0.00232 |
Grade A, and why
sprite-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 14d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprite Forge — 角色动态素材生产线
出生：F229 xianxian-codex 9 态 atlas 的实际生产管线（2026-06-22~24，
video-to-spritesheet-pipeline.md）。 Skill 化诱因：F258 素材首跑两连翻车（2026-07-08）——猫不知道家里有这条验证过的路，临场发明了两条被淘汰的路线（32px 手搓 + imagegen 逐帧直出），operator 连续两次 identity veto 后拉闸："未来做动态的东西，你们要能想到用这个 skill。"
第一性原理（本 skill 的灵魂判断）
动画的帧间一致性问题，靠换介质解决，不靠更好的 prompt。 imagegen 逐帧独立生图 = 体型漂移、风格跳变、帧间无时序关系（Spike R2 实证，59×64 显示尺寸下可感知劣于视频截帧）。视频模型天然时序连贯——所以生成层必须是视频，图像模型只出首帧。
管线五步（人猫协作产线，人工环节是设计的一部分）
| 步 | 做什么 | 谁 | 关键约束 |
|---|---|---|---|
| 1 锚身份 | 取角色设定母图（KD-21 视觉 canon） | — | 母图库=docs/videos/cucu-pr-flow/assets/references/character-sheets/（按角色名对应 *-r0N.png 四足设定图） |
| 2 生成首尾帧 | imagegen 出 Frame A + Frame B 两张（1024×1024 纯白底）：A=基准姿态，B=同姿态仅微小差异（"Only differences: ... Everything else IDENTICAL"句式） | 生图猫（须原生 imagegen；prompt 可由更贵的猫代写） | 强 2D 风格锚；母图作 reference image 传入；每次只做一个状态；B 帧锁不住（缩放/构图漂移）→ 降级单图 i2v 只用 A 帧 |
| 3 拍视频 | AI 视频工具生成 2-3s 循环：首尾帧模式（A+B，更可控）优先；单图 i2v（只喂 A，更稳）备选 | 人工（operator / 云端 Gemini） | 16:9 横屏 / 低运动强度 / 2D 锚 + 反 3D negative（模板见真相源 §3） |
| 4 截帧加工 | ffmpeg 截帧 → 抠图 → 缩放 → 拼 row | 廉价确定性执行猫即可（按 F293 实时供给/成本信号选，并避开 dossier antiSignals 标了机械活的猫）——纯确定性命令活，别烧贵猫 |
确定性工具链，命令见下 |
| 5 验收 | 三道闸 + 分批审 | 主审猫 + operator identity veto 终审 | 每批过了才做下一批（2-2-3 批次制先例） |
截帧加工命令（Step 4 速查）
ffmpeg -i video.mp4 -vf "fps=4" frame_%02d.png # 2-3s → 8-12 帧
magick frame_01.png -fuzz 10% -transparent white f1.png # 白底转透明（脏边则重跑 despill）
magick f1.png -resize 192x208 -gravity center -extent 192x208 cell_01.png
magick cell_*.png +append state_row.png # 拼 row strip
magick cell_01.png -resize 59x64 preview.png # 必做：缩到实际显示尺寸目检
工艺红线（每条都是真翻车）
- 2D 风格锚是保命符：视频 prompt 首行必须
2D hand-drawn anime illustration style, flat cel-shaded coloring, clean visible outlines+ negative 排除3D/CGI/photorealistic/plastic/Pixar——不加锚视频秒变塑料 3D（R1 实录） - 16:9 横屏：9:16 会把尾巴甩出画框（R1 实录）
- 运动强度调低：大幅运动=角色变形
- 约束宜简（五爪判例）：一页解剖学约束反而让模型逐条画出每个被提到的爪→五爪；operator 一句"不要生成五只猫爪了"完美通过。简单意图 + 一句负面 > 详细规格书
- 主审第一问是"这是不是我们家那只猫"，不是特征锚清单——checklist 全过 + operator"不像"= false pass（F229 r3-alpha 与 F258 两次翻车同型）
- 实战提示词必须回流：Step 3 人工环节实际用的提示词（含中途修正版）才是被验证的版本——生产完成后回流 prompt-pack/provenance。理论版翻车靠人工修正救活却不回流 = 下一只猫在同一个坑再摔一遍
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.
- 14d ago Changed · +1 lines da3917495d75
- 1mo ago First seen · 81 lines · 194 tokens per session scan A fa5f3dbb71dd
sprite-forge is a skill published in the GitHub repository zts212653/clowder-ai (3,471 stars, last pushed today), licensed MIT. It adds 194 tokens to every session and 2,321 once invoked, about $0.0008 per session on Opus 5.5. 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
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.