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 rullerzhou-afk/pet-forge --skill pet-forgegit clone --depth 1 https://github.com/rullerzhou-afk/pet-forgeWrote 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/rullerzhou-afk/pet-forge/pet-forge)<a href="https://agentmods.dev/skills/rullerzhou-afk/pet-forge/pet-forge"><img src="https://agentmods.dev/badge/skills/rullerzhou-afk/pet-forge/pet-forge.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00081 | $0.03912 |
| Opus 5 | $0.00041 | $0.01956 |
| Sonnet 5 | $0.00016 | $0.00782 |
| Haiku 4.5 | $0.00008 | $0.00391 |
Grade A, and why
pet-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 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pet-forge skill —— 触发条件 + 调用流程
给 AI coding agent 看的 skill 接入文档。当用户说"我想做桌宠"时,agent 应该按本文件的指引响应。
触发条件
当用户消息中出现以下信号时,激活 pet-forge skill:
强信号(必触发)
- "我想做(自己的 / 一个)桌宠"
- "做个 SVG 桌宠 / APNG 桌宠"
- "帮我做一个 idle 动画"
- "怎么做桌宠"
- "桌宠 [角色名],[风格]"
弱信号(询问后再决定)
- "我喜欢某个现有桌宠案例"(可能想要 fork 而不是做新的)
- "想做个动画"(可能不是桌宠,可能是其他动画)
- "做个角色"(可能是设计需求,不是动画)
弱信号触发时反问:"你是想做一个会循环动 + 接桌宠运行时的角色吗?还是只是单帧动画/设计图?"
反触发(不要触发)
- 用户已经在做某个具体产品项目,而不是想用 pet-forge 新建角色
- 用户只是在问某个现有桌宠是什么,而不是动手做
第一轮响应模板
skill 触发后,Claude 第一句话不要写代码,先确认 4 件事:
- 角色是什么:"你想做的角色是什么?(例:橘猫 / 机器人 / 蘑菇 / 你已有的设定...)"
- 角色拓扑:"它是只有头、头+身体,还是一团主体?有没有手脚、耳朵、尾巴、触角、道具、眼睛、嘴巴?是站地、悬浮还是贴边?"
- 审美方向:"想要什么风格?(例:苹果精致风 / 像素风 / 蹦跳多巴胺 / 禅宗极简 / 你给参考图)"
- 路线倾向:"你想要 SVG 还是 APNG?两者特性差异大:[列两路线对比表],没想好的话先选 SVG(不付费、可热改)"
路线选择决策树
用户回答"想要..."
│
├─ "循环完美 / 不付费 / 可热改" → 推荐 SVG 路线
├─ "快出成品 / 不在乎钱 / 风格化强" → 推荐 APNG 路线
├─ "不会写代码" → 推荐 APNG 路线(prompt 工程门槛低于前端动画)
├─ "想要精致圆润矢量感" → SVG 路线 + apple-precise preset
├─ "想要像素感" → SVG 路线 + pixel-art preset
└─ "都想试试" → 先 SVG(启动门槛低),跑通再考虑 APNG
SVG 路线工作流(skill 引导)
第 0 步:角色拓扑盘点
先不要默认角色一定有完整头、身体、手脚和嘴巴。问清:
- 主体形态:只有头、头+身体、一团主体、道具/物件,还是其他轮廓;
- 脸部结构:有没有眼睛、嘴巴、腮红、表情符号;
- 附属结构:有没有手、脚、耳朵、尾巴、触角、翅膀、道具;
- 支撑关系:站地、悬浮、贴边、挂载,还是靠道具支撑;
- 目标动作:转头、抬低头、眼睛跟随、表情、走路、挥手、弹跳、漂浮。
根据拓扑决定后续读哪些文档:
- 有脸部方向需求 →
routes/svg/conventions/head-motion-axis.md - 有主体 / 身体转向需求 →
routes/svg/conventions/body-motion-axis.md - 有手脚、尾巴、触角、道具等附属结构 →
routes/svg/conventions/limb-rig-points.md - 有嘴巴或多表情系统 →
routes/svg/conventions/expression-mouth-system.md - 没有手脚、尾巴、触角或道具时,不要强行套附属结构 rig;退化为主体轮廓、重心 / 悬浮基准和呼吸即可
- 没有嘴巴时,不要强行套 mouth rig;用眼睛、眉毛、腮红、表情符号或整体形变表达情绪
第 1 步:确定角色基础造型
询问用户:
- "你的角色基础造型在哪?" 三选项:
- A: 已有 PNG → 直接用
- B: 想 AI 生 → 推荐 ChatGPT / Claude 网页 / Midjourney 自己生(skill 不调 API)
- C: 自己画 → Figma / Procreate / 等等
关键:保证用户拿到一张透明背景 PNG。如果不是透明,引导用户用 rembg 处理:
py -3.13 -m pip install "rembg[cpu,cli]"
py -3.13 -m rembg i input.png input-clean.png
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 Changed · +3 lines 32366937b30b
- 8d ago First seen · 265 lines · 81 tokens per session scan A 141dba07f0a0
pet-forge is a skill published in the GitHub repository rullerzhou-afk/pet-forge (48 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 3,912 once invoked, about $0.0004 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.