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.
git clone --depth 1 https://github.com/jiushiwon/wg-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/commands/jiushiwon/wg-skills/forge)<a href="https://agentmods.dev/commands/jiushiwon/wg-skills/forge"><img src="https://agentmods.dev/badge/commands/jiushiwon/wg-skills/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/commands/jiushiwon/wg-skills/forge"><img src="https://agentmods.dev/badge/commands/jiushiwon/wg-skills/forge.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01252 |
| Opus 5 | $0.00000 | $0.00626 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
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 9d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge — 场景化生成
按指定场景（移动/PC/管理端/营销页/文档/金融/原生/3D）从零生成页面或项目。
用法
forge <scenario> [--brand <name>] [--stack <name>] [--dark] [--prose-only]
参数
| 参数 | 说明 | 默认 |
|---|---|---|
<scenario> |
必填，场景名 | — |
--brand |
品牌风格 | 赤琥金（中文）/ Stripe / Linear |
--stack |
技术栈 | html-tailwind |
--dark |
暗色模式优先 | 否（浅色优先） |
--prose-only |
只输出文案 + 骨架，不写实现 | 否 |
支持的场景
mobile-responsive / pc-corporate / admin-dashboard / landing-marketing / docs-site / fintech-app / mobile-native / threejs-3d
支持的技术栈
html-tailwind / react-nextjs / vue-nuxt / uniapp / react-native / svelte
6 步流水线
1. 加载场景基线
读取 references/scenarios/<scenario>.md，获取布局、组件、交互基线。
2. 选择品牌/调色板
优先级：用户指定品牌 → 推荐品牌（场景默认）→ 默认调色板（赤琥金）
读取 references/brands/<name>.md（如指定）获取调色策略 + 字体配对。
调色板快速选择：
- 场景默认品牌映射（见 SKILL.md 主文件）
- 用户可追加
--brand覆盖
3. 生成 Token
合并场景 + 品牌，输出完整 Token：
- CSS 变量文件（
tokens.css） - Tailwind 配置（如用 Tailwind）
- 主题对象（如用 JS 主题）
模板见 templates/tokens.css.tpl 和 templates/tokens.tailwind.tpl。
4. 生成代码骨架
按技术栈输出：
| 栈 | 输出 |
|---|---|
| html-tailwind | 单页 HTML + Tailwind config + 全局 CSS |
| react-nextjs | Next.js 项目结构 + page.tsx + 基础组件 |
| vue-nuxt | Nuxt 项目结构 + page.vue + 基础组件 |
| uniapp | pages.json + 页面 + 组件 |
| react-native | RN 项目结构 + screens + components |
| svelte | SvelteKit 路由 + page.svelte + 组件 |
5. 应用设计法则
按 anti-patterns.md 自检：
- 调色策略（4 档承诺度）
- 字号阶 ≥1.25 比例
- 行长 65-75ch
- 绝对禁令检查（侧边色条、渐变文字、玻璃拟态默认、hero-metric、相同卡片网格、模态第一反应）
- 减弱动效支持
- 触摸目标 ≥44pt
- 文字对比度 ≥4.5:1
6. 输出报告
# Forge Report — <scenario>
## 场景
- 场景：<scenario>
- 品牌：<brand>
- 技术栈：<stack>
- 主题：light / dark
## 调色板
- 主色：oklch(0.55 0.16 28) — 朱砂红
- 策略：Committed
## 字体
- 标题：'Noto Sans SC', sans-serif
- 正文：'Noto Sans SC', sans-serif
- 等宽：'JetBrains Mono', monospace
## 间距阶梯（4pt 网格）
4 / 8 / 12 / 16 / 20 / 24 / 32 / 40 / 48 / 64 / 96 / 128
## 文件清单
- [tokens.css]()
- [tailwind.config.ts]()
- [index.html]()
- [components/Button.vue]()
- ...
## 自检
- [x] 调色策略 Committed
- [x] 字号阶 ≥1.25
- [x] 触摸目标 ≥44pt
- [x] 减弱动效
- [x] 无 AI slop
## 截图
[本地路径 / URL]
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.
- 9d ago First seen · 144 lines · 0 tokens per session scan A 773cdf0ff80e
forge is a command published in the GitHub repository jiushiwon/wg-skills (97 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,252 tokens. 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 commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.
frontend-design
Read and follow the instructions in agents/frontend-design/design-all.md. Also read all referenced files in agents/frontend-design/reference/ as needed for the task.
get-component-source
The full TSX source of a component (append " demo" for its usage example).