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 rules/nuwax-ai/nuwax/project-rulesgit clone --depth 1 https://github.com/nuwax-ai/nuwaxWrote 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/rules/nuwax-ai/nuwax/project-rules)<a href="https://agentmods.dev/rules/nuwax-ai/nuwax/project-rules"><img src="https://agentmods.dev/badge/rules/nuwax-ai/nuwax/project-rules.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 | $0.00011 | $0.02233 |
| Opus 5 | $0.00005 | $0.01117 |
| Sonnet 5 | $0.00002 | $0.00447 |
| Haiku 4.5 | $0.00001 | $0.00223 |
Grade A, and why
project-rules 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 3d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能体平台前端项目开发规则
项目概述
这是一个基于 React 18 + UmiJS Max + Ant Design 的智能体平台前端项目,提供智能体开发、管理和使用的完整解决方案。
技术栈规范
核心技术
- 前端框架: React 18 (函数组件 + Hooks)
- UI 组件库: Ant Design 5.x + ProComponents
- 图形引擎: AntV X6 (流程图、图可视化)
- 框架工具: UmiJS Max 4.x (约定式路由、插件体系)
- 状态管理: UmiJS 内置 model (主要方案)
- 类型检查: TypeScript 5.x
- 样式方案: CSS Modules + Less (禁止全局污染)
- 包管理: pnpm (Node.js > 18.0.0)
代码规范
文件命名
- 组件文件:PascalCase (如
UserProfile.tsx) - 工具文件:camelCase (如
formatDate.ts) - 样式文件:与组件同名 (如
UserProfile.less) - 类型文件:camelCase +
.types.ts后缀
组件开发规范
// 组件必须包含详细注释
/**
* 用户资料组件
* @param {Object} props - 组件属性
* @param {string} props.userId - 用户ID
* @param {boolean} props.editable - 是否可编辑
* @param {Function} props.onSave - 保存回调
* @returns {JSX.Element} 用户资料组件
*/
interface UserProfileProps {
userId: string;
editable?: boolean;
onSave?: (data: UserData) => void;
}
const UserProfile: React.FC<UserProfileProps> = ({ userId, editable = false, onSave }) => {
// 组件实现
};
性能优化要求
- 使用
useMemo缓存计算结果 - 使用
useCallback缓存函数引用 - 路由和组件必须懒加载
- 表单、表格优先使用 ProComponents
- 图形功能统一使用 AntV X6
状态管理规范
- 全局状态使用 UmiJS model
- 局部状态使用 useState/useReducer
- 避免 props 层层传递
- 异步请求封装在
services/目录
样式规范
// 使用 CSS Modules,避免全局污染
.userProfile {
// 组件样式
&__header {
// 子元素样式
}
&--editable {
// 修饰符样式
}
}
AppDev Web IDE 开发规范
文件结构规范
- 页面组件:
pages/AppDev/components/目录下 - 自定义 Hooks:
hooks/useAppDev*.ts命名规范 - 状态管理: 使用
models/appDev.ts中的useAppDevStore - API 服务:
services/appDev.ts统一管理
核心 Hooks 使用
// 文件管理
const fileManagement = useAppDevFileManagement({
projectId: workspace.projectId,
onFileSelect: setActiveFile,
onFileContentChange: updateFileContent,
});
// AI 聊天
const chat = useAppDevChat({
projectId: workspace.projectId,
onMessage: handleMessage,
});
// 开发服务器
const server = useAppDevServer({
projectId: workspace.projectId,
onStatusChange: handleServerStatus,
});
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.
- 3d ago First seen · 250 lines · 11 tokens per session scan A 2aae8061c8e0
project-rules is a cursor rule published in the GitHub repository nuwax-ai/nuwax (874 stars, last pushed 6d ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,233 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 2026-08-30.
Other cursor rules, from other repositories
component_layer_rules
Component layer rules for reusable and feature-specific UI components.
hook_layer_rules
Hook layer rules for custom React hooks and state management.
frontend_overview_rules
Frontend overview - directory structure, layer responsibilities, and dependency rules.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
react
React 19 SPA invariants - client-only, no fetch in useEffect, Compiler memo policy.
react_hooks
React Hooks best practices for frontend package.