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/soaring-xiongkulu/easyaiotWrote 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/soaring-xiongkulu/easyaiot/project-overview)<a href="https://agentmods.dev/rules/soaring-xiongkulu/easyaiot/project-overview"><img src="https://agentmods.dev/badge/rules/soaring-xiongkulu/easyaiot/project-overview/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/rules/soaring-xiongkulu/easyaiot/project-overview"><img src="https://agentmods.dev/badge/rules/soaring-xiongkulu/easyaiot/project-overview.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 | $0.00416 | $0.00416 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
project-overview 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 10d 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.
What it actually says
unibest 项目概览
这是一个基于 uniapp + Vue3 + TypeScript + Vite5 + UnoCSS 的跨平台开发框架。
项目特点
- 支持 H5、小程序、APP 多平台开发
- 使用最新的前端技术栈
- 内置约定式路由、layout布局、请求封装、登录拦截、自定义tabbar等功能
- 无需依赖 HBuilderX，支持命令行开发
核心配置文件
- package.json - 项目依赖和脚本配置
- vite.config.ts - Vite 构建配置
- pages.config.ts - 页面路由配置
- manifest.config.ts - 应用清单配置
- uno.config.ts - UnoCSS 配置
主要目录结构
src/pages/- 页面文件src/components/- 组件文件src/layouts/- 布局文件src/api/- API 接口src/http/- HTTP 请求封装src/store/- 状态管理src/tabbar/- 底部导航栏src/App.ku.vue- 全局根组件（类似 App.vue 里面的 template作用）
开发命令
pnpm dev- 开发 H5 版本pnpm dev:mp- 开发微信小程序pnpm dev:mp-alipay- 开发支付宝小程序（含钉钉）pnpm dev:app- 开发 APP 版本pnpm build- 构建生产版本
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.
- 10d ago First seen · 37 lines · 416 tokens per session scan A 3646190d55e6
project-overview is a cursor rule published in the GitHub repository soaring-xiongkulu/easyaiot (712 stars, last pushed 5d ago), licensed MIT. It adds 416 tokens to every session, about $0.0021 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
sveltekit-tailwindcss-typescript-cursorrules-promp
Cursor rules for SvelteKit development with Tailwind CSS and TypeScript integration.
frontend
You are an expert in TypeScript, Node.js, Vite, Vue.js, Vue Router, Pinia, VueUse, Ant Design Vue, and UnoCSS, with a deep understanding of best practices and performance optimization techniques in these technologies.
code
A set of coding rules for Vue 3 components written with TypeScript. It covers component structure, typed properties and events, reusable composables, and stylesheet conventions.
structure
A set of frontend project rules for organizing files, naming code, using TypeScript, and structuring Vue components. It specifies locations and conventions for components, styles, API code, utilities, types, imports, and exports.
vue-rules
You are an expert in JavaScript, TypeScript, and the Vue.js framework for scalable web development.
vue3-typescript-auto
Vue 3 with TypeScript Standards.