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 instructions/wayn111/waynboot-mobile/agents-mdgit clone --depth 1 https://github.com/wayn111/waynboot-mobileWrote 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/instructions/wayn111/waynboot-mobile/agents-md)<a href="https://agentmods.dev/instructions/wayn111/waynboot-mobile/agents-md"><img src="https://agentmods.dev/badge/instructions/wayn111/waynboot-mobile/agents-md.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 | $0.02795 | $0.02795 |
| Opus 5 | $0.01398 | $0.01398 |
| Sonnet 5 | $0.00559 | $0.00559 |
| Haiku 4.5 | $0.00280 | $0.00280 |
Grade A, and why
waynboot-mobile AGENTS.md 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
仓库开发指南 (Repository Guidelines)
基于项目的最新技术栈和迁移经验,本指南规范了 waynboot-mobile 的开发约定,以确保代码库的高质量和一致性。
1. 核心技术栈与架构
本项目已全面升级为现代前端技术栈,主要包括:
- 核心框架:Vue 3 (Composition API,
<script setup>) - 构建工具:Vite 4
- UI 组件库:Vant 4
- 状态管理与路由:Vuex 4 & Vue Router 4
- 样式预处理:Sass (Dart Sass,推荐使用
@use语法) & 配合postcss-pxtorem进行移动端视口适配。
目录结构规范
src/views/:页面级视图组件,通常按功能模块划分(例如src/views/order/confirm/index.vue)。src/components/:全局共享或可复用的 UI 组件(推荐使用PascalCase命名,如NavBar.vue)。src/api/:API 接口封装,按业务领域(domain)分组,如order.js。src/store/:Vuex 状态管理模块。src/router/:Vue Router 路由配置。src/styles/:全局 SCSS/CSS 样式文件。src/icons/svg/:SVG 图标资源目录。src/assets/:图片等其他静态资源。
2. 开发、测试与构建命令
- 启动开发服务器:
npm run dev(通过 Vite 启动本地服务,默认代理/dev-api)。 - 构建生产包:
npm run build:prod。 - 构建测试包:
npm run build:dev。 - 代码规范检查:
npm run lint(检查src/下的.js和.vue文件)。 - SVG 图标优化:在
src/icons/svg/增删改图标后,运行npm run svgo进行压缩和规范化。
测试说明:目前项目未强制配置自动化测试用例,但在提交 PR 或推送代码前,务必在本地运行
npm run lint,并在移动端视图下完成相关功能的冒烟测试。
3. 编码风格与规范
遵循项目根目录的 .editorconfig 和 .eslintrc.js 规则:
- 基础格式:2 个空格缩进,删除行尾多余空格,文件末尾保留一个空行。
- JavaScript/Vue 规范:
- 强制使用单引号 (
')。 - 不使用分号 (
;)。 - 使用全等号 (
===/!==)。 - 变量和函数使用
camelCase(小驼峰命名法)。
- 强制使用单引号 (
- Vue 3 语法特别注意:
- 全面使用
<script setup>语法。 - 避免使用
this:使用useRouter,useRoute,useStore等 Composition API 替代原有的this.$router或this.$store。 - Vant 4 调用:对于弹窗或轻提示,直接从
vant导入函数式 API (如import { showToast, showDialog } from 'vant'),不要再使用挂载在原型上的方法(如this.$toast)。 - 事件派发:使用
const emit = defineEmits(['xxx'])声明并调用emit('xxx'),不要使用旧版的$emit(this, 'xxx')。
- 全面使用
UI 与设计规范
总体原则
- 商城前台页面统一参考
DESIGN.md,但在本项目中采用“Apple 风格的浅色化、H5 化落地版本”,不是直接照搬官网的整页纯黑方案。 - 默认设计取向为:
设计优先 > 美观优先 > 信息清晰 > 功能完整。 - 但任何视觉方案都不得破坏核心操作链路;当设计表现与下单、筛选、搜索、支付、跳转等关键操作冲突时,必须保证操作可达、状态清晰、信息可读。
- 页面重构不是简单“堆效果”,必须先整理版式层级,再做视觉细化。
页面气质
- 全站优先使用浅色背景体系:页面背景以
#f5f5f7、白色、浅灰为主,文字主色使用#1d1d1f。 - 交互强调色统一使用蓝色系,优先
#0071e3,链接或弱一级交互可使用#0066cc。 - 本项目中的 Apple 风格按浅色版本落地:强调留白、层级、字体、蓝色交互和轻模糊,不落地官网式大面积黑底。
- 禁止在商城前台页面使用大面积纯黑背景;首页、分类、搜索、购物车、我的、订单、优惠券等 H5 页面中的主按钮、主区域背景也不得使用纯黑或近黑底色。
- 不允许出现与商城功能无关的品牌文案、口号、长描述、装饰性说明文字。
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.
- 6d ago First seen · 153 lines · 2,795 tokens per session scan A d0bd5708d711
waynboot-mobile AGENTS.md is an instructions file published in the GitHub repository wayn111/waynboot-mobile (231 stars, last pushed 1mo ago), licensed MIT. It adds 2,795 tokens to every session, about $0.0140 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 instructions, from other repositories
tiptap tiptap.instructions.md
Instructions for ueberdosis/tiptap, covering tiptap, what is tiptap, repository layout, npm scripts and linting & formatting.
tiny-vue AGENTS.md
AGENTS.md instructions for opentiny/tiny-vue, covering agents.md, 项目概述, 关键目录结构, 环境要求 and 核心命令.
formkit CLAUDE.md
Instructions for formkit/formkit, covering formkit, architecture, packages, core (framework-agnostic) and vue integration.
frappe-ui copilot-instructions.md
Copilot instructions for frappe/frappe-ui, covering frappe-ui copilot instructions, read order, working rules, component api rules and area-specific pointers.
ui CLAUDE.md
Claude Code instructions for nuxt/ui, a project described as: The Intuitive Vue UI Library powered by Reka UI & Tailwind CSS.
inkline AGENTS.md
AGENTS.md instructions for inkline/inkline, covering inkline, quick start, repository map, where to look next and cross-cutting conventions.