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/yunsii/pinyin/agents-mdgit clone --depth 1 https://github.com/yunsii/pinyinWrote 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/yunsii/pinyin/agents-md)<a href="https://agentmods.dev/instructions/yunsii/pinyin/agents-md"><img src="https://agentmods.dev/badge/instructions/yunsii/pinyin/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 | $0.01085 | $0.01085 |
| Opus 5 | $0.00543 | $0.00543 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
pinyin 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
在线拼音打字练习（Vite + React 19 + Tailwind v4 + shadcn/ui / Base UI）。命令与依赖见 package.json，功能清单见 README.md，此处不重复。用户级规则不写进本文件。
Hard Rules
方案与文本靠 side-effect 注册，漏 import 等于没加
拼音方案、练习文本通过模块顶层的 Registry.schema.register / Registry.text.register / Registry.text.load 注册，再由 src/assets/schemes/index.ts、src/assets/texts/index.ts 侧效 import，最终经 src/global.ts 拉起（src/main.tsx 会先 import @/global）。
新增时两步都要做：
- 新建
src/assets/schemes/<Name>.ts或src/assets/texts/<Name>.ts，在文件内完成 register/load。 - 在对应
index.ts里import './<Name>'。
只建文件不挂 index，运行时列表里不会出现。参照 XianHe.ts、HelloWorld.ts、ChuShiBian.ts。
vite.config.ts 的 base: '/pinyin/' 不要随手改
站点部署在 GitHub Pages 子路径 /pinyin/（见 .github/workflows/gh-pages.yml）。改 base 或发布目录时，部署路径与静态资源前缀必须一起对齐，否则本地 pnpm build 看着正常、线上资源 404。
拼音术语变量名用全拼
src/core/Pinyin.ts 约定：拼音 → Pinyin/pinyin，全拼 → Quanpin/quanpin，双拼 → Shuangpin/shuangpin，声母 → Shengmu/shengmu。新编码与映射字段跟这套走，不要混用拼音缩写或英文意译（如 initial/final）。
TextRegister.load 的注音要人工核对
load({ content, pinyin }) 按「字 ↔ 拼音 token」一一对齐；工具站注音有已知错例（见 src/core/registers/TextRegister/index.ts 注释：「内」→na，「其」→ji）。用 load 新增长文后，抽查易错字，不要默认相信导出结果。短文优先手写 Registry.text.register（见 HelloWorld.ts）。
UI 用 shadcn（Base UI），不要重新引入 antd
交互组件放在 src/components/ui/，由 CLI 生成：
pnpm dlx shadcn@latest add <component>
components.json 的 style 为 base-nova（Base UI）。Toast 用 sonner，图标用 lucide-react。应用视觉组件（四线格等）可继续用 CSS Module，不要把 Less / antd 主题体系加回来。
包管理器用 pnpm
仓库锁文件是 pnpm-lock.yaml。本地与 CI 都用 pnpm，不要另起 package-lock.json。Registry 见 .npmrc（当前 npmmirror）。
Task Routing
只读匹配当前任务的那一处，不要预加载。
| 任务 | 读 |
|---|---|
| 新增 / 修改拼音方案 | 上面「side-effect 注册」+ src/assets/schemes/ + src/core/registers/PinyinSchemaRegister/ |
| 新增 / 修改练习文本 | 上面「side-effect 注册」与「注音核对」+ src/assets/texts/ |
| 编码枚举、声母、零声母、全拼↔双拼转换 | src/core/Pinyin.ts、src/core/registers/PinyinSchemaRegister/ |
| 练习页 UI、输入进度、同步/设置 | src/pages/Hero/ |
| 汉字格 / 四线格 | src/components/Hanzi/、src/components/FourLinesGrid/ |
| shadcn UI 原语 | src/components/ui/ + components.json |
| 入口 | src/main.tsx（单页，无路由库） |
| 本地验证 | pnpm typecheck / pnpm lint；改 UI 时 pnpm dev（port 8000）浏览器走流程；发版前 pnpm build |
| 部署 / Pages | .github/workflows/gh-pages.yml + 上面 base 规则 |
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.
- 5d ago First seen · 61 lines · 1,085 tokens per session scan A 2230ac9b4570
pinyin AGENTS.md is an instructions file published in the GitHub repository yunsii/pinyin (42 stars, last pushed 5d ago), licensed MIT. It adds 1,085 tokens to every session, about $0.0054 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
south-admin-react CLAUDE.md
Claude Code instructions for southliu/south-admin-react, covering claude.md, commands, development, code quality and package management.
south-admin-react AGENTS.md
AGENTS.md instructions for southliu/south-admin-react, covering agents.md, 常用命令, 新建页面（重要约定）, 目录结构 and 路由（自动生成）.
ant-design-pro CLAUDE.md
Claude Code instructions for ant-design/ant-design-pro, covering claude.md, project, commands, critical rules and architecture essentials.
v3-admin-vite AGENTS.md
Instructions for un-pany/v3-admin-vite, covering 原则, 1. 编码前思考, 2. 简洁优先, 3. 精准修改 and 4. 目标驱动执行.
skyroc AGENTS.md
AGENTS.md instructions for Ohh-889/skyroc, covering agents.md, 规范索引, skills 调用规则（关键）, 思考顺序 and react 组件规范.
weapp-vite CLAUDE.md
Claude Code instructions for weapp-vite/weapp-vite, covering claude.md, project overview, vue support, common commands and development.