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/umlink/easy-resume/claude-mdgit clone --depth 1 https://github.com/umlink/easy-resumeWrote 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/umlink/easy-resume/claude-md)<a href="https://agentmods.dev/instructions/umlink/easy-resume/claude-md"><img src="https://agentmods.dev/badge/instructions/umlink/easy-resume/claude-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 | $0.02919 | $0.02919 |
| Opus 5 | $0.01460 | $0.01460 |
| Sonnet 5 | $0.00584 | $0.00584 |
| Haiku 4.5 | $0.00292 | $0.00292 |
Grade A, and why
easy-resume CLAUDE.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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
本文件为 easy-resume 仓库根目录的 AI 协作指引。仓库下有 5 个独立子项目，每个子项目各自带有更详细的 CLAUDE.md，进入对应目录工作前请先读那份。
项目概述
"Easy简历" / "轻简历" 是一个面向中文用户的简历制作 SaaS。线上域名 wktline.com，主要功能：PC 端所见即所得简历编辑器、AI 简历诊断（SSE 流式）、VIP 会员体系、微信小程序登录、微信支付、PDF 导出（Puppeteer 服务端渲染）、邀请奖励、模板画廊。
仓库为多项目目录（非 yarn workspace，非 monorepo）：每个子项目独立
package.json/yarn.lock，互不依赖、独立部署。共享的是同一份 git 历史与线上域名/账号体系。
子项目布局
| 目录 | 角色 | 技术栈 | 端口 / 入口 | 详细文档 |
|---|---|---|---|---|
resume-server/ |
后端 API 服务 | NestJS + Fastify + Prisma + MySQL | :8088，前缀 /resume-api，Swagger /swagger-api |
resume-server/CLAUDE.md |
resume-pc/ |
PC 端主站（核心编辑器） | Umi Max 4 + React 18 + Ant Design 5 + Tailwind 3 + Quill 2 | :8000，路由 /editor/:rId |
resume-pc/CLAUDE.md |
resume-h5/ |
移动端 H5 编辑器 | UmiJS Max + antd-mobile 5 + Tailwind 3 | :8000，base /h5/，仅 /editor 路由 |
resume-h5/CLAUDE.md |
resume-mp/ |
微信小程序 | Taro 4 + React 18 + Vite | 编译产物 dist/，由微信开发者工具加载 |
resume-mp/CLAUDE.md |
resume-puppeteer/ |
PDF 渲染微服务 | Koa + Puppeteer + 七牛 OSS | :8090，三条 GET 路由 |
resume-puppeteer/CLAUDE.md |
包管理器统一为 yarn（每个子项目各自 yarn install）。Node ≥ 18。无根目录 package.json，无 workspace 配置——执行命令前先 cd 进对应子目录。
跨项目契约（所有前端 + 后端共享）
理解这些契约能避免 90% 的"看起来对、跑起来错"的问题：
1. 统一响应结构
所有后端接口（含错误）HTTP 状态码都是 200，真实状态在 body 里：
{ code: number, message: string, data: T | null, success: boolean }
- 判断成功用
success（或code === 200），不要用code === 0。 - 后端
HttpExceptionFilter把异常包成{ code, message, success: false, data: null, timestamp }但 HTTP 仍返回 200。前端拦截器按success分流，错误统一走message.error（PC/H5）或 toast（MP）。 - 跳过全局错误提示：PC/H5 给请求传
{ ignoreInterceptErr: true }；MP 在request.ts调用处自行处理。
2. 鉴权
- Header key：字面量
'authorization'（PC/H5/MP 全一致）。 - 值：JWT 字符串，无
Bearer前缀。 - 存储：
- PC / H5：
localStorage['authorization']（PCsrc/constants/enums.ts的LOCALHOST_ENUMS.TOKEN） - MP：
Taro.setStorageSync('TOKEN', ...)（key 字面量'TOKEN'）
- PC / H5：
- 后端
JwtAuthGuard默认所有路由需登录，@NotLogin()显式放开。JWT payload 含isVip，由VipGuard用于会员校验，前端无需额外请求就能拿到 VIP 状态。
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 · 124 lines · 2,919 tokens per session scan A 6d5bf7a1a9f5
easy-resume CLAUDE.md is an instructions file published in the GitHub repository umlink/easy-resume (22 stars, last pushed 27d ago), licensed MIT. It adds 2,919 tokens to every session, about $0.0146 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).