Borrowing it
Nothing to install: this file belongs to zxtshine/boos-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zxtshine/boos-ai/main/CLAUDE.mdgit clone --depth 1 https://github.com/zxtshine/boos-aiWrote 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/zxtshine/boos-ai/claude-md)<a href="https://agentmods.dev/instructions/zxtshine/boos-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/zxtshine/boos-ai/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 5.1 | $0.01829 | $0.01829 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
boos-ai 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 8d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — lakejobai-job-radar
AI 驱动的 BOSS 直聘智能求职助手 · Web 控制台 + CLI + Plan-then-Execute Agent + 面试练习
项目概述
BOSS 直聘（zhipin.com）自动化求职工具，核心能力：搜索 → 批量投递 → AI 自动回复 HR → AI 分析 JD/简历优化 → Plan-then-Execute Agent 自主执行求职任务。附带独立面试练习服务（Ollama 出题 + DeepSeek 批改）。
技术栈
| 层级 | 选型 |
|---|---|
| 后端 | Python ≥ 3.10 + FastAPI + Uvicorn |
| 浏览器自动化 | Playwright + Firefox 持久化 Profile + 注入 JS 反检测 |
| 数据库（主应用） | SQLite WAL，文件 .boss_profile/boss_state.db，启动自动建表 |
| 数据库（面试） | MySQL 8.0，配置在 interview/mysql_config.py |
| 前端 | 单文件 HTML + Vanilla JS + WebSocket（无构建步骤） |
| CLI | Click + httpx，stdout JSON 信封 |
| AI（主应用） | OpenAI 兼容 API（DeepSeek / OpenRouter / 自定义） |
| AI（面试） | Ollama 本地模型 + DeepSeek API |
项目结构
boss_app.py # FastAPI 后端 + WebSocket + 后台监控 + Agent + 面试端点
boss_firefox.py # BOSS 搜索/详情 XHR + 反检测 JS 注入 (BossScraper 基类)
boss_automation.py # 投递/聊天/发简历/风控退避/人类行为模拟/未读兜底
boss_replier.py # AI 回复生成 + 打招呼语 + 转人工引导
boss_state.py # SQLite 持久化层（8 张表 + 线程本地连接）
boss_company.py # 公司画像聚合 + 法人识别 + smart-send
boss_geo.py # 城市/区/规模编码映射（惰性获取 + 6h 缓存）
boss_rag.py # 历史 JD RAG 检索（embedding 余弦相似度 + few-shot）
agent/ # Plan-then-Execute Agent（tools/skills/loop）
lakejob_cli/ # CLI（20 条命令）
static/dashboard.html # Web 前端 SPA
interview/ # 面试子模块（独立 FastAPI，端口 8001，详见 interview/CLAUDE.md）
tests/ # 测试
架构与数据流
浏览器 (dashboard.html)
│ WebSocket + HTTP REST
▼
FastAPI (boss_app.py) ←──HTTP─── lakejob CLI
│
├── boss_automation.py ──Playwright/Firefox──► zhipin.com
│ │ ──page.evaluate()────► window.__bossApply (注入JS原生操作)
├── boss_replier.py ──HTTP────────────────► AI API
├── boss_state.py ──sqlite3─────────────► .boss_profile/boss_state.db
├── boss_rag.py ──embedding────────────► AI API + SQLite
└── agent/loop.py ──规划→执行→重规划────► LLM + 工具
面试服务（独立进程，端口 8001）
interview/main.py ──Ollama + DeepSeek──► 出题/批改/语义检索
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.
- 8d ago First seen · 137 lines · 1,829 tokens per session scan A 0bd8fd367a4f
boos-ai CLAUDE.md is an instructions file published in the GitHub repository zxtshine/boos-ai (12 stars, last pushed 20d ago), licensed MIT. It adds 1,829 tokens to every session, about $0.0091 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).
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).
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.