eatmoreduck/boss-zhipin-scraper is a Python tool that collects job listings from BOSS Zhipin by connecting to an already logged-in Chrome browser through Chrome DevTools Protocol. It is for searching jobs and exporting salary and job data as JSON or CSV, with summaries of salary distributions and skills. Its catalogue add-on is provided as a Hermes Agent Skill for using the scraper in conversations.
Borrowing it
Nothing to install: this file belongs to eatmoreduck/boss-zhipin-scraper. 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/eatmoreduck/boss-zhipin-scraper/master/AGENTS.mdgit clone --depth 1 https://github.com/eatmoreduck/boss-zhipin-scraperWrote 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/eatmoreduck/boss-zhipin-scraper/agents-md)<a href="https://agentmods.dev/instructions/eatmoreduck/boss-zhipin-scraper/agents-md"><img src="https://agentmods.dev/badge/instructions/eatmoreduck/boss-zhipin-scraper/agents-md/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/instructions/eatmoreduck/boss-zhipin-scraper/agents-md"><img src="https://agentmods.dev/badge/instructions/eatmoreduck/boss-zhipin-scraper/agents-md.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 | $0.01987 | $0.01987 |
| Opus 5 | $0.00993 | $0.00993 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
boss-zhipin-scraper 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 11d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
指引给未来的 ZCode agent。先读这份，再动代码。
这是什么
boss-zhipin-scraper —— 通过 Chrome CDP（远程调试端口）连接用户本人已登录的 Chrome，抓取 BOSS直聘的公开职位数据（列表 + 详情），并可生成求职分析摘要。仅用于个人求职分析，非大规模爬虫（见 CONTRIBUTING.md 的合规一节）。
目录结构
scripts/boss_cdp_raw.py # 核心：抓取 + CLI 主入口（长单文件，行数以实际为准）
scripts/job_summary.py # 抓取结果 → Markdown 求职分析摘要
data/city_codes.json # 全量城市码表（300+ 城市，外置；见下）
tests/test_chrome_setup.py # unittest，全 mock，不依赖真实 Chrome/网络
tests/test_job_summary.py # 摘要测试
pyproject.toml # hatchling 打包；入口 boss-scraper / boss-summary
requirements.txt # 仅 requests + websocket-client
SKILL.md / README(.en).md / CHANGELOG.md / CONTRIBUTING.md
重要边界：核心逻辑都放 scripts/boss_cdp_raw.py，不要随手新建文件（见 CONTRIBUTING.md「单文件原则」）。docs/ 被 .gitignore 忽略，是本地产物，不要提交。例外：data/city_codes.json 是城市码表数据（非逻辑代码），外置便于用户查看支持哪些城市；改它要同步跑 tests.test_chrome_setup 的城市码表防回归测试。
环境与命令
- Python >=3.10，依赖只有
requests+websocket-client。用项目里的.venv（source .venv/bin/activate），别用 pyenv 全局解释器（会缺依赖报错）。 - 包管理用
uv（仓库有uv.lock），也可pip install -r requirements.txt。 - 跑测试：
python3 -m unittest tests.test_chrome_setup（无需 Chrome / 联网，全 mock）。改了job_summary再加跑tests.test_job_summary。 - 语法自检：
python3 -m py_compile scripts/boss_cdp_raw.py。 - 实跑抓取需要先启动带调试端口的 Chrome：
python3 scripts/boss_cdp_raw.py --setup-chrome（开127.0.0.1:9222，默认端口见DEFAULT_CDP_PORT），登录后在另一个终端跑抓取命令。Chrome 关了端口就没了。
改代码时的硬规则
- 版本号四处一致：
scripts/boss_cdp_raw.py的__version__（第 22 行附近）、pyproject.toml、SKILL.md、README.md必须同步，否则VersionConsistencyTests会挂。改版本号时四处一起改。 - 异常处理：禁止 bare
except:，必须捕获具体类型（requests.ConnectionError、json.JSONDecodeError等），和现有代码保持一致。 - 改了用户可见行为 → 更新
README.md；有意义变更 →CHANGELOG.md顶部加一条。 - README 双语同步：
README.md（中文）和README.en.md（英文）必须保持一致，改了其中一个就要同步另一个。 - commit message 用 Conventional Commits（
feat:/fix:/docs:/optimize:/refactor:等，见CONTRIBUTING.md）。 - 动抓取链路必须真机验证：凡改列表抓取、登录探测、详情链路的 PR，合并前要在真机过一遍
--check→--smoke→--pages 2 --no-detail（Chrome 需已启动且已登录）。全 mock 单测覆盖不到浏览器的焦点、定时器节流、SPA 行为和风控——焦点仿真 bug 曾 96 个单测全绿而真机翻页静默失败。一次性验证脚本（spike）放/tmp，不进仓库。 - 合规红线：只做被动捕获（Network 域旁听页面自身请求）和请求节奏控制。禁止主动伪装类手段：指纹伪造、验证码绕过、代理池轮换。遇到
_security_check验证页时提示用户人工处理，不自动绕过。
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.
- 11d ago First seen · 60 lines · 1,987 tokens per session scan A 586053b7f28a
boss-zhipin-scraper AGENTS.md is an instructions file published in the GitHub repository eatmoreduck/boss-zhipin-scraper (1,346 stars, last pushed today), licensed MIT. It adds 1,987 tokens to every session, about $0.0099 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
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.
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.
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).