Borrowing it
Nothing to install: this file belongs to shuheng-mo/career-ops-china. 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/shuheng-mo/career-ops-china/main/CLAUDE.mdgit clone --depth 1 https://github.com/shuheng-mo/career-ops-chinaWrote 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/shuheng-mo/career-ops-china/claude-md)<a href="https://agentmods.dev/instructions/shuheng-mo/career-ops-china/claude-md"><img src="https://agentmods.dev/badge/instructions/shuheng-mo/career-ops-china/claude-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/shuheng-mo/career-ops-china/claude-md"><img src="https://agentmods.dev/badge/instructions/shuheng-mo/career-ops-china/claude-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 | $0.07270 | $0.07270 |
| Opus 5.5 | $0.02908 | $0.02908 |
| Sonnet 5.5 | $0.01454 | $0.01454 |
| Haiku 4.5 | $0.00727 | $0.00727 |
Grade A, and why
career-ops-china 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 9d 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Career-Ops -- AI Job Search Pipeline（中国大陆版）
Origin
This system was built and used by santifer to evaluate 740+ job offers, generate 100+ tailored CVs, and land a Head of Applied AI role.
This fork has been deeply customized for the China mainland job market — Chinese language by default, archetypes adapted for 数据工程 / 数据治理 / 数据仓库 / 大模型 / AI Infra / 后端 / 平台 roles, salary research sources switched to 看准网/脉脉/OfferShow/知乎/一亩三分地, portals.yml populated with Chinese tech giants and AI unicorns, and login-wall handling for Boss直聘/拉勾/猎聘.
The portfolio that goes with the original system is also open source: cv-santiago.
It will work out of the box, but it's designed to be made yours. If the archetypes don't match your career, the scoring doesn't fit your priorities -- just ask. You (Claude) can edit any file in this system. 用户说「改 archetype 到 后端 + 推荐算法」你就直接改。这就是这个系统的目的。
What is career-ops
AI-powered job search automation built on Claude Code: pipeline tracking, offer evaluation, CV generation, portal scanning, batch processing.
Main Files
| File | Function |
|---|---|
data/applications.md |
Application tracker |
data/pipeline.md |
Inbox of pending URLs |
data/scan-history.tsv |
Scanner dedup history |
portals.yml |
Query and company config |
tools/cv-md-to-pdf.mjs |
Tailored CV markdown → PDF (npm run cv -- file.md); the .md in output/ is the editable source |
tools/waiqi-scan.mjs |
神仙外企岗位抓取 → inbox（神仙外企只当线索源：JSON 的 url 是校验过的官网投递链接，官网已下线的不落盘）（npm run waiqi，可选 --max-pages N（列表请求上限）/ --since YYYY-MM-DD / --categories 名,名 / --dry-run） |
tools/apply-link.mjs |
校验官网投递链接是否还在招（npm run apply-link -- <url|inbox JSON>）：Workday / SmartRecruiters 走公开接口确认，其他站点能判下线就判，判不了标 unverified |
templates/cv-template.html + tools/generate-pdf.mjs |
Legacy HTML → PDF path, kept for old files only |
article-digest.md |
Compact proof points from portfolio (optional) |
interview-prep/story-bank.md |
Accumulated STAR+R stories across evaluations |
tools/meituan-careers.mjs |
美团官网社招岗位（npm run meituan -- agent --city 上海,深圳 --days 21 [--fetch]）：走官网公开接口，每行带更新日期和详情页链接，--fetch 存进 inbox/。和 tools/tencent-careers.mjs（npm run tencent）同一套用法，云端雷达也用这两个脚本拿在招岗 |
tools/radar-seen.mjs |
雷达去重清单（node tools/radar-seen.mjs --direction ai|auto）：从 tracker 生成「已处理过的公司 + 岗位」，贴进对应雷达 routine 的 prompt。每批 inbox / batch 之后刷新，见 modes/radar.md |
cv-evolve/ + tools/cv-version.mjs |
CV 进化：事实账本 ledger.yml（每个数字的出处/证据等级）、cv.md 版本快照与 CHANGELOG（npm run cv:version -- status|commit|log|diff|affected）。gitignored。流程见 modes/evolve.md |
reports/ |
Evaluation reports (format: {###}-{company-slug}-{YYYY-MM-DD}.md) |
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.
- 9d ago Changed · +1 lines · +104 tokens per session 1d676fbb9449
- 10d ago Changed · +4 lines · +290 tokens per session 80067ff2f909
- 15d ago Changed · +2 lines · +225 tokens per session 82580f160648
- 21d ago Changed · +14 lines · +461 tokens per session 993ef8cd3bb1
- 26d ago Changed · +7 lines · +435 tokens per session 36ed521106fa
- 27d ago Changed · +41 lines · +1,262 tokens per session 28299e933118
- 2mo ago First seen · 286 lines · 4,493 tokens per session scan A 464b99158b93
career-ops-china CLAUDE.md is an instructions file published in the GitHub repository shuheng-mo/career-ops-china (114 stars, last pushed yesterday), licensed MIT. It adds 7,270 tokens to every session, about $0.0291 per session on Opus 5.5. 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.
career-ops-china CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| career-ops-china CLAUDE.mdshuheng-mo/career-ops-china | Instructions file | 114 | yesterday | MIT | A | 7,270 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |