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 skills add chenzhiyong1994/career-os --skill job-searchgit clone --depth 1 https://github.com/chenzhiyong1994/career-osWrote 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/skills/chenzhiyong1994/career-os/job-search)<a href="https://agentmods.dev/skills/chenzhiyong1994/career-os/job-search"><img src="https://agentmods.dev/badge/skills/chenzhiyong1994/career-os/job-search/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/skills/chenzhiyong1994/career-os/job-search"><img src="https://agentmods.dev/badge/skills/chenzhiyong1994/career-os/job-search.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 | $0.00052 | $0.00842 |
| Opus 5 | $0.00026 | $0.00421 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
job-search 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 2d 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.
What it actually says
目标岗位搜索
输入与检索边界
从用户已有简历中提取角色、资历、领域、能力和明确限制，再结合本次求职条件形成 search brief。区分必须满足的条件与偏好；不能从曾经的工作地点或薪资推断用户当前要求。
缺少简历时，可以查询用户指定岗位或公司，但不声称完成个人匹配。只有缺失信息会实质改变检索方向且无法从上下文推断时再澄清，继续不依赖答案的查询。
岗位信息有时效性，搜索与状态查询必须使用当前可用的联网搜索、连接器或浏览器。工具不可用时交付检索式与未完成项，不用记忆生成“正在招聘”的结果。
搜索与核验
- 根据目标角色、同义职位名称、地点和核心能力构造查询。只传必要的泛化信息，不发送整份简历、姓名、联系方式或内部业务细节。
- 优先核验公司官方招聘页或招聘系统，再参考招聘平台。用户指定渠道时按该渠道检索；平台无法访问时可用其他公开来源佐证，但不能冒称已核验原平台。
- 打开具体岗位页核对正文，记录岗位链接、来源、查询时间，以及页面明确给出的发布日期或截止日。搜索摘要只能作为线索；未披露时间或薪资时保持未知，不把抓取时间当发布日期。
- 区分
open（页面明确显示在招）、closed（已截止或关闭）、unknown（未能确认）。记录支持该状态的页面证据。404、登录墙和职位页仍存在都不能单独证明在招或关闭。 - 按招聘编号、规范化链接及公司/岗位/地点/团队信息去重，保留多个来源。不同地点、团队或招聘编号不直接合并；拿不准时标记疑似重复。
- 对照硬约束与已有简历进行初筛。明确冲突的岗位单列，不混入推荐名单；关键信息缺失的岗位标为待核实，不能默认为满足条件。
- 按可解释的匹配理由排序，保留证据缺口。对需要深入比较的岗位使用 jd-analysis。只有用户要求定制时才进入 resume-tailor。
输出与结束条件
输出 search brief 和 job shortlist，清单至少包含：
- 公司、岗位、地点/工作方式、来源链接和招聘编号（如有）。
- 已披露的薪资/级别、发布日期/截止日、查询时间。
- 招聘状态及其证据、匹配理由、主要缺口和待核实条件。
- 优先级理由；不生成缺乏依据的精确匹配分或录用概率。
将已核验岗位、待核验线索与已关闭/不符合硬约束的结果分开。说明查过的来源和检索条件；数量不足时如实交付，不为凑数放宽硬约束。可以提出扩展检索方向，但扩大硬约束需用户明确调整。
达到用户要求的范围，或主要检索方向不再出现新的相关结果时交付。刷新已有清单时说明新增、关闭和信息变化，不把无法访问当成岗位关闭。该流程不后台持续监控、不登录申请、不上传简历、不代发消息或自动投递。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 38 lines · 52 tokens per session scan A e61fc15d5f06
job-search is a skill published in the GitHub repository chenzhiyong1994/career-os (3 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 842 once invoked, about $0.0003 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 2026-09-10.
Other skills, from other repositories
trackly-apply
Use trackly Apply to fill a user-approved job application in a controlled browser, resolve missing answers with the user, and stop at final review. Use when the user asks to fill, continue, or review an approved application.
html-ppt-zhangzara-capsule
A year-end self-review for a product manager — the role, the outcomes, the learning, and the ask, all evidence-backed. Built as a decision-grade career deck for manager, review committee.
html-ppt-zhangzara-neo-grid-bold
A designer's portfolio narrative for a senior interview — three case studies, the craft, and the judgment behind each. Built as a decision-grade career deck for hiring panel.
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
huashu-slides
A career-pivot story from consultant to product leader — the arc, the proof, and why the next role is the right bet. Built as a decision-grade career deck for hiring manager, mentors.
html-ppt-xhs-white-editorial
A staff-engineer promotion packet — scope, the proof moments, the artifacts, and the impact that clears the bar. Built as a decision-grade career deck for manager, calibration committee.