Borrowing it
Nothing to install: this file belongs to dizhouid-lgtm/liepin-ai-loop-recruiting. 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/dizhouid-lgtm/liepin-ai-loop-recruiting/main/CLAUDE.mdgit clone --depth 1 https://github.com/dizhouid-lgtm/liepin-ai-loop-recruitingWrote 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/dizhouid-lgtm/liepin-ai-loop-recruiting/claude-md)<a href="https://agentmods.dev/instructions/dizhouid-lgtm/liepin-ai-loop-recruiting/claude-md"><img src="https://agentmods.dev/badge/instructions/dizhouid-lgtm/liepin-ai-loop-recruiting/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/dizhouid-lgtm/liepin-ai-loop-recruiting/claude-md"><img src="https://agentmods.dev/badge/instructions/dizhouid-lgtm/liepin-ai-loop-recruiting/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 | $0.01706 | $0.01706 |
| Opus 5 | $0.00853 | $0.00853 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
liepin-ai-loop-recruiting 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 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
招聘工作区 — Pixboom
持续运行的招聘工作区，面向 Pixboom 所有岗位（前端、机械、HR、供应链、财务……）。 职责仅限：用猎聘搜人、筛人，凑齐合适候选人交付。打招呼 / 沟通 / 面试归 HR，不在此流程。
⚠️ 改本文件前先想：这里只放所有岗位通用的背景/结构/流程指向。某候选人、某一轮、某岗的偏好或经验 → 写进该岗
JD.md，别堆进这里（否则项目越用越乱）。本文件是项目治理文件，改动请保守。怎么搜、怎么筛、所有流程与注意事项都在项目级 Skill
pxb-liepin——搜人/筛简历前必须先调用它。本文件只讲背景和文件结构，不写作业细节。 东西放哪：岗位专属偏好 → 该岗JD.md；通用背景/结构 → 本文件；作业程序 →pxb-liepin。首次使用本工作区：先看仓库根
README.md（装环境、登录猎聘、按你的 AI 工具接入 skill）。
用前先更新（本工作区在持续迭代，版本常变）
每次开始招聘任务前，先确保是最新版——这是会话第一件事，在抢锁/搜人之前：
git fetch && git status -sb # 看是否落后 origin
- 落后且工作区干净 →
git pull拉最新再开工，并跟用户说一句"已更新到最新版"。 - 落后但有本地改动（有人改过被跟踪文件）→ 别擅自覆盖，先告诉用户，让其决定
git stash/丢弃后再 pull。 - 不是 git 仓库（用户是解压用的）→ 提示"建议改用
git clone以便后续一键更新"。 - 猎聘 CLI 版本：开工体检
doctor.mjs会顺带比对 npm 上的最新版，报"落后"→ 先问用户再更新（更新会覆盖补丁，处置动作见pxb-liepin步骤 0）。
放心拉：岗位数据（各岗
JD.md/候选人池.md/去重台账.csv）是未跟踪文件，git pull只动工具本体（skill/脚本/文档），不碰你的数据。
关于 Pixboom（写 JD / 介绍候选人的公共素材）
- 一句话：面向全球专业影视市场的高端摄影器材品牌，做出海 / 跨境独立站（pixboom.com）。
- 我们是谁：高端影视器材品牌，客户是全球专业影视市场；出海模式，核心阵地是独立站；国际化、品牌驱动、重品质感。
- 通用吸引点：高端出海/国际化舞台；把事当作品做不只是完成任务；鼓励用 AI 工具（Claude/ChatGPT）；能持续成长、不做纯重复。
- 跨境 / 出海背景对多数岗位加分，硬性要求看各 JD。
- 待补充（公共信息）：公司规模/办公地点、远程或混合办公、薪酬福利体系、组织架构概览。
换公司用本工作区:只需改本节 + 各岗
JD.md,流程/脚本岗位中立、公司无关。
文件结构（搜人判断只看 JD）
招聘/
├── README.md ← 装环境 + 接入(不同 AI 工具)。新人先看
├── CLAUDE.md ← 本文件：背景 + 结构(岗位中立)。Claude Code 自动读
├── AGENTS.md ← 同上内容的镜像,给 Codex/Cursor/Copilot 等非 Claude 工具
├── .claude/skills/ ← pxb-liepin(作业流程 + scripts/ 跨平台脚本)· liepin-cli(命令)
├── _共享/ ← 跨岗:搜索队列.md(排队防互顶)· 公司档案.md(目标公司研究底料,全岗共用)· 模板/
└── <岗位名>/
├── JD.md ← 对外JD + 内部备注(硬约束一行 + 开搜前三锚块 + 5列表:轮次/强搜索词/弱搜索词/正向建议/负向建议)。**唯一持续优化、判断只看它**
├── 候选人池.md ← 用户确认的最终候选人(一行一人 + 简历链接,事实源)
├── 去重台账.csv ← 每个召回过的人(两列 `resume_id,status`,状态五值),仅去重用
├── 参考简历/ ← 客户开搜前给的样板简历;intake 真读抽画像(没有就空着)
└── 待定/ ← 精筛产出的简历 PDF 中转,用户在此拍板(看完可删)
- JD 越搜越准：内部备注是一张表，一轮一行只追加——强/弱搜索词记本轮关键词效果，正向建议来自分析入选简历为何入选，负向建议来自用户毙掉的人。硬约束（预算/城市/经验/学历/年龄/目标人数）单列表上一行。
- 去重台账 只为查重：召回过的每个 id 自动登记为
未精筛，粗筛卡面一眼否的标粗筛不合适，精筛后升级为精筛不合适/待定，用户拍板后入选；状态 =未精筛 / 粗筛不合适 / 精筛不合适 / 待定 / 入选（五值）。未精筛= 卡面过得去/没细看的干净库存；待定= 细看够格、出了 PDF 等复核。台账增删改全走pxb-liepin的dedup.mjs，别手改（保 BOM/格式）。 - 搜人/筛人的所有机械活在
.claude/skills/pxb-liepin/scripts/里（Node 脚本，跨 Win/mac）；判断在 skill 正文 + agent。 - 开搜前三锚（治"没描述清就动手→多轮返工"）：搜任何岗前先做 ① 目标公司（读
_共享/公司档案.md×岗位性质，我研究+你确认）② 参考简历（客户样板放该岗参考简历/，我真读抽画像）③ 假阳性反向锚（"看着像 JD 实则不合适的行业/公司/岗位"）→ 全部回写 JD。作业细节在pxb-liepin步骤 P。 - 新增岗位：
node .claude/skills/pxb-liepin/scripts/init-role.mjs "<岗位名>"一键建档（复制_共享/模板/三件 + 建空待定/、参考简历/）。
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 · 53 lines · 1,706 tokens per session scan A 850adc1dbbac
liepin-ai-loop-recruiting CLAUDE.md is an instructions file published in the GitHub repository dizhouid-lgtm/liepin-ai-loop-recruiting (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,706 tokens to every session, about $0.0085 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 2026-08-31.
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).