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 agentmods add skills/ranxi2001/zero2agent/scrape-nowcodernpx skills add ranxi2001/zero2Agent --skill scrape-nowcodergit clone --depth 1 https://github.com/ranxi2001/zero2AgentWhat 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 | $0.00092 | $0.03503 |
| Opus 5 | $0.00046 | $0.01751 |
| Sonnet 5 | $0.00018 | $0.00701 |
| Haiku 4.5 | $0.00009 | $0.00350 |
Grade A, and why
scrape-nowcoder 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scrape-nowcoder:牛客面经 CDP 抓取
基于 Chrome DevTools Protocol 原生 WebSocket,零依赖。直接连接已运行的 Chrome 调试端口,复用浏览器登录态。
工作方式
- 连接 Chrome 调试端口(默认 9222)
- 如果端口不可达,自动启动独立 Chrome 实例(
~/.chrome-nowcoder) - 支持首页推荐流、标准话题 API、
creation/subject无限滚动话题和面经分类搜索结果 - 在已登录的浏览器中操作,抓取完成后 Chrome 保持运行
前置条件
- Node.js >= 22(需要原生 WebSocket 和 fetch)
- Google Chrome(Windows 或 macOS)以调试端口运行
- 已在该 Chrome 中登录牛客网
首次使用
启动带调试端口的 Chrome(会自动创建 ~/.chrome-nowcoder profile):
node .claude/skills/scrape-nowcoder/scrape.mjs --login
在弹出的 Chrome 中登录牛客,profile 会持久化 cookie。cookie 过期或页面跳转登录页时重新执行 --login。
用法
node .claude/skills/scrape-nowcoder/scrape.mjs [选项]
选项
| 参数 | 默认值 | 说明 |
|---|---|---|
--login |
— | 首次使用:启动 Chrome 并打开登录页 |
--home |
— | 抓取首页推荐流,通过连续下拉加载后续内容 |
--topic <url|id> |
818_1 |
抓取话题流;支持 creation/subject/<uuid> URL、其他完整牛客 URL 或 type 值 |
--pages <n> |
1 | 最大页数;首页模式下为连续滚动批次 |
--limit <n> |
0 | 列表去重和关键词筛选后最多抓取前 n 篇详情;0 表示不限 |
--since <date> |
(空) | 标准话题接口或搜索模式仅保留该日及之后内容;话题接口连续两页全部更早时停止 |
--until <date> |
(空) | 标准话题接口或搜索模式仅保留该日及之前内容;与 --since 组合限定月份/区间 |
--keyword <kw> |
(空) | 按关键词筛选标题和列表摘要(如“AI”、“大模型”) |
--search <query> |
(空) | 面经分类搜索模式;固定使用 type=all&searchType=顶部导航栏&subType=818 并翻页 |
--out <dir> |
.claude/skills/scrape-nowcoder/nowcoder-output |
输出目录 |
--port <port> |
9222 | Chrome 调试端口 |
--delay <ms> |
2000 | 请求间隔,避免触发反爬 |
常用示例
# 默认抓牛客面经话题 type=818_1 的第 1 页
node .claude/skills/scrape-nowcoder/scrape.mjs
# 从面经话题抓 10 页,连续两页全部早于指定日期时自动停止
node .claude/skills/scrape-nowcoder/scrape.mjs --topic "https://www.nowcoder.com/?type=818_1" --pages 10 --since "2026-08-12"
# 抓 creation/subject 无限滚动话题:初始可见页 + 9 次加载
node .claude/skills/scrape-nowcoder/scrape.mjs --topic "https://www.nowcoder.com/creation/subject/14710425d5b74593b2ef7103d293606f" --pages 10
# 只取 subject 首屏前 3 篇做流水线冒烟测试
node .claude/skills/scrape-nowcoder/scrape.mjs --topic "https://www.nowcoder.com/creation/subject/14710425d5b74593b2ef7103d293606f" --pages 1 --limit 3
# 首页推荐流连续滚动 3 个批次,只保留 AI 相关内容
node .claude/skills/scrape-nowcoder/scrape.mjs --home --pages 3 --keyword "AI"
# 面经分类搜索:搜"字节跳动 后端 面经",抓 5 页
node .claude/skills/scrape-nowcoder/scrape.mjs --search "字节跳动 后端 面经" --pages 5
# 搜索"面"并逐篇按详情发布日期筛选已召回的 2026 年 7 月候选
node .claude/skills/scrape-nowcoder/scrape.mjs --search "面" --pages 50 --since "2026-07-01" --until "2026-07-31" --out ".claude/skills/scrape-nowcoder/nowcoder-output-2026-07-search"
# 面经分类搜索:搜 Redis 八股
node .claude/skills/scrape-nowcoder/scrape.mjs --search "Redis 面经 八股" --pages 3
# 指定端口
node .claude/skills/scrape-nowcoder/scrape.mjs --port 9333
What ships with it
60 files 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.
- nowcoder-agent-excellent-full/2026-02-10-成都agent实习面经.md 6.4 KB
- nowcoder-agent-excellent-full/2026-02-12-阿里淘天AI-agent开发一面.md 6.9 KB
- nowcoder-agent-excellent-full/2026-02-27-字节AI开发一面面经-实习.md 4.9 KB
- nowcoder-agent-excellent-full/2026-02-27-某中厂Agent开发面经-日常实习.md 5.7 KB
- nowcoder-agent-excellent-full/2026-03-04-字节Agent研发面经-整体不太难.md 5.2 KB
- nowcoder-agent-excellent-full/2026-03-05-商汤科技Ai-agent开发面经(攒人品.md 5.7 KB
- nowcoder-agent-excellent-full/2026-03-06-北京四维图新面经.md 4.7 KB
- nowcoder-agent-excellent-full/2026-03-09-滴滴AI-agent开发日常实习面经.md 6.8 KB
- nowcoder-agent-excellent-full/2026-03-11-百度大模型实习-agent面经.md 5.1 KB
- nowcoder-agent-excellent-full/2026-03-16-AI-agent研发实习面经分享.md 6.0 KB
- nowcoder-agent-excellent-full/2026-03-17-顺丰大模型实习面经-攒人品.md 5.2 KB
- nowcoder-agent-excellent-full/2026-03-21-写面经攒人气,拼多多面经.md 529 B
- nowcoder-agent-excellent-full/2026-03-21-得物大模型算法实习面经分享.md 5.3 KB
- nowcoder-agent-excellent-full/2026-03-22-AI-Agent二面-字节实习面经.md 5.9 KB
- nowcoder-agent-excellent-full/2026-03-22-AI-Agent开发二面-阿里.md 673 B
- nowcoder-agent-excellent-full/2026-03-27-ailab-agent方向一面面经.md 5.9 KB
- nowcoder-agent-excellent-full/2026-03-27-双非腾讯后台一面面经.md 5.6 KB
- nowcoder-agent-excellent-full/2026-03-31-AI-Agent算法一面面经(小红书.md 5.3 KB
- nowcoder-agent-excellent-full/2026-04-05-ai-agent实习面经分享-字节.md 4.9 KB
- nowcoder-agent-excellent-full/2026-04-07-阿里控股集团Agent-Infra暑期一面.md 5.4 KB
- nowcoder-agent-excellent-full/2026-04-09-Agent-小厂面经.md 7.3 KB
- nowcoder-agent-excellent-full/2026-04-09-某教育agent开发面经.md 5.5 KB
- nowcoder-agent-excellent-full/2026-04-10-蚂蚁金融Agent开发暑期面经分享.md 5.6 KB
- nowcoder-agent-excellent-full/2026-04-13-蚂蚁集团效能研发面经.md 6.0 KB
- nowcoder-agent-excellent-full/2026-04-14-网新软件面经-攒人品.md 6.0 KB
- nowcoder-agent-excellent-full/2026-04-16-蚂蚁AI-Agent暑期实习一面分享.md 5.4 KB
- nowcoder-agent-excellent-full/2026-04-17-字节暑期Agent开发一面-面经分享.md 5.3 KB
- nowcoder-agent-excellent-full/2026-04-18-阿里淘天AI-agent一面实习面经.md 5.5 KB
- nowcoder-agent-excellent-full/2026-04-20-字节一面-AI-Agent面经?.md 6.7 KB
- nowcoder-agent-excellent-full/2026-04-20-滴滴一面agent.md 325 B
- nowcoder-agent-excellent-full/2026-04-20-阿里淘天-暑期agent算法一面-55m.md 4.8 KB
- nowcoder-agent-excellent-full/2026-04-23-美团一面面经.md 6.4 KB
- nowcoder-agent-excellent-full/2026-04-24-TCL科技Java实习面经.md 6.0 KB
- nowcoder-agent-excellent-full/2026-04-28-小红书AI应用开发面经分享.md 5.7 KB
- nowcoder-agent-excellent-full/2026-05-03-阿里云暑期实习Agent面经分享.md 5.5 KB
- nowcoder-agent-excellent-full/2026-05-03-阿里国际暑期实习Agent一面分享-1h.md 5.5 KB
- nowcoder-agent-excellent-full/2026-05-05-小红书AI应用开发面经分享.md 5.2 KB
- nowcoder-agent-excellent-full/2026-05-07-Agent开发实习一面分享-字节.md 5.2 KB
- nowcoder-agent-excellent-full/2026-05-07-AI-Agent开发面经分享-京东-攒人.md 6.0 KB
- nowcoder-agent-excellent-full/2026-05-14-线下某小厂面经.md 6.0 KB
- nowcoder-agent-excellent-full/2026-05-28-快手Agent面经.md 6.1 KB
- nowcoder-agent-excellent-full/2026-06-04-灵犀互娱暑期实习面经.md 6.2 KB
- nowcoder-agent-excellent-full/2026-06-10-阿里Agent面经.md 5.4 KB
- nowcoder-agent-excellent-full/2026-07-03-字节-AI-Agent-评测二面面经.md 6.8 KB
- nowcoder-agent-excellent-full/2026-07-06-上海agent初创面经.md 8.2 KB
- nowcoder-agent-excellent-full/2026-07-06-快手agent面试凉经.md 8.7 KB
- nowcoder-agent-excellent-full/2026-07-07-天津小厂前端面经.md 6.3 KB
- nowcoder-agent-excellent-full/2026-07-07-理想-ai-解决方案面经.md 6.2 KB
- nowcoder-agent-excellent-full/2026-07-08-Agent面试.md 7.7 KB
- nowcoder-agent-excellent-full/2026-07-08-阳光电源agent岗面经一面.md 6.9 KB
- nowcoder-agent-excellent-full/2026-07-09-7.6-字节-AI-Agent开发一面.md 5.2 KB
- nowcoder-agent-excellent-full/2026-07-09-长沙小厂面经.md 6.1 KB
- nowcoder-agent-excellent-full/2026-07-10-广州小厂面经.md 6.2 KB
- nowcoder-agent-excellent-full/2026-07-13-7.13-字节-AI-Agent开发二面.md 5.6 KB
- nowcoder-agent-excellent-full/2026-07-13-字节即梦agent全栈开发实习求问.md 6.2 KB
- nowcoder-agent-excellent-full/2026-07-14-阿里Agent面经.md 8.0 KB
- nowcoder-agent-excellent-full/2026-07-17-Agent实习面经.md 5.7 KB
- nowcoder-agent-excellent-full/2026-07-17-Agent开发想找个实习.md 7.2 KB
- nowcoder-agent-excellent-full/2026-07-17-小厂面经.md 6.8 KB
- nowcoder-agent-excellent-full/2026-07-20-7.14-字节-AI-Agent开发-三面.md 7.2 KB
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 · 200 lines · 92 tokens per session scan A 1fb9caa3c164
scrape-nowcoder is a skill published in the GitHub repository ranxi2001/zero2Agent (367 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 3,503 once invoked, about $0.0005 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 skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.telegram-notifications-setup
Set up a Telegram notification channel (Sentinel) for a colony by driving the browser — create a bot via @BotFather in Telegram Web, store its token, detect the chat to notify, and turn Sentinel on so the colony can ping the user on Telegram and accept replies. Use when the user asks to "set up Telegram…