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/zaptainz/radioheader/web-extractnpx skills add ZaptainZ/radioheader --skill web-extractgit clone --depth 1 https://github.com/ZaptainZ/radioheaderWrote 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/zaptainz/radioheader/web-extract)<a href="https://agentmods.dev/skills/zaptainz/radioheader/web-extract"><img src="https://agentmods.dev/badge/skills/zaptainz/radioheader/web-extract.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01273 |
| Opus 5 | $0.00048 | $0.00636 |
| Sonnet 5 | $0.00019 | $0.00255 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
web-extract 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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
网页正文提取 — 三层降级 + Cookie 辅助
概述
从任意 URL 提取干净的 Markdown 正文，自动选择最优方案。统一 maxChars=30000。
输入
用户提供的 URL 在 $ARGUMENTS 中。如果没有提供 URL，询问用户。
执行策略
域名快捷路由（优先判断）
| 域名模式 | 直接走 | 原因 |
|---|---|---|
mp.weixin.qq.com |
Scrapling | Jina 403，不浪费配额 |
github.com |
web_fetch | 静态页，无需 Jina |
raw.githubusercontent.com |
web_fetch | 原始文件 |
docs.* / *.readthedocs.io |
web_fetch | 技术文档，静态 |
非快捷路由 → 三层降级
第一层：Jina Reader（优先）
使用 WebFetch 工具访问: https://r.jina.ai/{原始URL}
设置 maxChars=30000
Jina 自动渲染、抽取正文、去噪，返回干净 Markdown。速度约 1.4 秒。
- 每天免费 200 次
- 如果返回内容为空、403、或明显不完整 → 降级到第二层
第二层：Scrapling + html2text（降级）
~/.claude/skills/web-extract/.venv/bin/python3 ~/.claude/skills/web-extract/scrapling_fetch.py "<URL>" 30000
依赖已安装在 skill 自带的 venv 中，无需额外操作。
特点：
- 无限制，无需 API Key
- 配合 html2text 输出与 Jina 同等质量的 Markdown
- 如果脚本报错（依赖未装等）→ 降级到第三层
第三层：web_fetch 直接抓（兜底）
使用 WebFetch 工具直接访问原始 URL
设置 maxChars=30000
注意：
- 返回全页 HTML 转 Markdown，噪音多
- 有反爬的平台会直接失败
- 仅适合静态页面
验证拦截检测 + Cookie 辅助（第四层）
当以上三层返回的内容包含以下特征时，判定为被验证拦截：
- 内容含"环境异常"、"完成验证"、"appmsgcaptcha"等字样
- 返回内容为空或明显是验证页（而非正文）
- Scrapling 报超时且域名为
mp.weixin.qq.com等已知需验证站点
检测到拦截后，必须告知用户并请求确认：
该网站需要人机验证，常规提取方式无法获取正文。 我可以尝试使用你本地浏览器（Chrome/Safari）中已有的 cookie 来绕过验证。 这会读取你浏览器中该站点的 cookie（仅用于本次请求，不会存储或外传）。
是否允许使用浏览器 cookie 提取？
用户确认后，使用 --cookie 标志调用：
~/.claude/skills/web-extract/.venv/bin/python3 ~/.claude/skills/web-extract/scrapling_fetch.py "<URL>" 30000 --cookie
用户拒绝时，告知替代方案：
- 在浏览器中手动打开文章，复制正文粘贴到对话中
- 或将文章链接转发给自己后用其他阅读器打开
已知需要 cookie 的站点
| 域名 | 原因 |
|---|---|
mp.weixin.qq.com |
微信公众号文章，2026 年起要求 PoC 验证码 |
遇到新的需验证站点时，同样走「检测 → 提示 → 确认 → cookie」流程。
输出格式
提取成功后，向用户展示：
- 使用的方案：告知用了哪一层（Jina / Scrapling / web_fetch / Cookie）
- 正文内容：干净的 Markdown
- 字符数：实际提取的字符数
- 如果发生降级或使用了 cookie，简要说明原因
依赖
Scrapling、html2text、browser-cookie3 已安装在 skill 自带的 venv 中：~/.claude/skills/web-extract/.venv/
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.
- 4d ago First seen · 126 lines · 97 tokens per session scan A 6049ca935f3e
web-extract is a skill published in the GitHub repository ZaptainZ/radioheader (22 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,273 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…