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 rockyflux/yq-workflow --skill scraplinggit clone --depth 1 https://github.com/rockyflux/yq-workflowWrote 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/rockyflux/yq-workflow/scrapling)<a href="https://agentmods.dev/skills/rockyflux/yq-workflow/scrapling"><img src="https://agentmods.dev/badge/skills/rockyflux/yq-workflow/scrapling/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/rockyflux/yq-workflow/scrapling"><img src="https://agentmods.dev/badge/skills/rockyflux/yq-workflow/scrapling.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 | $0.00074 | $0.01083 |
| Opus 5.5 | $0.00030 | $0.00433 |
| Sonnet 5.5 | $0.00015 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
scrapling 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 1mo 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.
This is a copy
100% identical to scrapling — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrapling 网页抓取 Skill
步骤 0：检查版本
pip show scrapling
- 未安装 → 执行
pip install "scrapling[fetchers]"+scrapling install - 有新版 → 执行
pip install --upgrade "scrapling[fetchers]"→ 查 changelog 告知用户 - 已最新 → 继续
步骤 1：选择 Fetcher
目标网站 →
│
├─ 已有 HTML 字符串/文件，只需解析?
│ → Selector（纯解析，无网络请求）
│ → 模板: templates/parse_only.py
│
├─ 静态页面，无 JS 渲染，无反爬?
│ → Fetcher（最快，基于 curl_cffi）
│ → 模板: templates/basic_fetch.py
│
├─ 需要登录（HTTP 表单，非 JS 登录）?
│ → FetcherSession（保持会话 cookie）
│ → 模板: templates/session_login.py
│
├─ 有 Cloudflare / WAF 保护?
│ → StealthyFetcher（Camoufox 浏览器，自动过 CF）
│ → 模板: templates/stealth_cloudflare.py
│
├─ SPA 应用（React/Vue），需要 JS 渲染?
│ → DynamicFetcher（Playwright 浏览器）
│ → 基于模板即时生成
│
└─ 不确定?
→ 先用 Fetcher 试，403/空内容 → 升级到 StealthyFetcher
步骤 2：执行工作流
1. 检查版本（步骤 0）
2. 查阅 references/site-patterns.md — 匹配已有模式则直接复用
3. 无匹配 → 用决策树选择 Fetcher
4. 读取对应模板 → 替换参数 → 生成完整脚本
5. 执行脚本 → 返回结果
6. **沉淀经验（必做）**:
- 新站点 → 追加到 site-patterns.md
- 新 cookie / 用户提供了 cookie → 保存到 cookie-vault.md
- **完成抓取后必须检查**：是否有新的 cookie 或 site pattern 需要保存
Cookie 格式速查
| Fetcher 类型 | Cookie 格式 | 示例 |
|---|---|---|
| Fetcher / FetcherSession | dict |
{'name': 'value', 'token': 'abc'} |
| StealthyFetcher / DynamicFetcher | list[dict] |
[{'name': 'n', 'value': 'v', 'domain': '.site.com', 'path': '/'}] |
浏览器 Fetcher cookie 必填字段: name, value, domain, path
超时单位速查
| Fetcher 类型 | 超时单位 | 示例 |
|---|---|---|
| Fetcher / FetcherSession | 秒 | timeout=30 |
| StealthyFetcher / DynamicFetcher | 毫秒 | timeout=60000 |
模板索引
| 模板 | 文件 | 何时读取 |
|---|---|---|
| 基础 HTTP 抓取 | templates/basic_fetch.py |
目标为静态页面，无反爬 |
| Cloudflare 绕过 | templates/stealth_cloudflare.py |
目标有 CF/WAF 保护 |
| Session 登录 | templates/session_login.py |
需 HTTP 表单登录后抓取 |
| 纯 HTML 解析 | templates/parse_only.py |
已有 HTML 字符串，只需提取数据 |
References 索引
| 文件 | 何时读取 |
|---|---|
references/site-patterns.md |
每次抓取前先查阅 — 检查目标站点是否有已记录的模式 |
references/api-quick-ref.md |
生成脚本时查阅 — Fetcher/Selector 方法签名和参数 |
references/troubleshooting.md |
执行报错时查阅 — 按错误信息查找原因和解决方案 |
references/cookie-vault.md |
需要登录 cookie 时查阅 — 检查是否有历史记录可复用 |
references/maintenance.md |
安装/升级/依赖问题时查阅 — 安装层级和验证命令 |
What ships with it
9 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.
- references/api-quick-ref.md 3.4 KB
- references/cookie-vault.md 1.4 KB
- references/maintenance.md 2.4 KB
- references/site-patterns.md 3.3 KB
- references/troubleshooting.md 3.1 KB
- templates/basic_fetch.py 527 B runs code
- templates/parse_only.py 488 B runs code
- templates/session_login.py 717 B runs code
- templates/stealth_cloudflare.py 677 B runs code
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.
- 1mo ago First seen · 99 lines · 74 tokens per session scan A e369e2cd5f31
scrapling is a skill published in the GitHub repository rockyflux/yq-workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,083 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to scrapling, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…