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/cloveric/tarocub/scraplingnpx skills add cloveric/tarocub --skill scraplinggit clone --depth 1 https://github.com/cloveric/tarocubWrote 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/cloveric/tarocub/scrapling)<a href="https://agentmods.dev/skills/cloveric/tarocub/scrapling"><img src="https://agentmods.dev/badge/skills/cloveric/tarocub/scrapling.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 | $0.00161 | $0.01573 |
| Opus 5 | $0.00081 | $0.00787 |
| Sonnet 5 | $0.00032 | $0.00315 |
| Haiku 4.5 | $0.00016 | $0.00157 |
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 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrapling — anti-bot web scraping (CLI)
Scrapling fetches web pages with anti-bot bypass, stealth (headless) browser automation, JS rendering, and a spider framework. Three strategies: HTTP (light, no browser), dynamic (runs JS in a browser), stealth (Cloudflare / anti-bot). The scrapling command is on PATH. Run scrapling extract <sub> --help for exact flags.
Educational/research use. Respect robots.txt and each site's Terms of Service.
When to use Scrapling (vs the bot's other web tools)
The bot has several ways to read the web — use the lightest that works, escalate only when it fails:
- Search / "what's the latest" / don't know the URL →
web_search. - A normal public page →
web_extract(light, no browser). Default for plain pages. - X/Twitter, or any page that needs YOUR login → the x-fetch skill (it uses the logged-in Chrome). Scrapling has no login session, so it cannot reach private/logged-in content.
- Multi-step interaction (log in, click through a flow, fill a form, take a screenshot) → the agent-browser skill. Scrapling is fetch-and-extract, NOT interaction.
- Reach for Scrapling when any of these is true:
web_extractcame back blocked / a login or captcha wall / a Cloudflare page / suspiciously empty / clearly not the real content → that is the signal to escalate. Do not accept the garbage as the answer.- The page is JS-rendered and
web_extractreturns an empty shell. - You already know the site is anti-bot or dynamic (you were told, or it's a known protected site) → go straight to Scrapling; don't waste a doomed
web_extractfirst. - You need to crawl many pages / extract structured fields at scale.
Match the weight to the task. Inside Scrapling, prefer the light HTTP get for plain pages; only use stealthy-fetch (opens a headless browser, +5–15s, hundreds of MB) when actually blocked, and fetch (also a browser) when JS rendering is actually needed.
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 · 100 lines · 0 tokens per session scan A e6d71c1e7b45
scrapling is a skill published in the GitHub repository cloveric/tarocub (4 stars, last pushed 4d ago), licensed MIT. It adds 161 tokens to every session and 1,573 once invoked, about $0.0008 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 skills, from other repositories
pr-screenshots
Capture Playwright screenshots and embed them in GitHub PR descriptions.
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成（shogun-imagegenを使え）。.
browser_scripts
Visual browser automation script editor & manager for TubeCLI.
browser-use
Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.
pentest-client-advanced
Advanced client-side attacks — CORS misconfiguration, WebSocket security, clickjacking, postMessage abuse, CSS injection, and browser storage vulnerabilities.
openviking
OpenViking 集成 — 浏览器自动化与 Web 搜索工具.