A web-scraping tool for fetching pages that ordinary requests cannot read because of bot protection or JavaScript-rendered content. It supports simple HTTP fetching, browser-based rendering, stealth fetching, and multi-page crawling.

Use it to scrape protected or dynamic public websites, render JavaScript pages, or crawl many pages while respecting site rules and terms.

It provides fallback methods when a normal web extractor returns an empty page or is blocked. It is for reading pages, not logging in or clicking through interactive workflows.

scrapling — Skill for Claude Code and Codex by cloveric/tarocub

Install

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.

Any agent

npx skills add cloveric/tarocub --skill scrapling

Clone the repo

git clone --depth 1 https://github.com/cloveric/tarocub

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cloveric/tarocub/scrapling/github.svg)](https://agentmods.dev/skills/cloveric/tarocub/scrapling)

Your own site

<a href="https://agentmods.dev/skills/cloveric/tarocub/scrapling"><img src="https://agentmods.dev/badge/skills/cloveric/tarocub/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cloveric/tarocub/scrapling"><img src="https://agentmods.dev/badge/skills/cloveric/tarocub/scrapling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,573 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 28
Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01573
Opus 5.5	$0.00000	$0.00629
Sonnet 5.5	$0.00000	$0.00315
Haiku 4.5	$0.00000	$0.00157

Measured 2mo ago against content hash e6d71c1e7b45, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/scrapling/SKILL.md · 100 lines

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_extract came 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_extract returns 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_extract first.
- 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.

Read the full file on GitHub · 100 lines

Changes

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.

2mo ago First seen · 100 lines · 0 tokens per session scan A e6d71c1e7b45

Subscribe to this mod's changes

scrapling is a skill published in the GitHub repository cloveric/tarocub (24 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,573 tokens. 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.

Browser automation Claude Code Multi-Agent Research TypeScript agent-bus anthropic codex

scrapling next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
scraplingcloveric/tarocub	Skill	24	20d ago	MIT	A	0	Claude Code, Codex
omk-computerusedmae97/omk	Skill	151	today	MIT	A	67	Claude Code, Codex
shogun-screenshotyohey-w/multi-agent-shogun	Skill	1.4k	3mo ago	MIT	A	149	Claude Code
omk-browserdmae97/omk	Skill	151	today	MIT	A	38	Claude Code, Codex
open-compute-bridgeellmos-ai/skills	Skill	9	4d ago	MIT	B	149	Claude Code, Codex
node-backendshahtuyakov/claude-setup	Skill	13	10mo ago	MIT	A	55	Claude Code, Codex
xhmoabualruz/fulcrum	Skill	7	1mo ago	MIT	A	49	Claude Code