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 cyberchitta/scrapling-fetch-mcp --skill s-fetchgit clone --depth 1 https://github.com/cyberchitta/scrapling-fetch-mcpWrote 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/cyberchitta/scrapling-fetch-mcp/s-fetch)<a href="https://agentmods.dev/skills/cyberchitta/scrapling-fetch-mcp/s-fetch"><img src="https://agentmods.dev/badge/skills/cyberchitta/scrapling-fetch-mcp/s-fetch/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/cyberchitta/scrapling-fetch-mcp/s-fetch"><img src="https://agentmods.dev/badge/skills/cyberchitta/scrapling-fetch-mcp/s-fetch.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 | $0.00037 | $0.00653 |
| Opus 5 | $0.00018 | $0.00327 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
s-fetch scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Fetch a URL directly with scrapling's bot-detection bypass. Use when the user asks to fetch, curl, or scrape a URL from a bot-protected site. This is a copy
81% identical to investor-outreach — 132 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
s-fetch
Fetches a URL directly via scrapling, bypassing bot detection.
Setup
If the bash command below fails because scrapling-fetch-mcp isn't
installed (e.g. No such file or directory for the bin/python3
path), follow references/install.md once before proceeding.
Arguments
$ARGUMENTS — parse as <url> [mode] [format]
- url (required)
- mode (optional, default
basic):basic|stealth|max-stealth - format (optional, default
markdown):markdown|html
Instructions
Run the following Bash command, substituting URL, MODE, and FORMAT with the parsed values:
"$(uv tool dir)/scrapling-fetch-mcp/bin/python3" - <<'PYEOF'
import asyncio
from contextlib import redirect_stdout
from os import devnull
async def fetch(url, mode):
with open(devnull, "w") as null, redirect_stdout(null):
from scrapling.fetchers import AsyncFetcher, StealthyFetcher
if mode == "basic":
return await AsyncFetcher.get(url, stealthy_headers=True)
elif mode == "stealth":
return await StealthyFetcher.async_fetch(url, headless=True, network_idle=True)
elif mode == "max-stealth":
return await StealthyFetcher.async_fetch(
url, headless=True, block_webrtc=True,
network_idle=True, disable_resources=False, block_images=False
)
else:
raise ValueError(f"Unknown mode: {mode}")
url = "URL"
mode = "MODE"
fmt = "FORMAT"
page = asyncio.run(fetch(url, mode))
html = page.html_content
if fmt == "markdown":
from bs4 import BeautifulSoup
from markdownify import markdownify as md
soup = BeautifulSoup(html, "lxml")
for tag in soup(["script", "style"]):
tag.extract()
body = soup.find("body")
print(md(str(body if body else soup)))
else:
print(html)
PYEOF
If mode was not given and basic returns blocked or empty content, retry with stealth, then max-stealth.
Mode guide
| Mode | Speed | Use when |
|---|---|---|
basic |
1–2s | Most sites; curl-cffi with stealth headers |
stealth |
3–8s | Sites that block basic; headless Chromium via patchright |
max-stealth |
10s+ | Heavily protected sites; full browser fingerprint |
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.
- 12d ago First seen · 81 lines · 37 tokens per session scan A 25506eedad8c
s-fetch is a skill published in the GitHub repository cyberchitta/scrapling-fetch-mcp (115 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 653 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 81% identical to investor-outreach, differing in 132 lines, and is treated as a copy.
Other skills, from other repositories
custom-features
Author a TanStack Table v9 feature plugin across every FeatureMap and API installation surface: state, options, column definitions, table, column, row, cell, header, row-model functions/caches, defaults, prototypes, and table/row/column instance data lifecycles. Load for initTableInstanceData, resetTableInstanceData…
frontend-conventions
Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
typescript-react
Apply, review, and explain React conventions from the TypeScript Style Guide. Use automatically for TypeScript and TSX tasks involving prop-derived state, prop typing, component responsibilities, data flow, compound components, or client and server state.
electron-dev
Electron desktop apps with React, TypeScript, and Vite. Use for IPC, window/tray, PTY terminals, WebRTC, and packaging.
typescript-rules
React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.