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 khalilbenaz/claude-skills-collection --skill web-scraper-subagentgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/web-scraper-subagent)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/web-scraper-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/web-scraper-subagent/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/khalilbenaz/claude-skills-collection/web-scraper-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/web-scraper-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.02834 |
| Opus 5 | $0.00046 | $0.01417 |
| Sonnet 5 | $0.00018 | $0.00567 |
| Haiku 4.5 | $0.00009 | $0.00283 |
Grade A, and why
web-scraper-subagent 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 11d 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.
Vérifier aussi que l'URL est bien formée (`urllib.parse.urlparse`) et que le schéma est `http` ou `https`. How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Scraper Sub-Agent
Quand utiliser ce skill
Utiliser ce skill quand un agent parent doit déléguer la collecte de données web à un sous-agent autonome. Cas typiques :
| Cas | Outil adapté |
|---|---|
| Page statique HTML simple | requests + BeautifulSoup |
| Page JS dynamique (SPA, lazy-load) | playwright headless |
| Extraction de texte principal | trafilatura |
| Tableau HTML → DataFrame | pandas.read_html |
| Scraping à grande échelle | scrapy + middlewares |
| Browser automation avec MCP | playwright-mcp |
Ne pas utiliser ce skill pour : APIs REST publiques (utiliser requests direct), données disponibles via export officiel (CSV, JSON), ou sites protégés par authentication que l'on ne détient pas.
Workflow en étapes
Étape 1 — Valider l'input avant toute requête réseau
REQUIRED_FIELDS = {"url"}
DEFAULTS = {"max_pages": 1, "timeout": 30, "output_format": "json",
"cache_ttl": 3600, "follow_pagination": False, "proxy": None}
def validate_input(params: dict) -> dict:
missing = REQUIRED_FIELDS - params.keys()
if missing:
raise ValueError(f"Champs obligatoires manquants : {missing}")
return {**DEFAULTS, **params}
Vérifier aussi que l'URL est bien formée (urllib.parse.urlparse) et que le schéma est http ou https.
Étape 2 — Choisir le moteur de rendu
# Décision : site statique ou dynamique ?
import requests
from bs4 import BeautifulSoup
r = requests.get(url, timeout=10)
soup = BeautifulSoup(r.text, "lxml")
# Si les sélecteurs retournent vide → site JS → basculer sur Playwright
if not soup.select(selectors["target_field"]):
use_playwright = True
Playwright en mode headless Chromium est le choix par défaut pour les sites dynamiques en 2026. Puppeteer n'est pertinent que si le reste de la stack est Node.js.
Étape 3 — Initialiser le navigateur (Playwright)
from playwright.sync_api import sync_playwright
def get_page_content(url: str, timeout: int, proxy: str | None) -> str:
with sync_playwright() as p:
browser = p.chromium.launch(
headless=True,
proxy={"server": proxy} if proxy else None,
args=["--no-sandbox", "--disable-blink-features=AutomationControlled"]
)
ctx = browser.new_context(
user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
locale="fr-FR",
viewport={"width": 1280, "height": 800},
)
page = ctx.new_page()
page.goto(url, wait_until="networkidle", timeout=timeout * 1000)
content = page.content()
browser.close()
return content
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.
- 11d ago First seen · 297 lines · 92 tokens per session scan A 848e28ee927a
web-scraper-subagent is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 92 tokens to every session and 2,834 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
finance-econ-literacy
A Korean-language guide to understanding economic indicators such as interest rates, exchange rates, inflation, GDP, employment, and trade. It explains how these figures can affect loans, savings, investments, and spending.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
stock-business-review
Review a US-listed company's business model and revenue structure for an equity-research workup. Covers product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition (organic vs acquired vs price vs volume), and information-tier discipline (which numbers are facts vs…
stock-earnings-quality-review
Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…