Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/christopherlouet/claude-basenpx agentmods add skills/christopherlouet/claude-base/web-scrapingWrote 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/christopherlouet/claude-base/web-scraping)<a href="https://agentmods.dev/skills/christopherlouet/claude-base/web-scraping"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/web-scraping/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/christopherlouet/claude-base/web-scraping"><img src="https://agentmods.dev/badge/skills/christopherlouet/claude-base/web-scraping.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 | $0.00075 | $0.01693 |
| Opus 5 | $0.00037 | $0.00847 |
| Sonnet 5 | $0.00015 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
web-scraping 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 5d 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: Clean LLM-ready web scraping via Firecrawl (scrape/crawl/map/extract/search). Trigger when the user wants to extract content from a page, crawl a site, collect structured data, bypass anti-bot/JS-rendering, How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Scraping (Firecrawl-first)
Goal
Extract LLM-ready web content without hacking around: clean markdown, structured JSON, anti-bot and JS-rendering handled. Firecrawl is the reference wrapper; fallback to Playwright or curl + html2text if unavailable.
When to trigger this skill
- "scrape this page / this site"
- "extract data from ..."
- "crawl site X"
- "fetch all articles from ..."
- "search the web and extract the content"
- "parse this dynamic page" (site with JS-rendering)
- "bypass the paywall / anti-bot" (legitimate use only)
When NOT to use this skill
- Quick web search without structured extraction ->
WebSearchis enough - A single static URL, simple page ->
WebFetchis enough - Visual test / browser interaction -> skill
qa-chromeor agent-browser - Form / login automation -> agent-browser or Playwright directly
Prerequisites
Option 1: Firecrawl cloud (recommended)
export FIRECRAWL_API_KEY="fc-xxx" # https://firecrawl.dev
npm install -g firecrawl # or pip install firecrawl-py
Option 2: Firecrawl self-hosted
Docker compose available on github.com/mendableai/firecrawl. Useful if data is sensitive or budget is limited.
Option 3: Fallback without Firecrawl
If Firecrawl is missing, degrade gracefully:
| Need | Fallback | Limitation |
|---|---|---|
| Simple static page | curl -sL URL | pandoc -f html -t markdown |
No JS rendering |
| JS-heavy page | npx playwright + page.content() + markdownify |
Heavy, 300MB+ of deps |
| Whole site | recursive filtered wget | No deduplication, no LLM-ready output |
IMPORTANT: always announce when degrading. The user must know if the content is partial (JS not rendered).
The 5 Firecrawl operations
1. Scrape (one URL)
firecrawl scrape https://example.com/article \
--formats markdown,links \
--only-main-content
Output: clean markdown (navigation / footers stripped), list of links, OG metadata.
2. Crawl (whole site)
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.
- 5d ago First seen · 211 lines · 75 tokens per session scan A 99271f766d5a
web-scraping is a skill published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,693 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
peekaboo-driver
Use this skill when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by skills/test-runner/ to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.
playwright-driver
Use this skill when executing web tests via the canonical playwright npm package (Microsoft, Apache-2.0). Dispatched by skills/test-runner/ to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under .orchestrator/metrics/test-runs/ /, and exits with…
Web Browser
Browse the web, take screenshots, interact with pages, fill forms. Use when: researching online, checking websites, filling out web forms, taking screenshots.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
ios-development
Comprehensive guide for building native Apple platform applications.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.