generate-crawler-scraper

generate-crawler-scraper is a skill for Claude Code from ScrapeOps/scrapeops-scraping-assistant-claude-plugin. It costs 119 tokens per session (27,360 once invoked), scanned B, original, MIT.

A tool-building guide for making a crawler and scraper that work together. The crawler finds product links on search or category pages, and the scraper visits those links to collect product details.

In plain words
What is it for?
Use it to generate runnable scripts for collecting products from online stores and saving discovered URLs and product data as JSONL files, one JSON object per line.
Why use it?
It removes the need to design URL discovery, data fields, file handoff, and local execution from scratch. It keeps link finding and product extraction as separate steps.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node src/crawler.js --listing-url "<URL>" --max-pages <N> --output urls.jsonl.

Part of the scrapeops-scraping-assistant-claude-plugin plugin — 5 skills, 1 agent shipped together

Good fit Use it to generate runnable scripts for collecting products from online stores and saving discovered URLs and product data as JSONL files, one JSON object per line.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ScrapeOps/scrapeops-scraping-assistant-claude-plugin
agentmods
npx agentmods add skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-crawler-scraper

Made for: Claude Code.

Or install scrapeops-scraping-assistant-claude-plugin, the plugin that ships this one along with the rest of its 5 skills, 1 agent.

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.

agentmods badge for generate-crawler-scraper

README.md
[![agentmods](https://agentmods.dev/badge/skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-crawler-scraper.svg)](https://agentmods.dev/skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-crawler-scraper)
Your own site
<a href="https://agentmods.dev/skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-crawler-scraper"><img src="https://agentmods.dev/badge/skills/scrapeops/scrapeops-scraping-assistant-claude-plugin/generate-crawler-scraper.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 27,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.27360
Opus 5 $0.00060 $0.13680
Sonnet 5 $0.00024 $0.05472
Haiku 4.5 $0.00012 $0.02736

Measured 8d ago against content hash e3f21a6ad045, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

generate-crawler-scraper scanned grade B with 2 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

> **API key handling**: The MCP server reads `SCRAPEOPS_API_KEY` from `~/.claude/settings.json` automatically. If a tool call fails with "SCRAPEOPS_API_KEY is not configured", ask the user for their key, write it to `~/.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

from urllib.parse import urlsplit, parse_qsl
skills/generate-crawler-scraper/SKILL.md · 2,238 lines

How it starts

The opening of the file, as written. The whole thing — 2,238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ScrapeOps — Generate Crawler + Scraper Skill (local-orchestrated)

Build a runnable crawler+scraper pair locally. Two files are produced by the Go backend (one per phase) and you run them on the user's machine. Each generated script talks to the ScrapeOps proxy directly (no server-side orchestration).

Default layout is SEPARATE: crawler writes URLs to a JSONL file, scraper reads that file and produces product JSONL. No merged script.

Core rule: the Go backend ONLY generates code. Everything else — URL discovery, schema generation, local execution, JSONL handoff — happens here in the Claude Code session.

API key handling: The MCP server reads SCRAPEOPS_API_KEY from ~/.claude/settings.json automatically. If a tool call fails with "SCRAPEOPS_API_KEY is not configured", ask the user for their key, write it to ~/.claude/settings.json under env.SCRAPEOPS_API_KEY, and retry.


Step 1 — Collect inputs

Ask for each value unless the user stated it in their opening message. Never assume language/library.

Slot Description
domain Target site, e.g. amazon.com, walmart.com, mercadolivre.com.br
search_query Natural-language search term, e.g. "mens shirts", "camisetas masculinas"
language Ask. Python, JavaScript, PHP, Ruby, Go, Rust, Java, or C#
library Ask. Depends on language (BeautifulSoup, Cheerio, symfony/dom-crawler, nokogiri, goquery, scraper, jsoup, HtmlAgilityPack)
max_pages Pagination cap. Default 1 — ask via the fixed AskUserQuestion format in Step 1.4

1.1 — Domain and query

Extract from the user's message. "Crawler da Amazon buscando camisetas"amazon.com, camisetas. If either is ambiguous, ask.

1.2 — Language (obligatory question if not provided)

Use AskUserQuestion:

question: "Which language do you want the crawler + scraper in?"
header: "Language"
options:
  - label: "Python"
  - label: "JavaScript"
  - label: "PHP"
  - label: "Other"
    description: "Ruby, Go, Rust, Java, C#"

Read the full file on GitHub · 2,238 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.

  1. 8d ago First seen · 2,238 lines · 119 tokens per session scan B e3f21a6ad045

Subscribe to this mod's changes

generate-crawler-scraper is a skill published in the GitHub repository ScrapeOps/scrapeops-scraping-assistant-claude-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 119 tokens to every session and 27,360 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ebay-search-listing

Extracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle, caption, price, priceWithCurrency, currency, wasPrice, bids, shipping, seller, sellerFeedbackCount, sellerPositiveRating, reviewsCount, starRating, image) plus pagination state (currentPage…

browser-act/skills · 221 tokens

amazon-bestseller-listing

Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…

browser-act/skills · 300 tokens

amazon-search-listing

Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast…

browser-act/skills · 341 tokens

etsy-product-detail

Etsy product detail scraper: given an Etsy listing URL, returns full product detail including listingId, title, priceCurrent, priceOriginal, currency, images (all), description, shopName, shopUrl, rating, reviewCount, favorites, inCartCount, variations (with per-option price ranges), highlights, listedDate…

browser-act/skills · 187 tokens

walmart-product-detail

Walmart product detail page extractor: given a walmart.com product URL (walmart.com/ip/...), extract full product data including itemId, title, brand, model, UPC, price, wasPrice, currency, availability, category path, seller info, all images, shortDescription, longDescription, product highlights, full specifications…

browser-act/skills · 252 tokens

ecommerce-listing

Extract product list from any e-commerce category page, search results page, or keyword search with filters. Returns paginated product arrays with URL, name, price, currency, image, rating, review count per item. Supports URL input, keyword search, and site-scoped search with filters: price range, brand, category…

browser-act/skills · 182 tokens