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 agentmods add skills/scraperapi/scraperapi-skills/scraperapi-scraper-buildernpx skills add scraperapi/scraperapi-skills --skill scraperapi-scraper-buildergit clone --depth 1 https://github.com/scraperapi/scraperapi-skillsWhat 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 | $0.00206 | $0.03189 |
| Opus 5 | $0.00103 | $0.01595 |
| Sonnet 5 | $0.00041 | $0.00638 |
| Haiku 4.5 | $0.00021 | $0.00319 |
Grade A, and why
scraperapi-scraper-builder 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 2d 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.
Scan inline `<script>` blocks for `fetch(` or `axios.get(` calls pointing to internal paths (e.g., `/api/products`, `/_next/data/`). If found, scraping that JSON endpoint is usually simpler and more stable than parsing H How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScraperAPI Scraper Builder
Build production-quality scrapers using ScraperAPI. Work through four phases: gather requirements, probe the target site, make architecture decisions, then generate a complete runnable script.
Phase 1 — Gather Requirements
Before writing code, collect the following. Pull from the user's prompt; ask only what is missing.
| Info | Default if not specified |
|---|---|
| Target URL or website | Required — ask if missing |
| Data fields to extract | Ask if vague ("product info" → which fields exactly?) |
| Volume | Infer: single URL / paginated / bulk list of URLs |
| Language | Ask if not clear from context; Python is a reasonable default |
| Output format | stdout JSON |
| Geo-targeting needed? | Infer from site type; confirm for e-commerce pricing |
Phase 2 — Site Reconnaissance
Before making any architecture decisions, fetch 1–2 sample pages from the target site using ScraperAPI to observe actual behavior. This replaces guesswork with evidence and costs at most 2 credits.
What to fetch
Fetch at most two pages:
- A listing or category page (the main target) — e.g., a product grid, search results, or article index
- A detail page (only if the user needs data from individual items) — e.g., a single product, article, or profile
Always start with a standard request (no render, no premium) — the cheapest probe:
GET https://api.scraperapi.com/?api_key=<SCRAPERAPI_API_KEY>&url=<target_url>
What to observe
1. Response status
| Status | Meaning |
|---|---|
| 200 | Proceed to content analysis |
403 + body has "Just a moment", cf-ray, or "Cloudflare" |
Cloudflare detected |
| 403 + body has "DataDome", "PerimeterX", or "Akamai" | Bot manager detected |
| 403 (generic) | Anti-bot protection present; premium proxies likely needed |
| 429 | Rate limited; note for architecture phase |
2. Content completeness (for 200 responses)
Signals that render=true will be needed:
- Empty SPA containers:
<div id="root"></div>,<div id="app"></div>,<div id="__next"></div>with no children - Framework markers in
<script>tags:_next,__nuxt__,react,vue,angular - Response is mostly
<script>and<div>tags with little visible text - Target data fields (from Phase 1) are absent from the HTML
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.
- 2d ago First seen · 291 lines · 206 tokens per session scan A 58e8683b33aa
scraperapi-scraper-builder is a skill published in the GitHub repository scraperapi/scraperapi-skills (10 stars, last pushed 25d ago), licensed MIT. It adds 206 tokens to every session and 3,189 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
ecommerce-full-pipeline
电商运营在开展跨境电商或闲鱼捡漏业务时，若需解决选品难、上架繁琐等痛点，必用此技能！一键打通“爆品挖掘→1688采集→多平台上架→推广文案→短视频生成”全自动流水线，轻松实现端到端自动化，让开店运营效率翻倍。.
agent-reach-channels
Use when multi-platform e-commerce and messaging channel extraction (Shopee, TikTok Shop, WeChat).
ecommerce-product-scraping
Use when you need to scrape e-commerce product data — titles, brands, prices, MRP/list price, discounts, ratings, variants/sizes, availability, images, and product URLs — from online storefronts and marketplaces. Covers Amazon, Flipkart, AliExpress, Myntra, Nykaa, Meesho, Snapdeal, Noon, AJIO, FirstCry, Tata Cliq, and…
review-reputation-scraping
Use when scraping reviews, ratings, or reputation data — review text, star ratings, TrustScore, pros/cons, company replies. Covers Trustpilot, G2, Capterra, Yelp, Google Maps, and Shopify review widgets. Triggers on "scrape reviews", "ratings", "brand monitoring", "voice of customer", "VOC", "competitor reviews"…
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…