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 sandbaseai/sandbase-skills --skill web-scrapergit clone --depth 1 https://github.com/sandbaseai/sandbase-skillsWrote 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/sandbaseai/sandbase-skills/web-scraper)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/web-scraper"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/web-scraper/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/sandbaseai/sandbase-skills/web-scraper"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/web-scraper.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 | $0.00052 | $0.00554 |
| Opus 5.5 | $0.00021 | $0.00222 |
| Sonnet 5.5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
web-scraper scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to playwright-api — 593 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Scraper
Universal web scraping and data extraction through SandBase. Scrape individual pages, crawl entire sites, extract structured data, and capture visual snapshots. Read the API map before selecting a capability.
Call SandBase capabilities
For every selected tool, call sandbase_describe_tool first and use only arguments in its current input schema. Then call sandbase_call_tool with the exact tool_name.
Operating principles
- Respect robots.txt and rate limits — these tools handle that automatically.
- Use the lightest tool for the job: markdown scrape before full crawl.
- Structured data extraction is best for product pages, directories, and lists.
- Screenshots are useful for visual verification and design research.
Workflow
1. Single page extraction
Use context_dev_scrape_markdown for clean Markdown output (best for articles, docs).
Use context_dev_scrape_html for raw HTML (best for structure analysis).
Use firecrawl_scrape for advanced single-page extraction with options.
2. Site crawling
Use firecrawl_crawl to crawl multiple pages following links.
Use firecrawl_map to discover all URLs on a site.
Use context_dev_crawl_site for site-wide content extraction.
Use context_dev_crawl_sitemap for sitemap-based crawling.
3. Structured data extraction
Use context_dev_extract_structured_data for custom schema extraction from pages.
Use context_dev_extract_product for single product data.
Use context_dev_extract_products for product listing pages.
4. Visual and metadata
Use context_dev_capture_screenshot for visual page snapshots.
Use context_dev_scrape_images for image extraction.
Use context_dev_scrape_fonts for typography analysis.
Use context_dev_retrieve_brand for brand asset extraction.
Output
Return: extracted content in requested format, structured data as JSON, screenshot URLs, or crawl results with page list.
Example tasks
- "Extract the content from this article as clean Markdown: [URL]."
- "Crawl [website] and list all their product pages."
- "Extract product name, price, and description from this page: [URL]."
- "Take a screenshot of [URL] at desktop resolution."
- "Map all pages on [website] and categorize by content type."
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.
- 1mo ago First seen · 60 lines · 52 tokens per session scan A eea3783d7bff
web-scraper is a skill published in the GitHub repository sandbaseai/sandbase-skills (202 stars, last pushed 23d ago), licensed Apache-2.0. It adds 52 tokens to every session and 554 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to playwright-api, differing in 593 lines, and is treated as a copy.
Other skills, from other repositories
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
browser-use-cli
Drive a real browser from the shell with the browser-use CLI when a task needs page interaction, rendered DOM, or a logged-in session.
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply.…
record-browser-gif
Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply.…
error-handling
A set of rules for deciding how software should report failures and what information error messages should contain.
test-first
A test-first development guide, where tests are written before the code they check. TDD, or test-driven development, means first writing a test that fails, then writing the simplest code that makes it pass.