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 nimadorostkar/Claude-Skills-collection --skill web-data-extractiongit clone --depth 1 https://github.com/nimadorostkar/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/nimadorostkar/claude-skills-collection/web-data-extraction)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/web-data-extraction"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/web-data-extraction/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/nimadorostkar/claude-skills-collection/web-data-extraction"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/web-data-extraction.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 | $0.00100 | $0.01432 |
| Opus 5.5 | $0.00040 | $0.00573 |
| Sonnet 5.5 | $0.00020 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
web-data-extraction 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 17d 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.
2. **Determine whether the content is in the HTML** — `curl` the URL and search for the data. If it is absent, the page renders it with JavaScript and static parsing will return nothing, forever, with no error. How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Data Extraction
Purpose
Get structured data out of web pages reliably. The two questions that determine the entire approach are whether an API exists, and whether the content is rendered by JavaScript — and both are answered in under a minute.
When to Use
- Extracting structured data from a website.
- A scraper that returns empty results or breaks constantly.
- Deciding between static parsing and a headless browser.
- Building a repeatable data-collection pipeline.
Capabilities
- Approach selection: API, static HTML, or browser rendering.
- Resilient selector strategy.
- JavaScript-rendered content.
- Rate limiting, retries, and politeness.
- Detecting and handling structure changes.
Inputs
- The target pages and the data required.
- Whether the site has an API, documented or otherwise.
- Volume and frequency.
Outputs
- Structured, validated data.
- A scraper that fails loudly when the page changes, rather than silently returning nothing.
Workflow
- Look for an API first — Check the documentation, then check the network tab. Very often the page itself calls a JSON endpoint, and that endpoint is stable, structured, and far easier to use than the HTML.
- Determine whether the content is in the HTML —
curlthe URL and search for the data. If it is absent, the page renders it with JavaScript and static parsing will return nothing, forever, with no error. - Choose the tool accordingly — Static HTML: an HTTP client and a parser. JavaScript-rendered: a headless browser. Do not use a browser when you do not need one; it is fifty times slower.
- Write resilient selectors — Anchor on stable attributes (
data-*, an id, a semantic element), not on a generated class name that changes with every deploy. - Be polite — Rate limit, identify yourself, respect
robots.txt, and cache. A scraper that hammers a site is both rude and likely to be blocked. - Validate the output — A scraper that silently returns zero rows because the page changed is worse than one that crashes.
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.
- 17d ago Changed · +57 tokens per session bae55fdc6455
- 1mo ago First seen · 128 lines · 43 tokens per session scan A a84ad60b936f
web-data-extraction is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (33 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 1,432 once invoked, about $0.0004 per session on Opus 5.5. 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
web-quality-audit
Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
agent-ready-scan-site
Sub-skill: Scan any URL for agent readiness. Checks 22 standards across 5 categories, returns readiness level (0-5), status of all checks, and fix instructions.
agent-ready-webmcp
Sub-skill de agent-ready-cloudflare: Implement WebMCP.
computer-use-runbook
Write the step-by-step runbook a computer-use or browser agent follows to finish a real online task, such as cancelling a subscription or changing an energy supplier: what to look for on screen, one action per step, how to know it worked, and where to stop for a human. Use when asked to write instructions for a…
geocode-get-geocode
Converts a free-text address into latitude and longitude coordinates.
useragent-get-useragent
Parses a user agent string and returns structured information about the browser, OS, device, and bot status.