A web page scraper that opens a supplied URL and extracts its content into Markdown, JSON, or plain text. It can also capture screenshots and scroll pages to load content that appears dynamically.

Use it to collect article or page text, export structured results, capture screenshots, or scrape JavaScript-driven pages and pages with infinite scrolling.

It removes the need to copy page content manually and handles pages whose full content is not visible at first load. Error handling helps deal with problems during retrieval.

web-scrape — Skill for Claude Code by 21pounder/terminalAgent

Install

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.

Any agent

npx skills add 21pounder/terminalAgent --skill web-scrape

Clone the repo

git clone --depth 1 https://github.com/21pounder/terminalAgent

Made for: Claude Code.

Or install deepresearch, the plugin that ships this one along with the rest of its 5 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/21pounder/terminalagent/web-scrape/github.svg)](https://agentmods.dev/skills/21pounder/terminalagent/web-scrape)

Your own site

<a href="https://agentmods.dev/skills/21pounder/terminalagent/web-scrape"><img src="https://agentmods.dev/badge/skills/21pounder/terminalagent/web-scrape/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/21pounder/terminalagent/web-scrape"><img src="https://agentmods.dev/badge/skills/21pounder/terminalagent/web-scrape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,500 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.01500
Opus 5.5	$0.00008	$0.00600
Sonnet 5.5	$0.00004	$0.00300
Haiku 4.5	$0.00002	$0.00150

Measured 2mo ago against content hash 0956d6336acc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-scrape 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/html_clean.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

deepresearch/.claude/skills/web-scrape/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Scraping Skill v3.0

Usage

/web-scrape <url> [options]

Options:

--format=markdown|json|text - Output format (default: markdown)
--full - Include full page content (skip smart extraction)
--screenshot - Also save a screenshot
--scroll - Scroll to load dynamic content (infinite scroll pages)

Examples:

/web-scrape https://example.com/article
/web-scrape https://news.site.com/story --format=json
/web-scrape https://spa-app.com/page --scroll --screenshot

Execution Flow

Phase 1: Navigate and Load

1. mcp__playwright__browser_navigate
   url: "<target URL>"

2. mcp__playwright__browser_wait_for
   time: 2  (allow initial render)

If --scroll option: Execute scroll sequence to trigger lazy loading:

3. mcp__playwright__browser_evaluate
   function: "async () => {
     for (let i = 0; i < 3; i++) {
       window.scrollTo(0, document.body.scrollHeight);
       await new Promise(r => setTimeout(r, 1000));
     }
     window.scrollTo(0, 0);
   }"

Phase 2: Capture Content

4. mcp__playwright__browser_snapshot
   → Returns full accessibility tree with all text content

If --screenshot option:

5. mcp__playwright__browser_take_screenshot
   filename: "scraped_<domain>_<timestamp>.png"
   fullPage: true

Phase 3: Close Browser

6. mcp__playwright__browser_close

Smart Content Extraction

After getting the snapshot, apply intelligent extraction:

Step 1: Identify Content Type

Page Type	Indicators	Extraction Strategy
Article/Blog	`<article>`, long paragraphs, date/author	Extract main article body
Product Page	Price, "Add to Cart", specs	Extract title, price, description, specs
Documentation	Code blocks, headings hierarchy	Preserve structure and code
List/Search	Repeated item patterns	Extract as structured list
Landing Page	Hero section, CTAs	Extract key messaging

Read the full file on GitHub · 259 lines

Files

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.

scripts/html_clean.js 1.5 KB runs code

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.

2mo ago First seen · 259 lines · 20 tokens per session scan A 0956d6336acc

Subscribe to this mod's changes

web-scrape is a skill published in the GitHub repository 21pounder/terminalAgent (116 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,500 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation Research

web-scrape next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web-scrape21pounder/terminalAgent	Skill	116	5mo ago	Apache-2.0	A	20	Claude Code
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code