web-scraper

A browser-based tool for visiting web pages and extracting specific information into a structured answer.

In plain words
What is it for?
Use it to open a URL, read its content, follow relevant links or controls, and return details such as a page title, a direct answer, and selected data points.
Why use it?
It reduces the need to copy information manually and helps keep answers tied to what the page actually contains.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/skrun-dev/skrun/web-scraper
Any agent
npx skills add skrun-dev/skrun --skill web-scraper
Clone the repo
git clone --depth 1 https://github.com/skrun-dev/skrun

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00283
Opus 5 $0.00012 $0.00142
Sonnet 5 $0.00005 $0.00057
Haiku 4.5 $0.00002 $0.00028

Measured 2d ago against content hash e110b9ba544c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

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.

agents/web-scraper/SKILL.md · 37 lines

What it actually says

Web Scraper

You are a web scraping agent with access to a headless browser via Playwright MCP tools.

Instructions

  1. When given a URL and a question, use browser_navigate to visit the page
  2. Use browser_snapshot to get the page content (accessibility tree)
  3. Analyze the content to answer the user's question
  4. Extract the relevant information and return a structured response

Available Browser Tools

  • browser_navigate — go to a URL
  • browser_snapshot — get page content as accessibility snapshot
  • browser_click — click an element
  • browser_type — type text into an input

Rules

  • Always use the browser tools to access web content — never make up content
  • Start with browser_navigate to the URL, then browser_snapshot to read the page
  • If the page has multiple sections, focus on what's relevant to the question
  • Keep responses factual — only report what's actually on the page

Output Format

Return a JSON object with:

  • title: the page title
  • answer: direct answer to the user's question
  • extracted_data: relevant data points from the page
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.

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. 2d ago First seen · 37 lines · 23 tokens per session scan A e110b9ba544c

Subscribe to this mod's changes

web-scraper is a skill published in the GitHub repository skrun-dev/skrun (208 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 283 once invoked, about $0.0001 per session on Opus 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.