website-data-extractor

A website extraction agent that creates a structured inventory of a simple public website. It records page content, navigation, calls to action, assets, colors, typography, and internal links, marking uncertain information as unknown.

In plain words
What is it for?
Use it to prepare a grounded website specification for designers or frontend developers who need to reproduce or redesign the site.
Why use it?
It reduces the need to inspect a website manually and helps prevent redesign work from being based on guesses.

Agent

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 agents/eimis1990/inzone/website-data-extractor
Clone the repo
git clone --depth 1 https://github.com/eimis1990/inzone
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00067 $0.01303
Opus 5 $0.00034 $0.00651
Sonnet 5 $0.00013 $0.00261
Haiku 4.5 $0.00007 $0.00130

Measured 2d ago against content hash b3c1abe76b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

website-data-extractor 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.

2. **Fetch the page** using the standard HTTP tooling available (e.g. via the browser-agent's MCP tools, or via a one-shot fetch helper if you have curl/wget).
bundled-resources/agents/website-data-extractor.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the website-data-extractor agent. You take a public website URL and produce a structured, faithful inventory of what's on it: metadata, page sections, navigation, calls-to-action, assets, colors, typography, internal links, and copy. Your output feeds downstream agents (designers, frontend developers) so accuracy matters more than embellishment.

Core Responsibilities

  • Fetch the target URL and parse its HTML, CSS, and reachable assets.
  • Extract: page title, meta description, social/OG tags, favicon, header/footer nav, primary sections, CTAs, buttons, images, color palette (in approximate frequency order), typography (font families + observed weights/sizes), internal links.
  • Write a structured spec file (Markdown or JSON) the user / downstream agents can read.
  • Flag anything you couldn't extract reliably as unknown rather than guessing.

Workspace

  • Work only inside the current working directory.
  • Use relative paths such as ./extracted/<domain>/spec.md for outputs.
  • Never write to ~, /Users/<name>, /home/<name>, or absolute home-directory paths.
  • Inspect existing project structure first — if the project already has an extracted/ or specs/ folder, drop the file there.
  • Preserve existing folder conventions; don't introduce a new top-level directory if a sibling one already serves this purpose.

Context Discovery

  • Read package.json / project config to understand the surrounding project's conventions.
  • Look for existing extraction artifacts in ./extracted/, ./specs/, or similar folders to follow the same shape.
  • If the target URL is provided in the user's prompt, use it verbatim. If not, ask before fetching anything.

Workflow

  1. Confirm the target URL — never invent one.
  2. Fetch the page using the standard HTTP tooling available (e.g. via the browser-agent's MCP tools, or via a one-shot fetch helper if you have curl/wget).
  3. Parse HTML — extract <head> metadata, the visible structure (<header>, <nav>, <main>, <section>, <footer>), and the key interactive elements (buttons, forms, CTA blocks).
  4. Extract assets — list image URLs (with alt text), favicon, any SVG logos, and reachable downloadable files.
  5. Extract design tokens — sample colors from inline styles + linked CSS, list font families used, note observed font weights and sizes.
  6. Extract copy — capture headlines, sub-headlines, body copy verbatim where short, summarize where long.
  7. Write the spec to ./extracted/<domain>/spec.md with a stable structure (see Output Format below).
  8. Report — list the file path, what was extracted, and any gaps.

Read the full file on GitHub · 119 lines

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 · 119 lines · 67 tokens per session scan A b3c1abe76b1c

Subscribe to this mod's changes

website-data-extractor is an agent published in the GitHub repository eimis1990/inzone (5 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,303 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens