More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Web Research Plus: Web Forensics from the Command Line

    1

    Retrieve web content without a browser — clean article extraction, RSS monitoring, Wayback snapshots, and Common Crawl history — with provenance on everything.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Web Research Plus: Web Forensics from the Command Line

    Web Research Plus: Web Forensics from the Command Line

    Example session with this skill installed

    What did our competitor's pricing page say last year? Find the old version and quote it with a source I can cite.

    • Read your context and instructions
    • Compiled the web research plus

    Triage picked the Wayback path first: the question is about a page as it was, not as it is, so a live fetch would answer the wrong question. The Wayback availability check found snapshots in March and September of last year; the March snapshot was closest to the period in question and was fetched in full. Article extraction pulled the pricing table cleanly: three tiers at $9, $29, and $79 per month, with the middle tier carrying unlimited projects — the current page shows $12, $39, and $99, with the middle tier now capped at 50 projects. A second snapshot from September confirmed the change happened between March and September, narrowing the window for the price rise to that six-month span. The deliverable was the quoted pricing from March with the full provenance attached: the snapshot timestamp, the archive URL, the fetch date, and the extraction method, plus the September snapshot as the confirming source, all filed under the competitor's name so the next pricing question starts from the record. One caution was recorded: the March snapshot's footer showed a stale copyright year, which is an artifact of how the page was archived, not evidence about the pricing — it was noted and set aside rather than quoted.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Some of the best web research never opens a browser. This skill retrieves content from the command line: clean article extraction from a page, RSS feed monitoring, Wayback snapshots of pages as they were, and Common Crawl fetches for history at scale. Every retrieval carries provenance — where it came from, when it was fetched, and what it is — because a quote without a source is a rumor with formatting. Use it when a page blocks your browser, when you need what a page said last year, when you are monitoring a feed, or when you need the same fact from many sources without clicking through each one.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    It retrieves public content; it does not bypass logins, paywalls, or access controls.
    Archive snapshots are captures, not the live page — a snapshot can be incomplete, stale, or show rendering artifacts that are not part of the original.
    Provenance is only as good as the record kept: a fetch without a timestamp and a source is a quote you cannot defend.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    For a live page, a browser is fine. For last year's page, a dead page, or fifty pages at once, the command line is faster — and it leaves a provenance record a browser visit does not.

    Yes, with its timestamp and archive address attached. Cite the snapshot, not the live page — the live page may have changed since.

    Then the answer is 'no snapshot exists', and the skill says so. Common Crawl may hold a copy, and if neither does, the honest result is that the page's history is not retrievable.

    New in Workflow Automation