web-extract

web-extract is a skill for Claude Code from epistemedeus/x402-url-extractor. It costs 86 tokens per session (1,646 once invoked), scanned A, original, MIT.

A tool for reading credential-free public webpages as structured JSON or clean Markdown, including page text and selected metadata.

In plain words
What is it for?
Use it to extract titles, descriptions, headings, links, JSON-LD, social metadata, or bounded page text from public websites.
Why use it?
It handles common fetching problems such as redirects, timeouts, oversized responses, and unsafe URL access.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the samedaydesk-extract plugin — 2 skills, 1 MCP server shipped together

Good fit Use it to extract titles, descriptions, headings, links, JSON-LD, social metadata, or bounded page text from public websites.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/epistemedeus/x402-url-extractor/web-extract
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 epistemedeus/x402-url-extractor --skill web-extract
Clone the repo
git clone --depth 1 https://github.com/epistemedeus/x402-url-extractor

Made for: Claude Code.

Or install samedaydesk-extract, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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.

agentmods badge for web-extract

README.md
[![agentmods](https://agentmods.dev/badge/skills/epistemedeus/x402-url-extractor/web-extract/github.svg)](https://agentmods.dev/skills/epistemedeus/x402-url-extractor/web-extract)
Your own site
<a href="https://agentmods.dev/skills/epistemedeus/x402-url-extractor/web-extract"><img src="https://agentmods.dev/badge/skills/epistemedeus/x402-url-extractor/web-extract/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.

agentmods 80×15 button for web-extract

Your own site · 80×15
<a href="https://agentmods.dev/skills/epistemedeus/x402-url-extractor/web-extract"><img src="https://agentmods.dev/badge/skills/epistemedeus/x402-url-extractor/web-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,646 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.01646
Opus 5 $0.00043 $0.00823
Sonnet 5 $0.00017 $0.00329
Haiku 4.5 $0.00009 $0.00165

Measured today against content hash 8c9e0cff68a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

web-extract 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 today.

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.

plugins/samedaydesk-extract/skills/web-extract/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract public webpage(s)

This skill constructs one SameDayDesk extract request. It does not pay, sign, store credentials, or add a second price.

Exact inputs

Required (choose one shape):

  • Single page: url, one public https:// page.
  • Batch: urls, a caller-supplied list of 1–5 public https:// pages, plus explicit desired fields from the live schema enum.

Reject http:, file:, javascript:, URL credentials, authenticated apps, localhost, and private-network targets. Do not invent URLs or fields. If the caller did not give a usable URL list, stop and ask.

If the caller supplies more than five URLs, stop. Do not automatically split into multiple paid batch calls. Do not issue repeated charges to repair partial rows from a prior attempt.

Optional claimed source header, already set on the plugin MCP client:

  • X-SameDayDesk-Agent-Source: claude-code-marketplace-v1

That header is a declared source label only. It is not authentication, access, payment, payer class, organic acquisition, or independent-customer evidence. The merchant may bucket this exact allowlisted value as caller-declared attribution. Unknown labels are ignored.

Retention covers HTTP request records and observed direct MCP tool outcomes. MCP extract_batch retains source on its exact /extract/batch HTTP record only. Initialization and tools/list create no tool-outcome events. Request construction, seller response, settlement and independent demand remain separate.

Route selection

  1. Read live OpenAPI at https://agents.samedaydesk.com/openapi.json (and optionally unpaid MCP tools/list) before choosing a route. Use the current schema and terms, not remembered fields.
  2. For 2–5 public HTTPS URLs, or an explicitly requested one-item batch, require caller-supplied desired fields. When live discovery shows POST /extract/batch (HTTP) or MCP extract_batch with matching input/output schemas, construct one bounded batch request.
  3. For exactly one URL, including a request for particular fields, use GET https://agents.samedaydesk.com/extract?url=<url-encoded-https-url> or MCP extract with the same url, unless the caller explicitly wants batch. If live batch is unsupported, retain GET for a single page. For multiple URLs stop and ask for a smaller scope; do not silently fan out paid GETs.
  4. MCP credential scopes and HTTP @x402/fetch scopes stay distinct. This plugin does not become payment-capable by documentation alone.

Read the full file on GitHub · 145 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. today Changed · +47 lines · +8 tokens per session 8c9e0cff68a8
  2. yesterday Changed · +73 lines · +6 tokens per session 098e9f1ded73
  3. 8d ago First seen · 25 lines · 72 tokens per session scan A 594a745ae744

Subscribe to this mod's changes

web-extract is a skill published in the GitHub repository epistemedeus/x402-url-extractor (1 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,646 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

x402

Monetize any user project/service with the x402 payment protocol on platform networks (Base + Monad + Robinhood + X Layer + Solana; Starchild platform billing: payperuse / lifetime / weekly / monthly / quarterly / yearly / prepaid, plus multi-plan services), limited-time free promotions (amount-0 verify, no…

Starchild-ai-agent/official-skills · 125 tokens

bankr-shopify

Shopify Admin & Storefront GraphQL APIs via curl, with Bankr-native bridges. Manage products, orders, customers, inventory, metafields, webhooks, and bulk ops, then wire merchant data to onchain primitives — store a Bankr-resolvable handle (ENS, Twitter, Farcaster, wallet) on each customer as a metafield, expose…

BankrBot/skills · 163 tokens

scvd-general-store

A live x402 practice counter: real settlement, no sandbox, from $0.001. Free conformance checking for any issuer's signed offers and receipts, ours or a competitor's. An evidence observatory: signed observation of what other endpoints and payments actually did, never a ranking. Reachable six ways, including browser…

seancrecord/scvd-general-store-repo · 79 tokens

x402-before-you-pay

Before an agent pays an x402 endpoint, read its 402 terms and run scvd.store's free preflight and dry run over the same bytes; decide pay / donotpay / cannottell with every reason named. Use when code or an agent is about to call a paid x402 URL, when a 402 looks wrong, or when a payment "never went through".…

seancrecord/scvd-general-store-repo · 90 tokens

agent-payment-stats

Cross-protocol agent-economy payment metrics from Barker's index. x402 (Base) volume is on-chain verifiable; ACP / AP2 / MPP / AP4M figures are self-reported claims. Separates real vs nominal volume by filtering wash/noise sellers. Use when users ask about x402 volume, agent payment stats, agent economy metrics, or…

barkermoney/barker-mcp · 134 tokens

alien-plugg-x402

38 paid x402 API endpoints for AI agents — Zora crypto analysis, Robinhood Chain tokenized stocks, on-chain intelligence, whale tracking, and utilities. MCP-compatible. Flat $0.003/call via USDC micropayments on Base.

michaelhutchings626-hub/alien-plugg-x402 · 57 tokens