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.
npx skills add ericgandrade/claude-superskills --skill webpage-readergit clone --depth 1 https://github.com/ericgandrade/claude-superskillsWrote 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.
[](https://agentmods.dev/skills/ericgandrade/claude-superskills/webpage-reader)<a href="https://agentmods.dev/skills/ericgandrade/claude-superskills/webpage-reader"><img src="https://agentmods.dev/badge/skills/ericgandrade/claude-superskills/webpage-reader/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.
<a href="https://agentmods.dev/skills/ericgandrade/claude-superskills/webpage-reader"><img src="https://agentmods.dev/badge/skills/ericgandrade/claude-superskills/webpage-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.02742 |
| Opus 5.5 | $0.00030 | $0.01097 |
| Sonnet 5.5 | $0.00015 | $0.00548 |
| Haiku 4.5 | $0.00008 | $0.00274 |
Grade A, and why
webpage-reader 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
This skill extracts clean, readable Markdown from any web page URL by stripping navigation menus, advertisements, sidebars, footers, cookie banners, and all other non-content elements. It produces token-efficient output that focuses exclusively on the meaningful content of the page.
When agents fetch web pages using standard tools, the raw output often includes hundreds of navigation links, promotional widgets, and boilerplate text that consume tokens without adding value. This skill eliminates that noise using Defuddle, a purpose-built content extraction tool, to isolate the article body, documentation text, or main content and return only what matters.
The skill gracefully degrades when Defuddle is not installed: it offers to install it automatically or falls back to standard web fetching with a clear note about the trade-off in output quality and token usage.
This is a universal skill — it works in any project, any terminal context, and does not require Obsidian or any specific project structure.
When to Use
Invoke this skill when:
- The user provides a URL and asks to "read", "fetch", "extract", or "get the content" of a page
- The user wants to analyze online documentation, API references, or technical guides
- The user shares a blog post, article, or research paper URL and needs the body content
- The user wants to save web content to a local Markdown file for offline reference or notes
- The agent needs to reference external content during a research or writing workflow
- The user asks to clean up or strip the noise from a page before reading it
- Multiple URLs are provided for batch processing in a research session
Do NOT use this skill when:
- The URL ends in
.md— those files are already Markdown, use WebFetch directly instead - The URL points to a PDF, DOCX, PPTX, or binary file — use
docling-converterinstead - The user needs a multi-source research synthesis with citations — use
deep-researchinstead - The user needs to interact with the page (forms, logins, JavaScript-heavy apps)
- The URL requires authentication that the agent cannot provide
- The user asks to summarize a YouTube video — use
youtube-summarizerinstead
What ships with it
3 files 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.
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.
- 1mo ago First seen · 268 lines · 76 tokens per session scan A 9ec95783cbb9
webpage-reader is a skill published in the GitHub repository ericgandrade/claude-superskills (85 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 2,742 once invoked, about $0.0003 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.
Other skills, from other repositories
webapp-selenium-testing
Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing screenshots, or setting up Maven test projects. Supports Chrome, Firefox, and Edge. Keywords: Selenium WebDriver, Java…
playwright-cli
Drive a live browser from the CLI with playwright-cli to navigate, interact, snapshot, and capture evidence. Use for ad-hoc browser commands, page inspection, screenshots, traces, network mocking, session management, or interactive debugging—not authoring @playwright/test specs. Keywords: playwright-cli, browser…
agent-e2e-test-specialist
Specialist subagent: Playwright, Cypress, and visual regression testing specialist. Use only when the user explicitly asks for E2E tests, browser test automation, or visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
agent-browser-extension-developer
Specialist subagent: Chrome, Firefox, and cross-browser extension development specialist. Manifest V3, service workers, content scripts, and WebExtension APIs. Use when building browser extensions or migrating from MV2 to MV3. Trigger phrases: browser extension, Chrome extension, Firefox addon, Manifest V3, MV3…
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
api-design
REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…