defuddle

defuddle is a skill for Claude Code, Codex from guanyang/open-agent-hub. It costs 74 tokens per session (277 once invoked), scanned A, a copy of defuddle, MIT.

A command-line tool and usage guide for extracting the readable content from ordinary web pages as clean Markdown. It removes page clutter such as navigation and advertisements.

In plain words
What is it for?
Use it to read online documentation, articles, blog posts, and other standard web pages. It is not intended for pages that already end in .md.
Why use it?
Raw web pages contain extra markup and unrelated content that use up the agent's attention. Clean extraction makes documentation and articles easier to read and analyze.

Skill for Claude CodeCodex

Part of the open-agent-hub plugin — 102 skills, 3 commands, 8 agents, 6 MCP servers shipped together

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/guanyang/open-agent-hub/defuddle
Any agent
npx skills add guanyang/open-agent-hub --skill defuddle
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub

Made for: Claude Code, Codex.

Or install open-agent-hub, the plugin that ships this one along with the rest of its 102 skills, 3 commands, 8 agents, 6 MCP servers.

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 defuddle

README.md
[![agentmods](https://agentmods.dev/badge/skills/guanyang/open-agent-hub/defuddle.svg)](https://agentmods.dev/skills/guanyang/open-agent-hub/defuddle)
Your own site
<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/defuddle"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/defuddle.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00074 $0.00277
Opus 5 $0.00037 $0.00138
Sonnet 5 $0.00015 $0.00055
Haiku 4.5 $0.00007 $0.00028

Measured 6d ago against content hash 10673a4dc70a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

defuddle 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 6d 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.

Origin

This is a copy

100% identical to defuddle — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/defuddle/SKILL.md · 42 lines

What it actually says

Defuddle

Use Defuddle CLI to extract clean readable content from web pages. Prefer over WebFetch for standard web pages — it removes navigation, ads, and clutter, reducing token usage.

If not installed: npm install -g defuddle

Usage

Always use --md for markdown output:

defuddle parse <url> --md

Save to file:

defuddle parse <url> --md -o content.md

Extract specific metadata:

defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain

Output formats

Flag Format
--md Markdown (default choice)
--json JSON with both HTML and markdown
(none) HTML
-p <name> Specific metadata property
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. 6d ago First seen · 42 lines · 74 tokens per session scan A 10673a4dc70a

Subscribe to this mod's changes

defuddle is a skill published in the GitHub repository guanyang/open-agent-hub (960 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 277 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to defuddle, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

agent-browser

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing…

majiayu000/claude-skill-registry · 105 tokens

agent-canvas

Interactive element picker for web pages. Opens a browser with click-to-select UI overlay. Use when you need to let users visually select DOM elements, identify element selectors, or get detailed element information interactively. Triggers on "select an element", "pick element", "let me choose", "which element", or…

majiayu000/claude-skill-registry · 83 tokens

agent-eyes

Visual context analyzer for AI agents. Provides screenshots, accessibility scans, DOM snapshots, and element descriptions for web pages. Use when you need to see what a web page looks like, analyze accessibility issues, inspect DOM structure, or get detailed element information. Triggers on requests like "take a…

majiayu000/claude-skill-registry · 94 tokens

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

majiayu000/claude-skill-registry · 108 tokens

agent-browser

ブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log…

majiayu000/claude-skill-registry · 120 tokens

agent-browser

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape…

majiayu000/claude-skill-registry · 77 tokens