1---
2name: defuddle
3description: Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
4---
5 
6# Defuddle
7 
8Use 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.
9 
10If not installed: `npm install -g defuddle`
11 
12## Usage
13 
14Always use `--md` for markdown output:
15 
16```bash
17defuddle parse <url> --md
18```
19 
20Save to file:
21 
22```bash
23defuddle parse <url> --md -o content.md
24```
25 
26Extract specific metadata:
27 
28```bash
29defuddle parse <url> -p title
30defuddle parse <url> -p description
31defuddle parse <url> -p domain
32```
33 
34## Output formats
35 
36| Flag | Format |
37|------|--------|
38| `--md` | Markdown (default choice) |
39| `--json` | JSON with both HTML and markdown |
40| (none) | HTML |
41| `-p <name>` | Specific metadata property |
42