{ "markdown": "# readdown — Claude Code Plugin\n\nFetch web pages and convert HTML to clean, LLM-optimized Markdown directly in Claude Code.\n\n## What it does\n\n- **Fetch any URL** and get clean Markdown with article content extracted\n- **Convert HTML** strings to Markdown\n- **Token estimation** — know how much context window a page will use\n- **Metadata extraction** — title, author, date\n- Strips navigation, ads, sidebars, and boilerplate automatically\n\n## Install\n\nIn Claude Code, run:\n\n```\n/install-plugin https://github.com/zcag/readdown-plugin\n```\n\nOr add manually to your Claude Code settings.\n\n## Usage\n\nOnce installed, Claude can fetch and convert web pages:\n\n> \"Fetch https://example.com and summarize it\"\n> \"Convert this HTML to markdown: ...\"\n> \"How many tokens is this article?\"\n\nThe plugin provides two MCP tools:\n\n- **fetch_markdown** — fetch a URL and convert to Markdown\n- **convert_html** — convert an HTML string to Markdown\n\n## How it works\n\nUses [readdown](https://github.com/zcag/readdown) — a single-library replacement for `@mozilla/readability` + `turndown`. Extracts article content and converts to clean Markdown optimized for LLMs.\n\n- No browser needed (uses linkedom, not Playwright/Puppeteer)\n- Fast (~3ms per article)\n- Small footprint (5KB core vs 65KB for readability+turndown)\n\n## License\n\nMIT\n", "bytes": 1318, "sha": "2801f83316be8ffc1afd3808e4bfbf98ac72d90c2c6a85969496c596314f9c77", "repo_slug": "zcag/readdown-plugin", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/plg_zcag_readdown_plugin_readdown_1158b859/readme" }