--- title: Site to Markdown url: "https://ops.modpack.egoeimi.org/modpack/site-to-markdown" creator: Modpack (built on trafilatura (Apache-2.0)) trust: Built by Modpack category: Research version: 1.4.0 (2026-09-28) price: $0.01 per first 10 pages; $0.01 per whole site; charged only when a run works payer: "you, from your Modpack balance ($5 starter credit, no card)" worked: Not enough data yet (a rate shows after 20 runs from 3 people in 30 days) runs_this_week: 0 needs: nothing to connect clients: Claude Code last_verified: 2026-09-28 license: Apache-2.0 add_to_claude: "https://ops.modpack.egoeimi.org/modpack/site-to-markdown/add (one link: opens Claude’s Add connector dialog, already filled in)" mcp_url: "https://mcp.modpack.egoeimi.org/mcp" indexed: "yes" --- # Site to Markdown Turn a docs site into clean Markdown with source links, ready for an AI to read. ## What it does Turn a docs site into clean Markdown with source links, ready for an AI to read. ## Runs and prices | Run | Price | Time | What it covers | | --- | --- | --- | --- | | First 10 pages | $0.01 | About 20 s | Converts up to 10 pages of a docs site to Markdown and estimates how many pages the site has, in under a minute. | | Whole site | $0.01 | | Converts up to 1,000 pages (200 by default), staying inside one section when asked, with include and exclude filters. | ## Facts - **Works with:** Claude Code - **You give it:** The docs site or page to start from, e.g. https://docs.example.com. A bare domain works too.; Pages to convert (the quick run reads at most 10).; Stay inside this path, e.g. /docs/. Default: the start page's first folder when it isn't the home page. - **You get:** result; site; index; pages; pages\_jsonl; crawl - **Needs:** Nothing to connect - **Time:** About 20 s for a first 10 pages - **Cost:** $0.01 per first 10 pages · $0.01 per whole site. You pay from your Modpack balance, only when a run works. - **Worked:** Not enough data yet (a rate shows after 20 runs from 3 people in 30 days) - **Median run:** 20 s in the last 30 days - **Limits:** Public pages only. Pages behind a login, paywall or consent wall that hides content aren't read. No browser runs, so JavaScript isn't executed. Pages that build their text in the browser come out empty or short; they're skipped and listed. robots.txt is honored for the ModpackBot crawler; disallowed pages are skipped and listed. The crawler makes at most 4 requests a second and stops at the page or time limit. Only the site's own pages are converted. Linked PDFs and other files are listed, not converted. The page count on the site is an estimate from the sitemap and the links the crawl saw. E-mail addresses in page text are replaced with "(email address removed)"; bylines and author names are dropped with the rest of the page chrome. Code blocks are kept exactly. site.md stops at 5 MB; every page is still in \`pages/\` and \`pages.jsonl\`. Tokens are estimated as words × 1.33; real counts depend on the model. - **Version:** v1.4.0 · Sep 28 · new versions pass the same checks first - **Last verified:** Sep 28 ## Evidence Checked by Modpack, not written by the creator. Each label is separate and dated. - Rebuilt from scratch: 2026-09-28 - Checks passed: 2026-09-28 ## Sample result (Your example (samples/quick.input.json) · first 10 pages) result: ```text { "schema": "modpack.result/v1", "pack": "modpack/site-to-markdown", "entrypoint": "quick", "status": "ok", "subject": "demo.modpack.egoeimi.org", "headline": "demo.modpack.egoeimi.org: 9 pages converted to Markdown, about 400 tokens", "summary": "Converted 9 pages of demo.modpack.egoeimi.org into Markdown with a source link on each: 301 words, about 400 tokens, small enough for one conversation. 6 code blocks kept their language and 1 table stayed a table. Skipped: 1 page couldn't be read. The quick run reads up to 10 pages; the site has about 10.", "stats": [ { "label": "pages converted", "value": "9" }, { "label": "words", "value": "301" }, { "label": "tokens (estimate)", "value": "400" }, { "label": "pages on the site (estimate)", "value": "10" } ], "table": { "title": "Pages, in reading order", "columns": [ { "key": "page", "label": "Page" }, { "key": "title", "label": "Title" }, { "key": "words", "label": "Words" } ], "rows": [ { "page": "/", "title": "Know when your jobs stop", "words": 20 }, { "page": "/docs/intro", "title": "Introduction", "words": 80 }, { "page": "/docs/install", "title": "Install", "words": 29 }, { "page": "/docs/configure", ``` ## Good for - Turn a public docs site into clean Markdown with a source link on every page, ready for an AI to read - Build an llms.txt-style index of a site, one line per page with its source - Refresh a docs snapshot for a coding agent after a release ## Not for - Pages behind a login or a paywall - Pages whose text is built by JavaScript in the browser (no browser runs) - Copying sites for republishing ## People ask **Does it keep code blocks and tables?** Yes. Code keeps its language and tables become Markdown tables. **Will it read pages that need JavaScript?** Not yet. It reads the HTML each page sends. **How big a site can it handle?** Up to 1,000 pages per run; the first run tells you how many pages the site has. ## What changed - v1.4.0 (2026-09-28): - v1.0.0 (2026-09-28): All versions: https://ops.modpack.egoeimi.org/modpack/site-to-markdown/versions.md ## Connect 1. Add it to Claude (about a minute): https://ops.modpack.egoeimi.org/modpack/site-to-markdown/add 2. Ask: “Use Modpack’s Site to Markdown pack” 3. Already connected? Just ask; Claude tells you the price and asks before the first run. Claude Code with an API key (a Claude subscription needs nothing): `claude mcp add --transport http --scope user modpack https://mcp.modpack.egoeimi.org/mcp && claude mcp login modpack` --- HTML page: https://ops.modpack.egoeimi.org/modpack/site-to-markdown · Catalog: https://ops.modpack.egoeimi.org/packs.md · About Modpack: https://ops.modpack.egoeimi.org/llms.txt