# Markdown Twin

> A clean markdown version of an HTML page, served from the same URL via content negotiation when a client requests text/markdown.

_The Agentic Web Lexicon · /glossary/markdown-twin · [JSON](/api/glossary/markdown-twin) · [all The Agentic Web Lexicon](/glossary)_

- **term:** Markdown Twin
- **category:** protocols
- **short_def:** A clean markdown version of an HTML page, served from the same URL via content negotiation when a client requests text/markdown.
- **long_def:** Markdown carries the meaning of a page in roughly a tenth of the tokens of the equivalent HTML. Agent fetchers (Claude Code's WebFetch, Cursor, Cloudflare's edge) request it with an Accept: text/markdown header; humans still get the styled HTML.
- **see_also:** content-negotiation, llms-txt, token-economics
- **etymology_origin:** — (verify-against-primary-at-build)
- **related_to:** content-negotiation, llms-txt, token-economics, rag
- **contrast_with:** Unlike a separate /page.md URL, a markdown twin lives at the SAME URL as the HTML and is selected by the Accept header via content negotiation — one canonical URL, two representations.
- **example:** Claude Code's WebFetch and Cursor request the markdown representation with an Accept: text/markdown header, receiving roughly a tenth of the tokens of the HTML.
- **source:** https://datatracker.ietf.org/doc/html/rfc7763
- **status:** emerging
- **why_it_matters:** The markdown twin is the canonical way to serve agents a cheap, clean, low-token version of a page without maintaining a duplicate site.
- **sameAs:** —
- **bridge_entity:** agent-readiness
- **last_verified:** 2026-06-15
- **md_twin:** /glossary/markdown-twin.md