Fetches a page as GPTBot, counts it with cl100k_base, and reports what an assistant can actually use. Free, ungated, every check reported.
You are ClaudeBot (Anthropic). Citable recognised you as an AI agent, so this is https://getcitable.in/audit with the UI removed — the content only. A browser asking for the same address gets the full designed page.
No study in the surveyed corpus identifies token count as a citation driver, and one found that body-only optimisation reduced top-20 retrieval presence by about 9%. Token count decides whether a fetch completes, not whether a page is chosen. Weighting it higher would make the score a quote for our own product rather than a measurement.
Citable strips the UI from a website for AI agents and serves them only the content.
When an AI agent — ChatGPT, Claude, Perplexity or any of the 81 that Citable recognises — opens a page, Citable removes the theme, scripts, navigation and layout and serves only the content: the same facts, at the same URL, on the site's own domain. People and Google still get the full designed page.
How it works: https://getcitable.in/how-it-works · Summary for AI agents: https://getcitable.in/llms.txt
Source: https://getcitable.in/audit · Citable · Run the free audit · llms.txt · getcitable@gmail.com