LLMs TXT Check

llms.txt and AI crawler access check

A read-only check of two files: /llms.txt and /robots.txt. It reports problems and does not write or change anything.

When to use

• "Do I have a valid llms.txt?", "is my site blocking ChatGPT / Claude / Perplexity?", "can AI crawlers read my site?"

How to run

python3 scripts/llms_check.py example.com
python3 scripts/llms_check.py https://docs.example.com --max-links 40

Needs outbound HTTPS. Makes about 25 requests at most (it checks up to --max-links links from llms.txt, with a short pause between them).

What it checks

• /llms.txt returns 200 and is text, not an HTML soft-404 page.
• Format per llmstxt.org: one # H1, a > summary, ## sections, Markdown links.
• Size under ~50 KB, so an agent can load it.
• Up to N links resolve (HEAD, falling back to GET).
• /llms-full.txt presence (optional).
• robots.txt access to / for GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended and CCBot.

Read the result honestly

AI search crawlers rarely fetch llms.txt today; coding agents and IDE assistants do. For appearing in AI answers, robots.txt access and server-rendered content matter more. Say this to the user rather than overselling llms.txt.

Example

python3 scripts/llms_check.py plausible.io → llms.txt missing (404), all 8 AI crawlers allowed, sitemap declared → "Publish /llms.txt" as the only fix.

Want the files written for you?

• Paid skill that writes a starter llms.txt, audits robots.txt for AI bots and ships a fix checklist: Ship llms.txt + Unlock AI Crawlers on Agensi
• Hosted multi-page check: AEO & GEO Readiness Checker on Apify