# https://www.robotstxt.org/robotstxt.html
User-agent: *
# Private / authenticated areas — no value to crawlers and may soft-404
Disallow: /admin
Disallow: /account
Disallow: /accounts
Disallow: /billing
Disallow: /users/settings
Disallow: /checkout
Disallow: /cart
Disallow: /login
Disallow: /register
Disallow: /reset-password
# Monitoring probes — /health/ready does a DB round trip per request
Disallow: /health
# Public machine-readable price catalog — aggregator + LLM ingestion (#423).
# Allow precedes the broad /api/ disallow so order-sensitive crawlers honor it
# (Google/Bing use longest-match regardless). Keeps the per-query EPP-backed
# /api/v1/domains/* endpoints blocked.
Allow: /api/v1/pricing
Allow: /api/v1/pricing.csv
# The OpenAPI spec and its SwaggerUI explorer, for API directories and search consoles
Allow: /api/v1/openapi
Allow: /api/v1/docs
Disallow: /api/
# Search-result query URLs — thin/duplicate; the /tld/* pages are the indexable equivalent
Disallow: /*?q=
# Everything else. Last, so a first-match crawler reads every Disallow above before it
Allow: /

Sitemap: https://www.orbitfour.com/sitemap.xml

# Agent/LLM entry point for the REST API (#553) — the llms.txt convention has no
# robots directive of its own, so advertise it as a comment for crawlers that read
# robots.txt first.
# LLM-Guide: https://www.orbitfour.com/llms.txt