# Content-Signal (contentsignals.org / draft-romm-aipref-contentsignals)
# We welcome AI search, answering, and agentic use of our content, but we do
# not consent to the content being used to train LLMs without explicit
# written permission.
Content-Signal: ai-train=no, search=yes, ai-input=yes

# One group for all crawlers. Note: robots.txt groups do NOT merge — a
# bot-specific group (e.g. "User-agent: Googlebot") would REPLACE this
# entire group for that bot, so we deliberately keep a single group.
# /_astro/ (CSS/JS/fingerprinted assets) must stay crawlable so pages
# render correctly for indexing.
# Removed URLs (old template pages, lorem posts, renamed slugs) are handled
# by 301s/404s so they age out of indexes naturally — do not Disallow them.
# Pagination (/blog/2/ ...) is handled via noindex meta, not robots blocks,
# so crawlers can actually see the noindex.
User-agent: *
Allow: /
Allow: /.well-known/
Disallow: /admin/
Disallow: /cdn-cgi/

# Let crawlers fetch tracking-parameter variants so they can read the
# self-referencing canonical in the HTML and consolidate them with the clean URL.

Sitemap: https://webdecoy.com/sitemap-index.xml