# Content Signals declaration (contentsignals.org). Search indexing is welcome, AI training is
# not. Cloudflare's "Managed robots.txt" used to inject this at the edge, which meant it bypassed
# the origin entirely — it now lives here so it is version-controlled and editable:
User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Disallow: /kinkyadmin/
Disallow: /api/

# Auth pages carry <meta name="robots" content="noindex"> — they must stay CRAWLABLE
# so Google can read that tag and drop them. Disallowing here would hide the noindex
# and cause the URLs to be indexed link-only (the bug this replaced).

# Block parameterised URL variants that waste crawl budget
Disallow: /*?tags=all
Disallow: /*?media=

# POST-only form endpoints — crawlers GET the form action and eat a 405, wasting budget:
Disallow: /report/submit/
Disallow: /games/*/suggest/

# Block AI training crawlers (scrape for datasets, send no traffic back):
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Amazonbot
Disallow: /

# Block SEO / backlink crawlers (index us for their own tools, send no traffic back):
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalBot
Disallow: /

# AI search crawlers (OAI-SearchBot, PerplexityBot) are allowed by default
# as they link back to the site from AI search results.

Sitemap: https://kinkygames.io/sitemap.xml