# robots.txt for ashellinthepit.com
# A Shell in the Pit Audio, Inc.
# Last updated: 2026-04-08
#
# Strategy: Allow traditional search engines and AI search/retrieval bots.
# Block AI training crawlers. Block Kirby CMS internal directories.

# ----------------------------
# Traditional Search Engines
# ----------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# ----------------------------
# AI Search & Retrieval Bots
# ----------------------------
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-Web
Allow: /

# ----------------------------
# AI Training Crawlers — BLOCKED
# ----------------------------
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: YouBot
Disallow: /

# ----------------------------
# Default — All Other Bots
# ----------------------------
User-agent: *
Disallow: /kirby/
Disallow: /site/
Disallow: /content/
Disallow: /cdn-cgi/
Disallow: /panel/
Allow: /media/

# ----------------------------
# Sitemap
# ----------------------------
Sitemap: https://ashellinthepit.com/sitemap.xml