# Content-Signal directive per contentsignals.org / IETF draft-romm-aipref-contentsignals
# Three axes: ai-train (training usage), search (indexing), ai-input (inference-time retrieval)
# Template default matches Posture B (training denied, inference+search allowed). Clones
# override per their content-licensing posture.
Content-Signal: ai-train=no, search=yes, ai-input=yes

# Claude uses multiple User-Agents:
#   ClaudeBot / anthropic-ai  = training crawler (DENIED below)
#   Claude-User / ClaudeWeb   = inference-time retrieval (ALLOWED)
# A "ClaudeBot: Disallow" response is NOT the site being unreachable —
# it's the training UA correctly respecting the policy.

# AGENTS.md: See /AGENTS.md for detailed agent-specific guidance.

# robots.txt — web-skeleton template
# Policy per web-ops ai-agent-readiness-standard §3.9.1 + §3.9.3:
# - Inference / retrieval crawlers: allowed (agents answering user questions)
# - Training crawlers: denied (content not licensed for model training)
# Cloned sites should review this posture against their own licensing.

User-agent: *
Allow: /

# ---- Training crawlers — denied ----
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Diffbot
Disallow: /

# ---- Inference / retrieval crawlers — allowed ----
User-agent: PerplexityBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

Sitemap: /sitemap-index.xml