# ═══════════════════════════════════════════════════════════════
# Ghost in the Codex — robots.txt (Faro Configuration)
# Updated: 2026-06-27
# ═══════════════════════════════════════════════════════════════

# ── Section 1: Block Training Crawlers ──
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

# ── Section 2: Allow AI Search / RAG Indexers ──
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /
Crawl-delay: 2

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

# ── Section 3: Allow Traditional Search Engines ──
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

User-agent: Applebot
Allow: /
Crawl-delay: 1

User-agent: YandexBot
Allow: /
Crawl-delay: 1

User-agent: Baiduspider
Allow: /
Crawl-delay: 1

# ── Section 4: Allow Social / Reference Previews ──
User-agent: facebookexternalhit
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Google-NotebookLM
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: OAI-AdsBot
Allow: /

User-agent: Copilot
Allow: /

# ── Section 5: Catch-all — Block everything else ──
User-agent: *
Disallow: /

# ── llms-full.txt — single-file RAG corpus, all crawlers welcome ──
User-agent: *
Allow: /llms-full.txt

Sitemap: https://ghostinthecodex.com/sitemap.xml
Sitemap: https://ghostinthecodex.com/sitemap_index.xml