# rote™ by modiqo — full agent / crawler access.
# We want LLMs and AI search to discover, cite, and link to our content.
#
# IMPORTANT FOR AGENTS: .md URLs are intentionally not published because this
# host serves unknown markdown extensions as application/octet-stream. Every
# machine-readable page is available as a .txt mirror instead. The llms.txt /
# llms-full.txt indexes only reference .txt URLs. We Disallow .md below so
# well-behaved crawlers do not waste budget on unsupported legacy paths.

# ── Search engines ─────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Disallow: /*.md$

User-agent: Googlebot-Image
Allow: /
Disallow: /*.md$

User-agent: Bingbot
Allow: /
Disallow: /*.md$

User-agent: DuckDuckBot
Allow: /
Disallow: /*.md$

User-agent: Applebot
Allow: /
Disallow: /*.md$

User-agent: Slurp
Allow: /
Disallow: /*.md$

User-agent: YandexBot
Allow: /
Disallow: /*.md$

User-agent: Baiduspider
Allow: /
Disallow: /*.md$

# ── Social previews ────────────────────────────────────────────
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: Discordbot
Allow: /

User-agent: TelegramBot
Allow: /

# ── AI / LLM crawlers (training + retrieval + answer engines) ──
User-agent: GPTBot
Allow: /
Disallow: /*.md$

User-agent: ChatGPT-User
Allow: /
Disallow: /*.md$

User-agent: OAI-SearchBot
Allow: /
Disallow: /*.md$

User-agent: ClaudeBot
Allow: /
Disallow: /*.md$

User-agent: Claude-Web
Allow: /
Disallow: /*.md$

User-agent: anthropic-ai
Allow: /
Disallow: /*.md$

User-agent: PerplexityBot
Allow: /
Disallow: /*.md$

User-agent: Perplexity-User
Allow: /
Disallow: /*.md$

User-agent: Google-Extended
Allow: /
Disallow: /*.md$

User-agent: Applebot-Extended
Allow: /
Disallow: /*.md$

User-agent: Amazonbot
Allow: /
Disallow: /*.md$

User-agent: Bytespider
Allow: /
Disallow: /*.md$

User-agent: CCBot
Allow: /
Disallow: /*.md$

User-agent: cohere-ai
Allow: /
Disallow: /*.md$

User-agent: Meta-ExternalAgent
Allow: /
Disallow: /*.md$

User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /*.md$

User-agent: YouBot
Allow: /
Disallow: /*.md$

User-agent: Diffbot
Allow: /
Disallow: /*.md$

User-agent: DuckAssistBot
Allow: /
Disallow: /*.md$

User-agent: MistralAI-User
Allow: /
Disallow: /*.md$

# ── Default: allow everything except .md ───────────────────────
User-agent: *
Allow: /
Disallow: /*.md$

# Sitemap + LLM indexes
# `Sitemap:` is the standard directive (RFC-ish, supported by all major crawlers).
# `LLMs:` and `LLM-Full:` are non-standard hints from the llmstxt.org convention —
# tolerated by parsers that ignore unknown directives, useful for AI-aware crawlers
# that look for them.
Sitemap: https://www.modiqo.ai/sitemap.xml
LLMs: https://www.modiqo.ai/llms.txt
LLM-Full: https://www.modiqo.ai/llms-full.txt