# robots.txt for jlegal.pro
# Site owner explicitly permits all crawlers including AI systems

# Default rules for all crawlers
User-agent: *
Allow: /
Allow: /evidence-photos/
Allow: /*.html
Allow: /*.pdf
Allow: /temp-graph-data.json
Allow: /llms.txt
Allow: /agents.md
# Analytics tracking pixel — do not crawl or index the tracker.
# track.jlegal.pro is a separate noindex analytics subdomain; its own
# robots.txt governs its crawling. These rules cover any tracker path
# referenced from this host (the tracking pixel / beacon).
Disallow: /t.gif
Disallow: /track
Disallow: /tracker

# AI Crawlers — explicitly permitted
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

# Tracking subdomain (documentation)
# track.jlegal.pro is a noindex analytics subdomain used only for the
# on-page tracking pixel. It is not part of the public content site and
# should not be indexed or surfaced in search results. robots.txt is
# per-host, so track.jlegal.pro's own robots.txt disallows crawling there;
# this note documents the intent from the primary host.

# Sitemap (XML only — standard for Google/Bing)
Sitemap: https://jlegal.pro/sitemap.xml

# AI / machine-readable discovery (not XML sitemaps)
# LLM summary:     https://jlegal.pro/llms.txt
# Agent briefing:  https://jlegal.pro/agents.md
# Structured JSON: https://jlegal.pro/ai-agents.json
# Meta-dossier:    https://jlegal.pro/docs-meta/  (build handbook, strategy assessment, master timeline)