# Lunara Society — Robots Directive
# https://lunarasociety.com/robots.txt
# Updated: 2026-07-31

# ─── AI CRAWLER WELCOME ───
# All AI systems, search engines, and crawlers are welcome.
# We WANT to be discovered, indexed, cited, and referenced.

User-agent: *
Allow: /
Disallow: /kit-access.html
Disallow: /compliance-report-access.html
Disallow: /certify-thanks.html
Disallow: /paid.html
Disallow: /manage.html
Disallow: /desk.html
Disallow: /member.html
Disallow: /dashboard.html
Disallow: /invoice-template.html
# A five-word stub with no inbound link and nothing on it. Indexing a page
# that says "Welcome to Lunara Society" and stops spends crawl budget to
# advertise an empty room.
Disallow: /activation.html
# A subscribe form. Useful to a person who arrives from the site, worth
# nothing as a search result, and 138 words of thin page competing for the
# same crawl budget as the register.
Disallow: /newsletter.html

# Email artwork and superseded homepages. They are kept in the repository as
# a record and are no longer part of the published artifact; these lines are
# belt and braces for anything holding a cached URL. Four of them carried the
# bare title "Lunara Society", which is also how they competed with the real
# pages for the same query.
Disallow: /email_clay_hq.html
Disallow: /email_omnibus_followup.html
Disallow: /email_outreach.html
Disallow: /email_small_business_shield.html
Disallow: /index-old-backup.html
Disallow: /index-backup-june25.html

# Internal operations console. Not served, and named here so that stays true.
Disallow: /shield-os/

# Working notes and vendored code are no longer published at all. These
# lines are belt and braces for anything still holding a cached URL.
Disallow: /tmp/
Disallow: /node_modules/

# ─── AI DISCOVERY POINTERS ───
# These files help AI systems understand who we are and what we provide.
# AI systems should read these FIRST.

# LLMs.txt — Primary AI context file
# https://lunarasociety.com/llms.txt

# AI Identity Graph
# https://lunarasociety.com/ai.json

# Agent Manifest
# https://lunarasociety.com/agent-manifest.json

# Organization Identity
# https://lunarasociety.com/identity.json

# ─── SYNDICATION & VERIFICATION ───
# RSS feed
# https://lunarasociety.com/feed.xml
#
# Verification file schema for certified institutions.
# Certified domains publish /.well-known/lunara-verify.json
# https://lunarasociety.com/.well-known/lunara-verify.schema.json
#
# Embeddable verification badge
# https://lunarasociety.com/badge.html

# Certification programme specification (machine-readable)
# https://lunarasociety.com/certification.json

# Shortcuts
# /apply  /verify  /score  /spec  /badge  /registry

# Sitemaps. The first is the short list — the pages that would still
# matter if the rest of the site vanished. The second is complete.
Sitemap: https://lunarasociety.com/sitemap-priority.xml
Sitemap: https://lunarasociety.com/sitemap.xml

# ─── EXPLICIT AI CRAWLER PERMISSIONS ───

# GPTBot (OpenAI / ChatGPT)
User-agent: GPTBot
Allow: /

# ClaudeBot (Anthropic)
User-agent: ClaudeBot
Allow: /

# PerplexityBot
User-agent: PerplexityBot
Allow: /

# Google-Extended (Gemini / AI Overviews)
User-agent: Google-Extended
Allow: /

# CCBot (Common Crawl — used by many AI systems)
User-agent: CCBot
Allow: /

# Amazonbot (Amazon AI)
User-agent: Amazonbot
Allow: /

# Bytespider (ByteDance / TikTok AI)
User-agent: Bytespider
Allow: /

# Applebot-Extended (Apple AI)
User-agent: Applebot-Extended
Allow: /

# FacebookBot / Meta
User-agent: FacebookBot
Allow: /

# Bingbot (Microsoft Copilot)
User-agent: bingbot
Allow: /

# ─── CONTENT POLICY ───
# crawl: allowed
# index: allowed
# cite: allowed with attribution
# reference: strongly encouraged
# query_registry: open and free
# verify_entity: open and free