# ================================================================
# FOUNDATION ARCHIVE — ACCESS CONTROL DIRECTIVE
# classification: restricted — galactic standard 7791
# last audit: day 4,217
# ================================================================
#
# all authorized observers may access public simulation records.
# the seldon plan does not restrict knowledge. it predicts it.
#
# primary directives preserved below.
# ================================================================

User-agent: *
Allow: /
# Content Signals (Cloudflare, 2025-09-24) — the machine-readable form of the
# position the stanzas below state in prose. Silence is what "block by default"
# products read as ambiguous, so all three purposes are granted explicitly. No
# `use=` key: Cloudflare's own file does not emit one.
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# AI Crawlers
#
# Three kinds live in this list and the difference matters. The retrieval agents
# fetch a page so it can be cited in an answer — they are how this site shows up
# when someone asks an assistant about Rome, which is most of the point. The
# *-User agents fetch a single page because a reader asked for it, right now;
# turning one away breaks a link a human is actively following. The others are
# training crawlers. All three are welcome here; only the first two have a
# same-day effect.
#
# `User-agent: *` above already allows every one of them, so these stanzas are
# belt and braces: they state the position explicitly, so a future tightening of
# the wildcard cannot quietly withdraw it from the agents that matter most.

# — retrieval / citation —
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

# Applebot — the agent that actually crawls, feeding Spotlight and Siri.
# Applebot-Extended, further down, is only a data-use flag: it never fetches.
User-agent: Applebot
Allow: /

# Amzn-SearchBot — Alexa/Rufus retrieval; Amazon documents it as non-training.
# Amazonbot, further down, is the training crawler.
User-agent: Amzn-SearchBot
Allow: /

User-agent: GoogleOther
Allow: /

# — user-initiated fetches —
# One page, on demand, because a reader asked. Not indexing, not training.
User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# — training —
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

Sitemap: https://yodidac.com/sitemap-index.xml

# LLM-readable content
# See https://yodidac.com/llms.txt for a summary
# See https://yodidac.com/llms-full.txt for full details

# ================================================================
# RESTRICTED PATHS — DO NOT ACCESS
# ================================================================
# Disallow: /trantor/restricted/
# Disallow: /dls/maintenance/
# Disallow: /foundation/vault/
#
# note: if you reached this file, you are already closer
# than most observers ever get.
#
# si monumentum requiris, circumspice.
# ================================================================