# Reviewed 2026-08
# /blog/_content/ holds the Markdown the blog pages are generated from. It
# sits under the docroot, so Caddy will serve it; disallowing it keeps the
# same article from being indexed twice, once as HTML and once as source.
# Bots match on the single most specific User-agent block; there is no
# fallback to "*" once a name matches, so /success and /api/ are repeated
# in every Allow-listed block rather than left to the wildcard alone.
# /api/classify, /api/checkout and /api/packs/ are re-opened per-bot below
# via a longest-match Allow line (RFC 9309: the most specific rule for a
# path wins), so agents can evaluate (classify), buy (checkout) and
# retrieve (packs) the product without opening the rest of /api/.
# /api/packs/{token} is guarded by an unguessable token and returns 402
# until paid — robots.txt is not the access control there, the token is.
# Allow: /api/checkout is a bare string-prefix match (RFC 9309 has no
# path-segment anchoring), so it would also collaterally allow
# /api/checkout/upgrade and /api/checkout/resume — the latter carries a
# live order token in its query string. Disallow: /api/checkout/ is one
# character longer, so it wins the longest-match tie-break and re-closes
# just the subpaths, leaving the literal POST /api/checkout endpoint open.

User-agent: *
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/

# --- AI search / answer agents: allowed to fetch-and-cite ---
User-agent: OAI-SearchBot
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: ChatGPT-User
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: Claude-SearchBot
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: Claude-User
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: PerplexityBot
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: Perplexity-User
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: DuckAssistBot
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/
User-agent: Applebot
Allow: /
Disallow: /success
Disallow: /api/
Allow: /api/classify
Allow: /api/checkout
Disallow: /api/checkout/
Allow: /api/packs/
Disallow: /blog/_content/

# --- AI training / bulk-scraping crawlers: disallowed entirely ---
User-agent: GPTBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: img2dataset
Disallow: /

Sitemap: https://klariq.eu/sitemap.xml