# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# robots.txt for intercognito.com

# Where your sitemap will live (add if/when you generate it)
Sitemap: https://intercognito.com/sitemap.xml

# Default policy: allow everything except sensitive/internal paths.
User-agent: *
Allow: /
Disallow: /forms/
Disallow: /includes/
Disallow: /config/
Disallow: /vendor/
Disallow: /node_modules/
Disallow: /tmp/
Disallow: /private/
Disallow: /cgi-bin/

# Make sure assets are crawlable for proper rendering/indexing
Allow: /assets/css/
Allow: /assets/js/
Allow: /assets/img/
Allow: /assets/fonts/

# (Optional) be nice to smaller engines/crawlers
Crawl-delay: 5

# --- Explicit ALLOW for major search engines ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

# --- Explicit ALLOW for reputable AI/web crawlers ---
# OpenAI
User-agent: GPTBot
Allow: /

# ChatGPT browsing UA (used in some integrations)
User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Common Crawl (feeds many AI datasets)
User-agent: CCBot
Allow: /

# --- Politely DISALLOW common scrapers/scanners (best-effort; many ignore robots.txt) ---
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: DotBot
Disallow: /

# Generic tooling & libraries often used by scrapers/scanners
User-agent: Wget
Disallow: /
User-agent: curl
Disallow: /
User-agent: python-requests
Disallow: /
User-agent: Go-http-client
Disallow: /
User-agent: libwww-perl
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: httpx
Disallow: /
User-agent: Java
Disallow: /

# Security scanners / vulnerability tools (will usually ignore robots.txt)
User-agent: sqlmap
Disallow: /
User-agent: Nikto
Disallow: /
User-agent: Nmap Scripting Engine
Disallow: /