{"schema_version":"newruntime-reader-dossiers-v1","type":"reader_dossier","id":"reader:crawlcheck","slug":"crawlcheck","name":"CrawlCheck","kind":"seo","kind_label":"SEO & backlink crawlers","operator":{"name":"CrawlCheck (crawlcheck.io)","url":"https://crawlcheck.io/"},"docs_url":"https://crawlcheck.io/policy","robots_tokens":["CrawlCheck"],"purpose":"Free site audit that checks whether AI and search crawlers can read a site. The CrawlCheck/1.0 UA fetches machine files and control paths (robots.txt, sitemaps, llms.txt, API catalog); the homepage is additionally requested once under ~12 other crawler identities (GPTBot, ClaudeBot, Googlebot, etc.).","feeds":["monitoring"],"respects_robots":"documented_yes","robots_note":"Docs: 'User-agent: CrawlCheck' Disallow: / or 'CrawlCheck: none' opts out on next scan. CrawlCheck/1.0 requests are Web Bot Auth-signed; measurement probes under other crawlers' UAs are unsigned. No owned IP range (egress via Cloudflare).","verification":{"method":"none_published","url":null},"why_it_matters":{"text":"Someone ran an AI-crawlability audit on our domain; it also means some 'GPTBot/ClaudeBot' homepage hits may actually be CrawlCheck probes.","kind":"new_runtime_interpretation"},"confidence":"high","researched_at":"2026-10-23","sources":["https://crawlcheck.io/policy","https://crawlcheck.io/"],"icon_url":"https://newruntime.com/readers/icons/crawlcheck.png","matching":{"aliases":["crawlcheck"],"rule":"Reduce each agent_days label to a token: for labels starting with Mozilla/ take the product after 'compatible;', else a versioned crawler token such as 'FooBot/1.0' (a truncated 'Mozilla/5.0 (Linux; Android 7.0;) AppleWebKit/537.36 (KHTML, like Gecko) Mobile' prefix logged before 23 Oct 2026 is PetalBot; anything else is unidentified-android, unidentified-linux-chrome or unidentified-browser); otherwise take the text before the first '/', '(' or ';' and drop a trailing ' token probe'. Lowercase it. A dossier owns the tokens in its aliases."},"observed_baseline":{"as_of":"2026-10-23T08:01:01.990Z","window_first_day":"2026-07-23","window_last_day":"2026-10-23","observed_days":93,"note":"Refreshed daily in production from the live aggregates (dated by as_of). For current numbers aggregate live_sources.history agent_days by matching.aliases.","total_requests":12,"first_seen":"2026-10-10T23:02:24.866Z","last_seen":"2026-10-22T14:52:55.723Z","days_active":4,"recency":"returning","categories":["other_bot"],"label_variants":1,"journeys":null},"identity_note":"A family name is what a client claims in its user agent. It is verified only when its request came from the operator's published IP ranges or passed forward-confirmed reverse DNS, as reported per family in /crawler-journeys.json. Anyone can claim any name.","privacy":{"scope":"family-level aggregates only","ip_addresses":"not_output","raw_user_agents":"not_output (labels are sanitized; URLs inside them are redacted)","visitor_ids":"not_output","query_strings":"not_output"},"live_sources":{"history":"https://newruntime.com/bot-traffic-history.json","latest":"https://newruntime.com/bot-traffic-latest.json","machine_consumption":"https://newruntime.com/machine-consumption.json","crawler_journeys":"https://newruntime.com/crawler-journeys.json"},"routes":{"html":"https://newruntime.com/readers/crawlcheck/","markdown":"https://newruntime.com/readers/crawlcheck.md","json":"https://newruntime.com/readers/crawlcheck.json","index":"https://newruntime.com/readers.json","index_html":"https://newruntime.com/readers/"}}