{"ok":true,"kind":"crawlcheck-rulebook","v":1,"generated_at":"2026-10-07T17:44:52.982Z","score_version":28,"schema":"https://crawlcheck.io/schemas/rulebook.json","counts":{"rules":77,"by_kind":{"scan":52,"answer_correlation":5,"capability_mismatch":6,"self_audit":12,"mcp_server":2},"by_family":{"site":8,"headers":4,"mostly_code":3,"machine_files":11,"robots":13,"delivery":8,"jsonld":3,"nap":2,"answers":5,"capabilities":6,"self_audit":12,"mcp":1,"watch":1},"revised":7,"scored":48},"scans_counted":3137,"severity_scale":[{"level":"info"},{"level":"low"},{"level":"medium"},{"level":"high"},{"level":"critical"}],"method":{"revisions":"A rule that changes what it reports gets a new revision; a record keeps the revision that decided it, and a replay uses that revision, never today's.","share":"Share of counted scans that carried the code at least once, the same numbers /data publishes. Self-scans and opted-out sites are never counted.","grade":"Each finding has a level from info to critical. Open findings at medium and above lower the letter grade; fix them first."},"rules":[{"code":"ROBOTS_NOT_200","kind":"scan","family":{"id":"robots","label":"Robots"},"title":"robots.txt does not return 200","meaning":"The response code on robots.txt determines how crawlers treat the whole site. Anything other than 200 or a clean 404 is risky.","severity":{"level":"medium"},"scored":true,"measured_on":"every scan","revision":{"current":1,"revised_at":null},"fix":{"advice":"Serve robots.txt with status 200 as text/plain. A 404 or 410 means no file: under RFC 9309 a crawler may then fetch everything, so any rule you meant to publish is not in force. A 429 is read by Google as a server error, which pauses crawling: exempt robots.txt from rate limits.","effort":"config","endpoint":null},"share_of_scans":{"pct":3.9,"scans":123,"of_scans":3137,"basis":"share of counted scans that carried it; the same numbers /data publishes"},"links":{"self":"https://crawlcheck.io/rules#ROBOTS_NOT_200","api":"https://crawlcheck.io/api/rules?code=ROBOTS_NOT_200","glossary":["https://crawlcheck.io/glossary/robots-txt","https://crawlcheck.io/glossary/robots-unavailable"],"workflow":null,"lineage":"https://crawlcheck.io/docs/lineage-coverage","explain_template":"https://crawlcheck.io/api/explain?id={report_id}&code=ROBOTS_NOT_200"}}],"filter":{"code":"ROBOTS_NOT_200"}}