{"ok":true,"kind":"crawlcheck-rulebook","v":1,"generated_at":"2026-10-07T17:45:10.003Z","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":"HOST_DUPLICATE_200","kind":"scan","family":{"id":"site","label":"Site, hosts and page"},"title":"www and the apex both serve the site instead of one redirecting","meaning":"Both www and the bare domain answer 200 with the same pages, so every URL on this site exists at two addresses and a crawler fetches the whole site twice. A canonical tag does not prevent this: it is read after the response arrives, so the second fetch has already been spent. Nothing looks broken from a browser, which is why this survives for years. The fix is a 301 from one host to the other so there is one address per page.","severity":{"level":"medium"},"scored":true,"measured_on":"every scan","revision":{"current":1,"revised_at":null},"fix":{"advice":"Pick one host (apex or www) and redirect the other to it with a 301 so there is one copy of every page.","effort":"config","endpoint":null},"share_of_scans":{"pct":3.5,"scans":111,"of_scans":3137,"basis":"share of counted scans that carried it; the same numbers /data publishes"},"links":{"self":"https://crawlcheck.io/rules#HOST_DUPLICATE_200","api":"https://crawlcheck.io/api/rules?code=HOST_DUPLICATE_200","glossary":["https://crawlcheck.io/glossary/canonical","https://crawlcheck.io/glossary/canonical-url","https://crawlcheck.io/glossary/host-duplicate","https://crawlcheck.io/glossary/apex-domain"],"workflow":null,"lineage":"https://crawlcheck.io/docs/lineage-coverage","explain_template":"https://crawlcheck.io/api/explain?id={report_id}&code=HOST_DUPLICATE_200"}}],"filter":{"code":"HOST_DUPLICATE_200"}}