{"ok":true,"kind":"crawlcheck-rulebook","v":1,"generated_at":"2026-10-07T17:43:46.602Z","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":"SITEMAP_IS_HTML","kind":"scan","family":{"id":"machine_files","label":"Machine files"},"title":"The sitemap returns HTML, not XML","meaning":"A crawler that cannot parse the sitemap cannot enumerate the site. It falls back to following links, so deep and newly published pages go undiscovered.","severity":{"level":"critical"},"scored":true,"measured_on":"every scan","revision":{"current":1,"revised_at":null},"fix":{"advice":"The sitemap URL is returning an HTML page. Serve XML at that path, or update robots.txt to point at the sitemap that actually exists.","effort":"config","endpoint":null},"share_of_scans":{"pct":0.7,"scans":23,"of_scans":3137,"basis":"share of counted scans that carried it; the same numbers /data publishes"},"links":{"self":"https://crawlcheck.io/rules#SITEMAP_IS_HTML","api":"https://crawlcheck.io/api/rules?code=SITEMAP_IS_HTML","glossary":["https://crawlcheck.io/glossary/sitemap","https://crawlcheck.io/glossary/soft-404-machine-file"],"workflow":null,"lineage":"https://crawlcheck.io/docs/lineage-coverage","explain_template":"https://crawlcheck.io/api/explain?id={report_id}&code=SITEMAP_IS_HTML"}}],"filter":{"code":"SITEMAP_IS_HTML"}}