{"ok":true,"kind":"crawlcheck-rulebook","v":1,"generated_at":"2026-10-07T17:46:04.984Z","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_RULES_SHADOWED","kind":"scan","family":{"id":"robots","label":"Robots"},"title":"robots.txt rules do not apply to named agents","meaning":"A crawler reads only the User-agent group that matches it best and ignores every other group, including `*`. Naming an agent and giving it only `Allow: /` therefore deletes all of your `*` Disallow rules for that agent. The file still parses and the agent still reaches your homepage, so this is invisible on inspection — but the paths you meant to keep out of search are open, and search engines will crawl and may index them.","severity":{"level":"medium"},"scored":true,"measured_on":"every scan","revision":{"current":2,"revised_at":"2026-09-30"},"fix":{"advice":"Every User-agent group that names a crawler must repeat the Disallow rules you want applied. A named group with no rules means 'allow everything' for that crawler.","effort":"config","endpoint":"https://crawlcheck.io/api/fix/robots?domain={domain}"},"share_of_scans":{"pct":13.4,"scans":419,"of_scans":3137,"basis":"share of counted scans that carried it; the same numbers /data publishes"},"links":{"self":"https://crawlcheck.io/rules#ROBOTS_RULES_SHADOWED","api":"https://crawlcheck.io/api/rules?code=ROBOTS_RULES_SHADOWED","glossary":["https://crawlcheck.io/glossary/robots-txt","https://crawlcheck.io/glossary/robots-group-merging"],"workflow":null,"lineage":"https://crawlcheck.io/docs/lineage-coverage","explain_template":"https://crawlcheck.io/api/explain?id={report_id}&code=ROBOTS_RULES_SHADOWED"}}],"filter":{"code":"ROBOTS_RULES_SHADOWED"}}