Free · no signup · no install
Paste your system prompt. See which of the eight ways agents go wrong it never mentions - prompt injection, hallucination, runaway cost, no human approval, no stop condition. Same open rules as the CLI. Not a red-team.
Coverage, not a quality ranking. You can prove that from the shipped rules: a prompt that states all eight governance controls clearly, once each, scores 28/100 - below the lowest tier. Stating every one of them twice reaches only 41/100. A high score is unreachable by clear writing; it needs the same control restated four to six different ways, which is exactly the redundancy our own Context Bloat detector flags. A low score tells you what you have not written down. A high score means the text is present - nothing more. Read the validation study.
These are judged by different rulesets. The CLI decides from the filename; a browser has no filename, so you declare it — CrewScore never guesses from your text.
Which ruleset applies comes from the artifact type above — not from the content.
Secondary: Vendor checklist (self-attest) — not the primary product path.
10 diligence questions. Self-attested — not a formal audit.