judge
Run the judgement checklist (--judge) over text, HTML, or a directory: the 5-question review (purpose/audience/decision/variety/defaults) with machine-flagged signals per question, a craft-floor gate (contrast/alignment/text-hierarchy/spacing/no-fake-data/no-decorative-effects) mapped from scanner evidence with human-checkbox items for the non-machineable parts, refusal scaffolds, and a machine-computed PASS | REVIEW | REFUSE verdict computed ONLY from machine-verifiable parts. Same input always gives the same verdict.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| dir | No | directory path to judge — local filesystem access only | |
| html | No | HTML document to judge | |
| text | No | plain text to judge |