The house critic's judgement of a script version — the same independent critic the writing pipeline uses, reading the deterministic quality report alongside. Returns scores 0-100 (global, fidelity to the material, channel voice, rhythm), per-scene notes with severity, and the quality report. Each note says where it comes from (source): critic is the model's reading, audit is a contradiction checked against the research material without a model. factualAudit is the deterministic half: per scene, which facts it cites (citations), whether that backing was cited by the script, inferred from its text, or is text the author dictated in the request (dictated_in_the_request: a disclosure or a closing line — it is not a factual claim and is left out of factualScenes), and what happened to each on-screen figure the material does not carry (onScreenClaims[].outcome): notAsserted = it is not shown (stripped from the text, or its magnitude withheld from the chart), drawnWithoutFigure = plotted without its number, stillAsserted = left on screen; placeholders counts, also without a model, text that names with a letter or an order number what the source does not name («Repository A», «Server 1») or leaves a template marker («N/A», «TODO»), per scene and surface (narration, screen, caption); inputs.script says which document was judged (vbp = the version's blueprint, with its citations). scope states what the critic judges (judges: script) and what it does not see (seesCharts, seesPeriods): the charts and each figure's period are covered by the fidelityReport of the project status. Judgement only: it does not rewrite. The verdict is kept on the version as the critic wrote it; the critic judges in one language for every reader, and the notes returned are presented in the reader's language (notesLanguage says which, and whether they were translated). Defaults to the head version. Requires write. Spends one critic call (small, seconds), plus a short translation of its notes when the reader's language is not the critic's.