Run Argot's complete configured detector pipeline over one selected changeset. Use this after editing when you need the same voice, semantic, architecture, integrity, and custom-rule findings as the CLI. Returns the stable check JSON, including findings, evidence, suppressions, and result counts. Read-only: it does not fit, mute, edit files, or update the last-check cache; requires a fitted repository.

Score one supplied code hunk with Argot's fast fitted voice model. Use while drafting or for an isolated snippet when no Git changeset exists. Returns out_of_voice, score, threshold, rule, and concise evidence; it does not run semantic, architecture, integrity, or custom rules. For a real change, prefer check_changeset. Read-only; requires a fitted repository.

Explain one hunk-level voice result with untruncated structured evidence, including surprising identifiers and attestation counts. Use as a follow-up when check_hunk flags or nearly flags a snippet; do not use it as a second independent check. It covers the fitted voice model only. Read-only; requires a fitted repository.

Get the repository vocabulary relevant to a file before writing: typical callees, familiar imports, and active replacement guidance for the file's language. This is generation context, not a verdict about code and not a changeset check. Read-only; requires a fitted repository.

Get repository readiness before using learned tools: fit suitability, committed-snapshot completeness, configuration compatibility, and the adaptive refresh recommendation with structured reasons and next_action. This tool diagnoses setup and maintenance only; it never fits or writes.

List conventions learned from the repository: internal API vocabulary, placement concentrations, and migrations still in progress. Use this to discover candidate team conventions or understand where code belongs; it does not evaluate a change. Read-only; requires a fitted repository.