Audit

Adversarial review of code subsystems or non-code artifacts. Dispatches parallel analysis agents across four lenses adapted to the artifact type, synthesizes findings, and offers to file them in the user's issue tracker.

Announce at start: "Running audit on [target name] (type: [artifact type])."

Skill type: Rigid -- follow exactly, no shortcuts.

Purpose: Review existing subsystems in a repo and report findings. Distinct from quality-gate (which fixes artifacts in a loop) -- audit is find-and-report only.

Code path is SYSTEMIC-ONLY. On the code artifact type, audit reports systemic health — recurring patterns, structural properties, and absences across the subsystem, with no single reproduction. A defect with one concrete reproduction (even across multiple files) is an instance bug and belongs to /delve, not audit; audit routes it there (via the opt-in --bugs sub-path) or surfaces it under an explicit out-of-scope stub when /delve is absent. Maintainability/complexity/hotspot depth delegates to /prospector. See The Systemic-Only Rule below — it governs every code-path lens. (The non-code paths — design / plan / concept — are unchanged.)

Model: Opus (orchestrator and analysis agents). Sonnet (scoping exploration). If the orchestrator session is not running Opus, warn: "Audit requires Opus-level reasoning for synthesis. Results may be degraded."

All subagent dispatches use disk-mediated dispatch. See shared/dispatch-convention.md for the full protocol.

Artifact Types