audit
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.
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
Audit supports 4 artifact types, each with tailored analytical lenses:
More from raddue/crucible
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
8adversarial-tester
Use after completing implementation to find unknown failure modes. Reads implementation diff and writes up to 5 tests designed to make it break. Triggers on 'break it', 'adversarial test', 'stress test implementation', 'find weaknesses', or any task seeking to expose unknown failure modes.
5quality-gate
Iterative red-teaming of any artifact (design docs, plans, code, hypotheses, mockups). Loops until clean or stagnation. Invoked by artifact-producing skills or their parent orchestrator.
5code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
5finish
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
4verify
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
4