--- name: audit description: | Use when the user wants a code review on recent changes — quality, spec, security, or performance feedback. Triggers a multi-level (L1-L5) review with a standalone Reviewer; on NEEDS_FIX, offers to apply findings via /hyperflow:plan. Trigger with /hyperflow:audit, "review this change", "review my PR", "audit the diff", "code review". allowed-tools: Read, Write, Edit, Bash(git:*), Glob, Grep, Agent, Skill, AskUserQuestion argument-hint: "[target] [--level 1-5]" version: 3.1.3 license: MIT compatibility: Designed for Claude Code tags: [code-review, quality, multi-level, multi-agent] --- # Audit Multi-level code review. All agents inherit the session model. Reviewers bold-labeled; Workers plain. This skill exercises **Layer 3 (Orchestrator)** and **Layer 9 (Security)**. After the review prints, a **fix gate** asks the user whether to apply the findings — on `Yes`, audit auto-invokes `/hyperflow:plan` with the findings as the spec, which then chains to `/hyperflow:dispatch`. ## Iron Rules **Failure recovery (DOCTRINE rule 14).** Worker errors, malformed output, NEEDS_REVISION verdicts, and gate failures in every Step follow the canonical policy in [`skills/hyperflow/failure-recovery.md`](../hyperflow/failure-recovery.md). Audit-specific exception: a failed Reviewer at L1/L2 escalates to an L3+ Reviewer at the same severity level rather than aborting — audit exists to catch issues, so a Reviewer failure is best resolved by a more thorough Reviewer, not by stopping the chain. ## Per-Step Agent Map (DOCTRINE rule 12) | Step | Sub-phase | Workers | Reviewers | Notes | |---|---|---|---|---| | 1 — Resolve scope | — | — | — | Mechanical decision (exempt) | | 2 — Gather context | 2a — Surface mapping | Searcher × 2 (glob + import-graph) | Reviewer | Parallel | | 2 — Gather context | 2b — Semantic indexing | Searcher × 2 (type-system + symbol-graph) | Reviewer | Parallel | | 2 — Gather context | 2c — Convention scan | Searcher × 1 (test patterns + lint config) | Reviewer | Justified single-angle | | 2 — Gather context | 2d — Aggregate coverage gate | — | **Reviewer** verifies aggregate coverage | Standalone coverage gate | | 3 — Review | 3a — L1+L2 (syntax/format/naming) | — | **Domain specialist Reviewer** × 2 (file groups, surface-matched) + Reviewer aggregates | Parallel pair dispatched as the matching domain specialists | | 3 — Review | 3b — L3 (integration/security) | — | **Reviewer** × 2 — backend-reviewer + security-reviewer/vulnerability-reviewer + Reviewer aggregates | Parallel pair; security specialists web-research-first | | 3 — Review | 3c — L4+L5 (perf/scale/a11y/UX) | — | **Reviewer** × 2 — performance-reviewer + accessibility-reviewer + Reviewer aggregates | Parallel pair dispatched as the matching specialists | | 4 — Findings synthesis | 4a — Critical findings | Writer × 2 (evidence probe + impact analysis) | Revie