audit-code

Read-only architecture audit of a codebase. Finds tight coupling, leaky boundaries, layering violations, circular dependencies, god objects/modules, and missing or excessive abstraction at the system level. Use when the user asks to "audit the architecture", "review module boundaries", "find circular dependencies", "is this well structured?", "check separation of concerns", or "are the layers leaking?". Complements audit-code-quality (which works at the function/file level). For the full multi-dimension audit use audit-code-master. Never edits code.

Read-only correctness audit of a codebase. Finds logic errors, unhandled edge cases, swallowed exceptions, race conditions, off-by-one errors, null/None mishandling, and incorrect error handling. Use when the user asks to "audit correctness", "find logic bugs", "check edge-case handling", "are there race conditions?", "is the error handling correct?", or "what could break here?". For the full multi-dimension audit use audit-code-master. Never edits code.

Read-only dependency audit of a codebase. Finds outdated or known-vulnerable packages, unused dependencies, unpinned/floating versions, license risk, and unjustified new dependencies. Use when the user asks to "audit dependencies", "check for vulnerable packages", "find unused dependencies", "are versions pinned?", "review the dependency tree", or "any license risks?". For the full multi-dimension audit use audit-code-master. Never edits code.

Read-only multi-agent codebase audit orchestrator. Fans out parallel sub-agents across the audit-code dimension skills (security, correctness, performance, quality, architecture, dependencies, testing), aggregates and ranks findings by severity, writes a styled HTML report to ~/.reports/audit-<project>.html (auto-opened), prints a Markdown summary, then offers to file issues or export a CSV. Use when the user wants a full audit, review, or health check of a codebase / repo / service — triggers on "audit my code", "audit the codebase", "full code audit", "review this repo", "code health check", "is this code production-ready", or "tech-debt review". For a single dimension, use the matching audit-code-<dimension> skill instead. Never edits code.

Read-only performance audit of a codebase. Finds N+1 queries, O(n^2) loops, blocking I/O on async paths, unbounded memory growth, missing database indexes, redundant work, and chatty network calls. Use when the user asks to "audit performance", "find perf issues", "why is this slow?", "check for N+1 queries", "find bottlenecks", or "is this scalable?". For the full multi-dimension audit use audit-code-master. Never edits code.