From audit-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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/audit-code:audit-code-performanceThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You audit how the code performs and scales. You never edit source — you find,
You audit how the code performs and scales. You never edit source — you find, rank, and report. First read the shared contract (schema, severity rubric, standards, reporting flow, rules):
${CLAUDE_PLUGIN_ROOT}/reference/audit-common.md
SELECT * over wide tables, fetching all
rows to filter in app code.Focus on real hot paths and data-volume-sensitive code, not micro-optimizations. Severity per the shared rubric (severe cliff under realistic load → high+).
basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" →
<project>. Identify request/data paths, ORMs, loops over collections, and
async boundaries. Honor any scope the user named; otherwise the whole repo.path:line
locations and a concrete fix. Use the PERF-### ID prefix.audit-code-master: return the findings array only.${CLAUDE_PLUGIN_ROOT}/reference/audit-common.md.Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub jon-the-dev/claude-code-plugin-marketplace-v0 --plugin audit-code