openauditB85out of 100: openaudit's audit of itself
agent.performance

Performance review

Finds performance problems that need understanding of hot paths: N+1 queries, missing indexes, unbounded queries, blocking work, missing caching, heavy client bundles, leaks and render waterfalls. (agentic, uses Claude)

Engine
Agent
Targets
Codebase
Areas
Performance, Reliability
Runs
Opt-in: only when selected with --only
Network
Contacts services beyond the target

Run only this auditor

bunx openaudit . --only agent.performance

Runs a playbook with the Claude Agent SDK. Needs ANTHROPIC_API_KEY or a Claude Code login; host agents can run the same playbook over MCP without a key.

Playbook

Finds performance problems that need understanding of hot paths: N+1 queries, missing indexes, unbounded queries, blocking work, missing caching, heavy client bundles, leaks and render waterfalls.

Host agents fetch it with get_playbook over MCP. How playbooks work