performance-review
Codex compatibility note:
- Invoke
$skill-name: load the registered.agents/skills/<name>/SKILL.mdand execute it with Codex tools; no separateSkilltool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author.claude/**; mirrors are generated.- Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
- Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agentsubagent(s) for that task.- Preserve protocol order unless the user approves a deviation. Workflows use
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.
Quick Summary
Review modes: For review/audit work, standalone defaults to
--review-only(--report-onlyalias);--fix-loopenables review → validate → authorized fix → fresh re-review, default cap 3.--fix-loop --loop-owner=callerreturns a read-only pass to the caller that owns fixes/re-review. Create triage, review, validation and re-review todo tasks first; apply the carriedreview-policycontract for LOW deferral and user-approved bounded extensions. Non-review modes and terminal findings validation keep their own dispatch.
Goal: Ensure every shipped performance fix removes a measured or static-risk-labeled bottleneck across data access, compute, runtime/GC, network, client delivery, and concurrency/resilience; calibrate every number against a known anchor, preserve behavior/authorization/semantics, prove before/after evidence, pass $why-review before any fix, and complete a clean full Phase-0 re-review — never hide waste or break correctness.
Summary:
- Main path: detect scope → discover local patterns → measure or label static risk → review all applicable performance dimensions → calibrate severity → plan → validate findings → fix at the owning layer → prove before/after → run a fresh full re-review.
- Gates: count rows before row size; bound memory, queues and concurrency; preserve authorization and semantics. Round 1 clears all validated findings, with a LOW-only fix set reviewed after the fix (LOW deferral). Round 2 clears CRITICAL/HIGH/MEDIUM and defers LOW; failed binary gates always block.
--report-only: read-only leaf mode for a caller that owns every fix — Phases 0–6 only, no nested sub-agents, no writer beyond the report; see Report-Only Mode.
Workflow: Detect scope → discover local patterns → measure or label static risk → run 12 serial dimension passes → findings and severity → plan → validate findings → fix → run a full re-review.