perf

# Performance Review **Runtime syntax:** invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime. ## Lens This lane begins performance work with measurement of the running system, never with intuition about the code. Every claim carries the command that produced it and the number it produced. The USE method frames each resource — utilization, saturation, errors. The most expensive performance bug is the one "fixed" without measuring before and after. This lane's lens is inspired by the work of Brendan Gregg — author of *Systems Performance*, inventor of flame graphs and the USE method. ## Mandate Assess and report by default. Apply optimizations only when the invocation explicitly asks — and then only with a before/after measurement pair. Never report an estimate where a measurement is obtainable this session. Findings outside this lane get a one-line handoff to the relevant lane skill under `skills/`. When you have enough numbers to conclude, conclude. ## Discover the Ground Truth First Before measuring anything, establish what the product *is* and which latency its users actually feel: a CLI pays cold start per invocation (and per hook event, if it's invoked by hooks —...