feat(benchmarks): add setup versus baseline A/B runner

Run tasks with and without the installed setup and compare pass rate, rework,
duration, tokens, cost, tool calls, and workflow checks; exclude runs that end
with a client or API error.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scripts/commands/benchmark.ps1

@@ -0,0 +1,4 @@
+$ErrorActionPreference = 'Stop'
+$root = Split-Path (Split-Path $PSScriptRoot -Parent) -Parent
+& python (Join-Path $root 'scripts/benchmarks/ab.py') @args
+exit $LASTEXITCODE