sumo-qa-executing-qa-rolloutlisted

# Executing a QA rollout with subagents Take a written plan from `sumo-qa-planning-qa-rollout` (or a hand-written equivalent at `docs/qa/plans/...`) and execute it by dispatching one fresh subagent per task, then walking each subagent's output through a two-stage review. **Announce at start:** *"Dispatching the plan with subagents."* ## Output discipline (mandatory) Inherits the global discipline from `using-sumo-qa`: **output discipline** (never surface internal taxonomy labels — say *"behaviour change in pricing"*, not *"Classification: business_logic_change"*), **output economy** (spend output on findings not framing; no preamble or self-narration; one question per turn; no closing pleasantries), knowledge authority hierarchy, internal scaffolding stays internal, and specialty-tool fit. <HARD-GATE> Do NOT execute tasks inline. Every task goes to a fresh subagent — a fresh delegated worker with no inherited task context (see `using-sumo-qa` → Shared vocabulary). The orchestrator (you) does dispatch + review + coordination only — it never edits test files directly. If the current host has no worker-delegation primitive at all, STOP and report the capability gap to the user; do NOT silently execute the plan inline. If a subagent fails three times, escalate to the user. </HARD-GATE> ## The Iron Law **ONE FRESH SUBAGENT PER TASK. TWO-STAGE REVIEW. CONTINUOUS EXECUTION.** Fresh subagent prevents context pollution; two-stage review separates "catches the right risk" from