QEMU RLCR Loop

Use this foundational flow after qemu-flow-plan when the task needs iterative implementation, debugging, or substantial validation. It adapts Humanize's RLCR idea to QEMU while keeping every agent-created artifact under build/.

RLCR here means: Ralph Loop with Codex/Reviewer Review.

Hard policy boundary

Do not produce source code intended for QEMU upstream submission. QEMU currently declines contributions believed to include or derive from AI-generated content. You may help with local-only experiments, research, debugging, and verification. Do not add Signed-off-by, Reviewed-by, Acked-by, Tested-by, or similar contribution trailers.

Required inputs

• A plan created by qemu-flow-plan.
• Its artifact root, usually build/agent/<task-slug>/.
• Frozen acceptance criteria.
• A chosen domain skill for the technical work.

If there is no plan, run qemu-flow-plan first.