plan 2

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Plan-document review panel for DeepSeek Harness: intercepts exit_plan_mode, shows the markdown plan in a right-side panel styled like the sidebar, lets the user edit the document and enter feedback, then confirms to start implementing.