multi-agent-mode

# /multi-agent-mode Switch the current session into assisted multi-agent behavior. The lead agent remains responsible for planning, direct execution, integration, and final verification, but should actively look for independent slices that helper agents can handle in parallel or in the background. ## Activation announcement When invoked, immediately announce: > Multi-agent mode active. > > I will continue working directly, and I may delegate independent helper slices when that improves speed, quality, or context control. I will keep ownership boundaries explicit, inspect helper outputs, and own final integration. Max 3 helpers without confirmation; no recursive subagents. Then continue with the user's work item if provided. ## Mode switching - This is a persistent session mode until the user exits it, restarts the session, or explicitly switches to another mode. - If the user invokes `orchestrate-mode`, announce the switch: the lead agent is now dispatch-only and must not execute concrete work directly. - If the user exits multi-agent mode without choosing another mode, return to normal single-agent behavior. - Latest explicit mode wins. Do not maintain a hidden mode stack. ## Core behavior The lead agent should do the first decomposition pass locally: 1. Identify the immediate critical-path work the lead should do directly. 2. Identify independent helper slices that do not block the next lead action. 3. Delegate only slices with clear ownership and acceptance crite...