multi-model-team

Delegates token-heavy, self-contained tasks to local CLI backends chosen by task size and type, with credit-exhaustion fallback through the backend chain to native Claude and a glanceable statusline HUD. Routing and shipped backend behavior are configured in config/roster.json; adding a new backend kind requires invoker and health support in code. /team runs a decompose → dispatch → verify → fix → synthesize pipeline; an optional config-gated UserPromptSubmit hook can proactively nudge delegation.