teamlisted

> **Model routing for this tool** (from `model-routing.data.yaml`, snapshot 2026-08-17): > `frontier` → **fable** · `workhorse` → **opus** · `standard` → **sonnet** · `utility` → **haiku** > Roles → tiers: ba-challenger: standard · ba-draft: standard · dev-r1: workhorse · dev-r2: standard (high-stakes: workhorse) · dev-r3: workhorse · explore: utility · qa-challenger: standard · sa-background: workhorse · sa-challenger: workhorse · sa-writer: workhorse > Resolve at runtime: `python3 .vteam/scripts/model_route.py <role> --tool claude-code [--high-stakes]` — high-stakes diffs (review.high_stakes_*) bump dev-r2 to the workhorse tier. > Spawning a subagent: pass the resolved name as the Agent tool's `model` parameter. # /team — one command, the whole team at work This is the "start the workday" button. The complete rulebook is inherited **intact** from the `/pm` workflow — the 5-role lineup, the immutable principles, the UNBLOCKED definition, the lane priority order, the SA lane, P-DECIDE, the ledger. This file only defines what differs: **running in one sweep, and running in parallel**. On any conflict between the two files → /pm wins. **What this workflow is NOT:** not a "drop the gates for speed" mode. Every QUALITY gate of the child lanes (/verify, reviews per `review-standard.md`, the evidence gate, challengers) holds absolutely. At `autonomy.level: full`, the WAIT-FOR-HUMAN gates run autonomous: eligible PRs self-merge — governed by config `autonomy.self_merge` (this in