pmlisted

> **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. # /pm — orchestrate the team; the owner keeps only the decision desk **What this workflow is NOT:** it never answers an open business question itself (the documented 🟡 PROVISIONAL mechanism in P-DECIDE 2b is the sole exception, and only at `autonomy.level: full`), never bypasses a child lane's QUALITY gate (/dev's verify + reviewers, /ba's challenger, /qa's evidence gate + challenger), and never merges/transitions ANYTHING itself — merging PRs and moving statuses belong to the child lanes under their own autonomy rules. Its single output: work flowing through the right lane, and ONE table of things only the owner can do. **The lineup** — 5 roles; three have their own workflows; /pm plays the other two and keeps the beat: | Role | Lane | Runner | |---|---|---|