planlisted

> **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. # /plan — from an idea to a gated source of truth (planning lane, no code) **Why this exists:** every other vteam lane assumes an oracle already exists. `/ba` shards a spec; `/docs` reverse-engineers one from code; `/dev` and `/qa` cite it. A brand-new project has neither code nor documents — so before this workflow, vteam was mute at the exact moment the most expensive decisions get made. `/plan` is the intake: it turns the owner's head into documents the gates can guard. **Lane boundaries (pick the right door):** - No code, no docs → **/plan** (this lane). - Code exists, docs don't → **/docs** (read the code first, then ask). - A spec document exists → **/ba** (shard it, build the backlog). **What this workflow is NOT:** it never writes or edits product code,