opinion-workflowlisted

# opinion-workflow (Dynamic Workflow asset) A Dynamic Workflow asset (see `CLAUDE.md` -> "Dynamic Workflow Assets"; `review-workflow` is the reference example). `opinion.workflow.js` is executed by the `Workflow` tool, invoked from `/lets:opinion`'s Workflow Mode via: ``` Workflow({ scriptPath: "${CLAUDE_PLUGIN_ROOT}/skills/opinion-workflow/opinion.workflow.js", args }) ``` `${CLAUDE_PLUGIN_ROOT}` is substituted at command-load time, so `opinion.md` carries the literal absolute path. Treat `opinion.workflow.js` as a template the command points at, not a script to reproduce inline. ## What it does (off-context) A multi-stage chain so per-agent opinions never enter the conversation - only the final aggregate returns: 1. **Opine** - fan out the selected `lets:<name>` experts in parallel (structured `OPINION_SCHEMA`: per-option scores 1-5, recommended option, risks, confidence, reasoning). 2. **Tally** (pure logic) - aggregate -> options ranked by **recommendation plurality** (average score is only a tiebreak), so `leading` = the most-recommended option (the same axis `unanimous`/`weakConsensus` use). Zero opinions -> no leading (`recommendation` surfaces as null, never a phantom first option). The option-id allowlist also feeds `OPINION_SCHEMA`/`CHALLENGE_SCHEMA` as a runtime enum, so agents can only emit valid ids. 3. **Challenge** (CONDITIONAL) - runs ONLY when `weakConsensus` (not unanimous, or any low-confidence vote). Re-dispatch the same experts to argue the stronges