panel

# /panel — multi-provider deliberation For hard questions where you want several strong models to genuinely deliberate, not just answer in parallel. Each stage builds on the last, so the panel converges *through* disagreement and verification instead of averaging opinions. ## When to use - **architecture** — a feature/system design where the tradeoffs are non-obvious. - **strategy** — a business/product call that rests on assumptions worth stress-testing. - **research** — market/competitive questions where claims need refuting. - **sweep** — a codebase audit (security / correctness / dead-code / refactor). Reach for it when a single model's answer would be a guess, and you'd otherwise open five terminals yourself. ## How it works (4 stages) 1. **Diverge** — every fleet provider (codex / kimi / claude / glm-5.2 / deepseek-harness) analyses the SAME question through a DIFFERENT mode-specific lens. 2. **Contrarian** — one designated seat red-teams the emerging consensus: what did everyone miss, which "this is fine" is wrong. 3. **Verify** — the top claims are adversarially checked (against the CODE for sweeps — real `file:line`; against SOURCES for research — try to refute). 4. **Synthesis** — one cited report: consensus + surviving dissent + verified/refuted claims, ranked and deduped. ## Run it ```bash python3 scripts/panel.py <mode> "<question>" [--context-file FILE] [--timeout 900] [--out FILE] ``` Examples: ```bash # architecture decision, grounded on a design doc...