tribunallisted

# /tribunal — Multi-Mode AI Debate Two AI buddies engage on a codebase question using one of six modes. Every claim requires FILE:LINE evidence. ## Modes | Mode | Flag | AIs do | Claude's role | Best for | |------|------|--------|---------------|----------| | adversarial | *(default)* | Argue FOR vs AGAINST | Judge — picks winner | Binary decisions, should/shouldn't | | socratic | `--socratic` | Probe assumptions with questions | Synthesizer — surfaces insights | Early exploration, unclear framing | | steelman | `--steelman` | Argue the OTHER side's strongest case | Calibrator — shows true strength of each side | Avoiding confirmation bias | | red-team | `--red-team` | Attack from different angles, no defense | Risk assessor — prioritized vulnerability table | Poking holes in designs/plans | | synthesis | `--synthesis` | Each proposes a solution, then hybridize | Merger — evaluates proposals + hybrid | Finding a third option | | postmortem | `--postmortem` | Investigate failure from different angles | Investigator — unified timeline + root cause | Bug investigation, incident analysis | ## How to invoke ``` /tribunal "Should we refactor the auth middleware?" /tribunal --socratic "Is our error handling resilient enough?" /tribunal --steelman "Should we migrate to microservices?" /tribunal --red-team "Review our new payment flow" /tribunal --synthesis "How should we restructure the data layer?" /tribunal --postmortem "Why did the deploy fail yesterday?" /tribunal --mode red