war-room

# War Room Skill A war room runs personas through a structured two-phase session: 1. **Phase 1 — Ideation** (5 rounds max): personas debate the research idea question by question. Ends early on consensus (all `[AGREE]` or `[PASS]`, no `[OBJECT]`) or two consecutive all-`[PASS]` rounds. Output: `memory/war-room/idea-snapshot.md` 2. **Phase 2 — Proposal** (5 rounds max): personas collaboratively draft each proposal section. Output: `memory/war-room/proposal-draft.md` --- ## Configurations Defined in `skills/war-room/personas/agents.json` under the `configurations` key. | Name | Participants | Use when | |------|-------------|----------| | `full` | Creative, Senior Prof, Young Faculty, Industry Liaison | Deep ideation, novel directions, full proposal needed | | `1on1` | Senior Professor, Young Faculty | Quick feasibility check, tight scope | The configuration is specified in `PROJECT.md` frontmatter under `war_room.configuration`. Default: `full`. --- ## Consensus Protocol Every persona response **must** end with one of: | Tag | Meaning | |-----|---------| | `[AGREE]` | I accept the current position | | `[PASS]` | No strong view either way | | `[OBJECT: reason]` | I reject — give specific reason | Do not embed tags mid-response. They must be the final line. --- ## Single-Agent Fallback (Codex / no subagent spawning) If you cannot spawn subagents, run the same loop inline. For each persona turn: 1. Print a clear header: `--- [Round N] <Persona Name> ---`...