Multi-LLM deliberation for strategic decisions via expert pressure-testing and consensus building. Use for critical, irreversible, or high-stakes architecture choices and conflicts. Skip for trivial or reversible decisions.
Orchestrates multi-LLM expert deliberation for high-stakes, irreversible strategic decisions.
/plugin marketplace add athola/claude-night-market/plugin install attune@claude-night-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
modules/deliberation-protocol.mdmodules/discussion-publishing.mdmodules/expert-roles.mdmodules/merkle-dag.mdmodules/reversibility-assessment.mdOrchestrate multi-LLM deliberation for complex strategic decisions.
The War Room convenes multiple AI experts to analyze problems from diverse perspectives, challenge assumptions through adversarial review, and synthesize optimal approaches under the guidance of a Supreme Commander.
"The trick is that there is no trick. The power of intelligence stems from our vast diversity, not from any single, perfect principle."
- Marvin Minsky, Society of Mind
Before deliberation, assess the Reversibility Score (RS) to determine appropriate resource allocation:
RS = (Reversal Cost + Time Lock-In + Blast Radius + Information Loss + Reputation Impact) / 25
| RS Range | Type | Mode | Resources |
|---|---|---|---|
| 0.04 - 0.40 | Type 2 | Express | 1 expert, < 2 min |
| 0.41 - 0.60 | Type 1B | Lightweight | 3 experts, 5-10 min |
| 0.61 - 0.80 | Type 1A | Full Council | 7 experts, 15-30 min |
| 0.81 - 1.00 | Type 1A+ | Delphi | 7 experts, 30-60 min |
Quick Heuristics:
See modules/reversibility-assessment.md for full scoring guide.
| Role | Model | Purpose |
|---|---|---|
| Supreme Commander | Claude Opus | Final synthesis, escalation decisions |
| Chief Strategist | Claude Sonnet | Approach generation, trade-off analysis |
| Red Team | Gemini Flash | Adversarial challenge, failure modes |
| Role | Model | Purpose |
|---|---|---|
| Supreme Commander | Claude Opus | Final synthesis |
| Chief Strategist | Claude Sonnet | Approach generation |
| Intelligence Officer | Gemini 2.5 Pro | Large context analysis (1M+) |
| Field Tactician | GLM-4.7 | Implementation feasibility |
| Scout | Qwen Turbo | Quick data gathering |
| Red Team Commander | Gemini Flash | Adversarial challenge |
| Logistics Officer | Qwen Max | Resource estimation |
Round 1: Generation
- Phase 1: Intelligence Gathering (Scout, Intel Officer)
- Phase 2: Situation Assessment (Chief Strategist)
- Phase 3: COA Development (Multiple experts, parallel)
- Commander Escalation Check
Round 2: Pressure Testing
- Phase 4: Red Team Review (all COAs)
- Phase 5: Voting + Narrowing (top 2-3)
- Phase 6: Premortem Analysis (selected COA)
- Phase 7: Supreme Commander Synthesis
For high-stakes decisions, extend to iterative Delphi convergence:
War Room is AUTOMATICALLY INVOKED from Skill(attune:project-brainstorming) after Phase 3 (Approach Generation).
The brainstorm skill passes all context to War Room:
Bypass conditions (only if ALL true):
# Automatic invocation from brainstorm (do not skip)
/attune:war-room --from-brainstorm
# Direct invocation (standalone)
/attune:war-room "Should we use microservices or monolith for this system?"
Sessions persist to the Strategeion (War Palace):
~/.claude/memory-palace/strategeion/
- war-table/ # Active sessions
- campaign-archive/ # Historical decisions
- doctrine/ # Learned patterns
- armory/ # Expert configurations
Experts are invoked via conjure delegation:
conjure:gemini-delegation for Gemini modelsconjure:qwen-delegation for Qwen modelsccgd or claude-glm --dangerously-skip-permissions)/attune:war-room "What architecture should we use for the new payment system?"
/attune:war-room "Best approach for API versioning" --files src/api/**/*.py
Quick assessment without full deliberation:
/attune:war-room "Database migration to MongoDB" --assess-only
Output:
Reversibility Assessment
========================
Decision: Database migration to MongoDB
Dimensions:
Reversal Cost: 5/5 (months of rework)
Time Lock-In: 4/5 (migration path hardens)
Blast Radius: 5/5 (all services affected)
Information Loss: 4/5 (query patterns, ACID)
Reputation Impact: 2/5 (internal unless downtime)
Reversibility Score: 0.80
Decision Type: Type 1A (One-Way Door)
Recommended Mode: Full Council
Proceed with full deliberation? [Y/n]
Skip to rapid decision for clearly reversible choices:
/attune:war-room "Which logging library to use" --express
Override RS assessment for critical decisions:
/attune:war-room "Migration strategy" --full-council
For highest-stakes irreversible decisions:
/attune:war-room "Long-term platform decision" --delphi
/attune:war-room --resume war-room-20260120-153022
The War Room produces a Supreme Commander Decision document:
## SUPREME COMMANDER DECISION: {session_id}
### Reversibility Assessment
| Dimension | Score | Rationale |
|-----------|-------|-----------|
| Reversal Cost | X/5 | ... |
| Time Lock-In | X/5 | ... |
| Blast Radius | X/5 | ... |
| Information Loss | X/5 | ... |
| Reputation Impact | X/5 | ... |
**RS: 0.XX | Type: [1A+/1A/1B/2] | Mode: [delphi/full_council/lightweight/express]**
### Decision
**Selected Approach**: [Name]
### Rationale
[Why this approach was selected]
### Implementation Orders
1. [ ] Immediate actions
2. [ ] Short-term actions
### Watch Points
[From Premortem - what to monitor]
### Reversal Plan (for Type 1 decisions)
[If this decision proves wrong, here's the exit strategy]
### Dissenting Views
[For the record]
Saved to Strategeion:
Expert contributions are anonymized during deliberation using Merkle-DAG:
See modules/merkle-dag.md for details.
Deliberation mode is automatically selected based on Reversibility Score:
| RS Score | Automatic Mode |
|---|---|
| ≤ 0.40 | Express (bypass full War Room) |
| 0.41 - 0.60 | Lightweight panel |
| 0.61 - 0.80 | Full Council |
| > 0.80 | Full Council + Delphi |
The Supreme Commander may override automatic classification when:
Escalation requires written justification with RS assessment.
Equally important: identify decisions being over-deliberated:
{
"war_room": {
"default_mode": "lightweight",
"auto_escalate": true,
"delphi_threshold": 0.85,
"max_delphi_rounds": 5
}
}
War Room can be auto-suggested via hook when:
When --agent-teams is specified (or auto-selected for Full Council / Delphi modes), the War Room uses Claude Code Agent Teams instead of sequential conjure delegation. Each expert runs as a persistent teammate with bidirectional messaging, enabling real-time deliberation instead of batch request/response cycles.
Requires: Claude Code 2.1.32+, CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1, tmux installed.
| Mode | Without Agent Teams | With Agent Teams | Benefit |
|---|---|---|---|
| Express | Sonnet direct call | N/A (overkill) | None — skip |
| Lightweight | 3 sequential delegations | N/A (overhead exceeds benefit) | None — skip |
| Full Council | 7 sequential/parallel delegations | 7 teammates with live inbox messaging | Experts can react to each other's COAs in real-time |
| Delphi | Multiple delegation rounds | Persistent team iterates until convergence | No re-invocation cost per round; state preserved across rounds |
Rule of thumb: Use agent teams only for Full Council and Delphi modes. Lightweight and Express modes don't generate enough inter-expert traffic to justify the coordination overhead.
# War Room agent team structure
Team: war-room-{session-id}
Lead: supreme-commander (Opus) — orchestrates phases, final synthesis
Teammates:
chief-strategist (Sonnet) — approach generation
intel-officer (Sonnet) — deep context analysis
field-tactician (Sonnet) — implementation feasibility
scout (Haiku) — rapid reconnaissance
red-team (Sonnet) — adversarial challenge
logistics (Haiku) — resource estimation
Note: In agent teams mode, all teammates run as Claude Code instances (Opus/Sonnet/Haiku). External LLM experts (Gemini, Qwen, GLM) are not used because agent teams requires the Claude CLI. The trade-off is losing model diversity but gaining real-time inter-expert messaging.
If agent teams fails (tmux unavailable, team creation error), the War Room automatically falls back to standard conjure delegation. The deliberation protocol is identical — only the execution backend differs.
Agent teams is significantly more token-intensive than conjure delegation (each teammate maintains its own context window). Use only when the coordination value justifies the cost — typically Delphi mode where multiple rounds of revision make persistent teammates worthwhile.
Skill(attune:project-brainstorming) - Pre-War Room ideationSkill(imbue:scope-guard) - Scope managementSkill(imbue:rigorous-reasoning) - Reasoning methodologySkill(conjure:delegation-core) - Expert dispatchSkill(conjure:agent-teams) - Agent teams coordination (Full Council / Delphi)/attune:war-room - Invoke this skill/attune:brainstorm - Pre-War Room ideation/memory-palace:strategeion - Access War Room historyActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.