/war-room

name: war-room
description: "Convene a multi-LLM expert panel to pressure-test strategic decisions with adversarial review and reversibility assessment."

War Room Command

Orchestrate multi-expert deliberation for complex strategic decisions with reversibility assessment and adversarial review.

When To Use

Use this command when you need to:

• Make critical, high-stakes decisions
• Evaluate irreversible or costly changes
• Compare architectural approaches with trade-offs
• Resolve conflicting expert opinions
• Pressure-test assumptions before commitment
• Build consensus on strategic direction
• Assess decision reversibility

When NOT To Use

Avoid this command if:

• Decision is trivial or easily reversible
• Single obvious path exists
• Already decided and need implementation
• Routine operational choices
• Quick tactical adjustments

Usage

# Basic invocation with problem statement
/attune:war-room "What architecture should we use for the payment system?"

# With context files
/attune:war-room "Best API versioning strategy" --files src/api/**/*.py

# Reversibility assessment only (no deliberation)
/attune:war-room "Database migration to MongoDB" --assess-only

# Force express mode (Type 2 decisions)
/attune:war-room "Which logging library?" --express

# Use startup threshold profile (more aggressive)
/attune:war-room "New feature architecture" --thresholds startup

# Use regulated profile (more conservative)
/attune:war-room "Data retention policy" --thresholds regulated

# Force full council (all experts)
/attune:war-room "Migration approach" --full-council

# High-stakes Delphi mode (iterative until consensus)
/attune:war-room "Platform decision" --delphi

# Resume interrupted session
/attune:war-room --resume war-room-20260120-153022

# Escalate from brainstorm
/attune:war-room --from-brainstorm

What This Command Does

1. **Assesses reversibility** (Phase 0) to determine appropriate deliberation intensity 2. **Routes to correct mode** based on Reversibility Score (RS):

• RS ≤ 0.40: Express (1 expert, < 2 min)
• RS 0.41-0.60: Lightweight (3 experts, 5-10 min)
• RS 0.61-0.80: Full Council (7 experts, 15-30 min)
• RS > 0.80: Full Council + Delphi (iterative, 30-60 min)

3. **Gathers intelligence** via Scout and Intelligence Officer 4. **Develops courses of action** from multiple perspectives 5. **Pressure tests** via Red Team adversarial review 6. **Synthesizes decision** via Supreme Commander 7. **Persists session** to Strategeion (Memory Palace)

Reversibility Score (RS)

The War Room automatically assesses decision reversibility using five dimensions (1-5 each):

| Dimension | 1 (Reversible) | 5 (Irreversible) | |-----------|----------------|------------------| | **Reversal Cost** | Trivial (<1 day) | Prohibitive (months+) | | **Time Lock-In** | Reverse anytime | Crystallizes immediately | | **Blast Radius** | Single component | Organization-wide | | **Information Loss** | All options preserved | Critical paths closed | | **Reputation Impact** | Internal only | Public trust at stake |

**RS = Sum / 25** → Routes to appropriate deliberation mode.

Arguments

| Argument | Description | |----------|-------------| | `<problem>` | The decision/problem to deliberate (required unless --resume) | | `--files <globs>` | Context files to analyze | | `--assess-only` | Show RS assessment without full deliberation | | `--express` | Force Type 2 mode (single expert, fast) | | `--full-council` | Use all experts (override RS recommendation) | | `--delphi` | Iterate until expert consensus (Type 1A+ mode) | | `--thresholds <profile>` | Use preset threshold profile: `default`, `fast`, `cautious`, `startup`, `regulated` | | `--resume <id>` | Resume interrupted session | | `--from-brainstorm` | Import context from recent brainstorm | | `--archive <name>` | Custom name for campaign archive |

Threshold Profiles

| Profile | Express | Lightweight | Full Council | Use When | |---------|---------|-------------|--------------|----------| | `default` | 0.40 | 0.60 | 0.80 | General use | | `fast` | 0.50 | 0.70 | 0.90 | Speed over process | | `cautious` | 0.30 | 0.50 | 0.70 | Higher stakes environment | | `startup` | 0.55 | 0.75 | 0.90 | Move fast, break things | | `regulated` | 0.25 | 0.45 | 0.65 | Compliance-heavy industries |

Or customize at session start when prompted.

Expert Panel

Lightweight Mode (Default)

| Expert | Model | Role | |--------|-------|------| | Supreme Commander | Claude Opus | Final synthesis | | Chief Strategist | Claude Sonnet | Approach generation | | Red Team | Gemini Flash | Adversarial challenge |

Full Council (--full-council)

| Expert | Model | Role | |--------|-------|------| | Supreme Commander | Claude Opus | Final synthesis | | Chief Strategist | Claude Sonnet | Approach generation | | Intelligence Officer | Gemini 2.5 Pro | Deep context analysis | | Field Tactician | GLM-5.2 | Implementation feasibility | | Scout | Qwen Turbo | Rapid reconnaissance | | Red Team Commander | Gemini Flash | Adversarial challenge | | Logistics Officer | Qwen Max | Resource estimation |

Workflow

# 1. Invoke war-room skill
Skill(attune:war-room)

# 2. Execute deliberation phases:
#    - Phase 0: Reversibility Assessment (immediate)
#      ↳ RS ≤ 0.40? → EXPRESS MODE (skip to Phase 7)
#    - Phase 1: Intelligence Gathering (parallel)
#    - Phase 2: Situation Assessment
#    - Phase 3: COA Development (parallel, anonymized)
#    - Escalation Check (Commander validates RS or overrides)
#    - Phase 4: Red Team Review
#    - Phase 5: Voting + Narrowing
#    - Phase 6: Premortem Analysis
#    - Phase 7: Supreme Commander Synthesis

# 3. Persist to Strategeion
#    ~/.claude/memory-palace/strategeion/war-table/{session-id}/

# 4. **AUTO-DOCUMENT TO PROJECT PLANS** (NEW)
#    Write decision to docs/plans/YYYY-MM-DD-war-room-{topic}.md
#    Creates docs/plans/ if it doesn't exist

# 5. Output decision document with RS ass