War Room
Convene a multi-LLM expert panel to pressure-test strategic decisions with adversarial review and reversibility assessment.
- Type
- Slash Command
- Repository
- athola/claude-night-market
- GitHub stars
- 339
- License
- MIT
- Repo last updated
- Sep 24, 2026
- Source file
- plugins/attune/commands/war-room.md
What War Room is
War Room is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”
A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.
War Room gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.
How to install War Room
Claude Code
- Download war-room.md from the repository.
- Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
- Run it by typing / followed by its name.
Claude Cowork
- Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
- In Customize → Skills, click +, then upload the ZIP.
- Run it from any task with / and the skill name.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/attune/commands/war-room.md, shared under the repository's MIT license. Read the full file on GitHub.
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
…What This Command Does
- Assesses reversibility (Phase 0) to determine appropriate deliberation intensity
- 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)
- Gathers intelligence via Scout and Intelligence Officer
- Develops courses of action from multiple perspectives
- Pressure tests via Red Team adversarial review
- Synthesizes decision via Supreme Commander
- Persists session to Strategeion (Memory Palace)
Reversibility Score (RS)
The War Room automatically assesses decision reversibility using five dimensions (1-5 each):
RS = Sum / 25 → Routes to appropriate deliberation mode.
Arguments
Threshold Profiles
Or customize at session start when prompted.
Expert Panel
Lightweight Mode (Default)
Full Council (--full-council)
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}/
…Output
Decision Document
## SUPREME COMMANDER DECISION: war-room-20260120-153022
### Reversibility Assessment
| Dimension | Score | Rationale |
|-----------|-------|-----------|
| Reversal Cost | 4/5 | Service decomposition hard to reverse |
| Time Lock-In | 3/5 | Architecture hardens over months |
| Blast Radius | 4/5 | Affects all teams |
| Information Loss | 3/5 | Some patterns locked |
| Reputation Impact | 2/5 | Internal decision |
**RS: 0.64 | Type: 1A | Mode: full_council**
### Decision
**Selected Approach**: Microservices with Event Sourcing
### Rationale
[2-3 paragraphs explaining why]
…Session Artifacts
Saved to Strategeion:
~/.claude/memory-palace/strategeion/war-table/{session-id}/
session.json # Full session state
intelligence/ # Scout and Intel Officer reports
battle-plans/ # All COAs
wargames/ # Red Team challenges + Premortem
orders/ # Final decisionIntegration
From Brainstorm
When brainstorm produces multiple strong approaches:
# Brainstorm first
/attune:brainstorm "New payment system"
# Then escalate to War Room
/attune:war-room --from-brainstormWith Memory Palace
# Review past War Room sessions
/memory-palace:strategeion list
# Archive completed campaign
/memory-palace:strategeion archive {session-id} --project payments
# Extract patterns to doctrine
/memory-palace:strategeion doctrine --extract {session-id}Escalation
Automatic (RS-Based)
Mode is automatically selected based on Reversibility Score:
- RS ≤ 0.40 → Express mode (or skip War Room entirely)
- RS 0.41-0.60 → Lightweight panel
- RS 0.61-0.80 → Full Council
- RS > 0.80 → Full Council + Delphi
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is War Room?
War Room is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Convene a multi-LLM expert panel to pressure-test strategic decisions with adversarial review and reversibility assessment.
How do I install War Room in Claude Code?
Download war-room.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.
Can I use War Room in Claude Cowork?
Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.
Is War Room safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Arch Init Initialize projects with architecture-aware templates using paradigm research and selection guidance for the target domain. Slash Command · athola/claude-night-market
- Archetypes Architecture paradigm selection and implementation planning for software systems Plugin · athola/claude-night-market
- Blast Radius Reviewer Review code changes using blast radius analysis from the code knowledge graph. Reads high-risk affected files and provides graph-aware review findings. Subagent · athola/claude-night-market
- Brainstorm Guide project ideation through Socratic questioning to generate briefs with validated approaches and decision rationale. Slash Command · athola/claude-night-market
- Update Scaffold Check for and apply myPKA scaffold framework updates safely. Shows a plain-English plan first (what is new, what changed, and confirms… Slash Command · myICOR/myPKA
- Voice Review Review existing text against a voice profile Slash Command · athola/claude-night-market
- Voice Learn Run learning pass on manually edited text to improve voice profile Slash Command · athola/claude-night-market
- Voice Generate Generate text in your extracted writing voice Slash Command · athola/claude-night-market