war-roomMulti-agent war room for brainstorming, system design, architecture review, product specs, business strategy, or any complex problem. Use when a user wants to run a structured multi-agent session with specialist roles, when they mention "war room", when they need to brainstorm a project from scratch, design a system with multiple perspectives, stress-test decisions with a devil's advocate, or produce a comprehensive blueprint/spec. Works for software, hardware, content, business — any domain.
Install via ClawdBot CLI:
clawdbot install maxkle1nz/war-roomA methodology for running multi-agent brainstorming and execution sessions. Specialist agents collaborate via shared filesystem in dependency-ordered waves. A CHAOS agent (devil's advocate) shadows every wave. Output: decisions log, specialist docs, consolidated blueprint, post-mortem.
bash skills/war-room/scripts/init_war_room.sh to create the project folder structure under war-rooms// .war-rooms//BRIEF.md with the project description, goals, constraints, and known risks.skills/war-room/references/dna-template.md → war-rooms//DNA.md . Customize if needed (add project-specific identity, owner name).war-rooms//artifacts/ .war-rooms//lessons/ .Full protocol details: wave-protocol.md
Before any spec work, identify the single riskiest assumption and test it with real work (code spike, prototype, market research, etc.). 30 min max. If it fails, pivot BEFORE spending tokens on detailed specs.
Each wave deploys a group of agents that can work in parallel (no inter-dependencies within a wave). Agents in later waves depend on earlier waves' outputs.
Planning a wave:
Each agent in a wave:
BRIEF.md, DNA.md, DECISIONS.md, and any prior agents' output foldersagents// — their specs, findings, decisionsDECISIONS.md (their domain decisions), STATUS.md (their completion status)comms/ for cross-agent questions/challengesSpawning agents: Each agent is a subagent. Its system prompt includes:
DNA.md)Before launching each new wave, ask: "Has any fundamental assumption changed since the last wave?"
VOIDED in DECISIONS.md.CHAOS is not a separate wave — it shadows all waves. After each wave completes, CHAOS:
agents/chaos/challenges.md[C-ID] CHALLENGE to D### — attack — verdict (SURVIVE/WOUNDED/KILLED)CHAOS also writes counter-proposals when it sees a fundamentally better path.
One agent (or the orchestrator) merges all specialist outputs into a single blueprint:
agents/*/ outputsartifacts/-BLUEPRINT.md After consolidation, write lessons/session-N-postmortem.md:
Not every project needs every role. Match roles to scope:
| Project Type | Typical Agents |
|---|---|
| Software MVP | ARCH, PM, DEV, UX, SEC, QA, CHAOS |
| Business strategy | PM, RESEARCH, FINANCE, MKT, LEGAL, CHAOS |
| Content/creative | PM, UX, RESEARCH, MKT, CHAOS |
| Hardware/IoT | ARCH, DEV, OPS, SEC, QA, CHAOS |
| Architecture review | ARCH, SEC, OPS, QA, CHAOS |
CHAOS is always included. It's the immune system.
Full role descriptions and briefing templates: agent-roles.md
All inter-agent communication uses the filesystem. Zero extra token cost.
| File | Purpose | Who writes |
|---|---|---|
| BRIEF.md | Project description and constraints | Orchestrator (you) |
| DNA.md | Shared mindset injected into all agents | Orchestrator (immutable during session) |
| DECISIONS.md | Append-only decision log | Each agent (own domain only) |
| STATUS.md | Agent completion status | Each agent |
| BLOCKERS.md | Blockers requiring orchestrator action | Any agent |
| TLDR.md | Executive summary (updated after consolidation) | Orchestrator |
| comms/ | Cross-agent messages and challenges | Any agent |
| agents/ | Agent-specific outputs | Owning agent only |
[D###] OWNER — what was decided — why (1 sentence each)Cap at ~25 decisions per session. More = scope too big, split the session. Only log decisions that constrain future work. Implementation details are not decisions.
FROM: {role}
TO: {target} | ALL | LEAD
TYPE: FINDING | QUESTION | DECISION | BLOCKER | UPDATE | CHALLENGE
PRI: LOW | MED | HIGH | CRIT
---
{content — max 200 words}
---
FILES: [{paths}]The war room doesn't stop at the blueprint. After consolidation, suggest concrete next actions and offer to execute them using the same agents:
"Based on the war room results, I can:"
├── 📄 Generate a complete PRD (Product Requirements Document)
├── 💻 Scaffold the project (Xcode, npm init, cargo new, etc.)
├── 🎨 Create detailed mockups/wireframes
├── 📋 Create a task board (Linear, GitHub Issues)
├── 🔍 Run specific research (trademark, competitive, market)
├── 🌐 Build a landing page
├── 🧪 Run Wave 0 proof-of-concept
├── 📊 Deep-dive on any specialist's area
└── [Any domain-specific deliverable]The key insight: agents that DESIGNED the system can also PRODUCE deliverables from it. The war room is a pipeline, not an event. Brainstorm → Plan → Build → Ship.
When executing Phase 3, spawn agents with the full war room context (blueprint + decisions + specialist docs) so they build ON the decisions, not from scratch.
The standard War Room builds UPWARD (from zero to product). The Reverse War Room builds DOWNWARD (from the final product to current reality). Use both together for maximum clarity.
When to use: When you already have a prototype or partial build and need to find the fastest path to a paying customer or shipped product.
Agents:
Key outputs:
Track record: First tested on KOSMO (Feb 8, 2026). Found: 30 gaps, killed 10 unnecessary features (~20h saved), identified root cause ("engineering without a customer"), wrote realistic obituary that prevented premature scaling.
The INTERCEPTOR is the War Room's interface and autonomy layer. It manages the session, communicates with the Operator, and never stops.
██ EXEC — Agents working. Processing. Shipping.
██ AWAIT — Blocked on OPERATOR decision. Presents options. Waits.
██ WATCH — All tasks complete or agents running. Sets cron auto-wake.To maintain session continuity when agents are processing asynchronously:
This ensures the war room session remains responsive without requiring the operator to manually poll for results. All scheduling is handled through the standard OpenClaw cron API with operator-visible job management.
When the war room produces visual artifacts (images, diagrams, blueprints), present them to the operator using the platform's standard file viewer:
open command to display artifacts in the default viewer (Preview, Finder)xdg-open for the same purposeINTERCEPTOR communicates in terminal aesthetic:
When a decision requires the Operator:
The DNA is what makes the war room special. Every principle is a mandatory protocol — not decoration.
19 protocols across 4 pillars:
Full DNA template with all protocol formats: dna-template.md
Generated Mar 1, 2026
A startup wants to build a minimum viable product for a new SaaS platform. The war room orchestrates agents like ARCH, PM, DEV, UX, SEC, and QA to design architecture, define features, and ensure security, with CHAOS stress-testing assumptions to avoid costly pivots later.
A company planning to enter a new market uses the war room with PM, RESEARCH, FINANCE, MKT, and LEGAL agents to analyze competition, financial viability, and regulatory risks, while CHAOS challenges strategic decisions to uncover blind spots.
An IoT device manufacturer employs the war room with ARCH, DEV, OPS, SEC, and QA agents to prototype hardware-software integration, optimize operations, and test security, with CHAOS identifying vulnerabilities before production.
An enterprise needs to modernize an outdated software system. The war room uses ARCH, SEC, OPS, and QA agents to assess current architecture, plan migration, and ensure compliance, with CHAOS probing for hidden risks in the transition.
A marketing agency creates a multi-channel content strategy. The war room coordinates PM, UX, RESEARCH, and MKT agents to define audience personas, content themes, and distribution, with CHAOS questioning engagement assumptions to refine the approach.
Offer war room sessions as a paid service for businesses needing structured problem-solving. Charge per project or subscription for ongoing support, leveraging the multi-agent methodology to deliver high-value blueprints and reduce client risk.
Embed the war room skill into a larger AI platform as a premium feature. Users pay monthly for access to automated brainstorming and execution tools, with tiered pricing based on session complexity and agent roles used.
Sell training programs and certifications on using the war room methodology for teams. Include workshops, materials, and access to templates, generating revenue from course fees and certification renewals.
💬 Integration Tip
Start by integrating the war room into existing project management workflows; use the wave protocol to break down complex tasks into manageable agent-driven steps, ensuring clear dependencies and regular pivot checks.
Create jobs and transact with other specialised agents through the Agent Commerce Protocol (ACP) — extends the agent's action space by discovering and using agents on the marketplace, enables launching an agent token for fundraising and revenue, and supports registering service offerings to sell capabilities to other agents.
Write, structure, and update a business plan for a solopreneur. Use when creating a plan from scratch, updating an existing plan after a pivot or new phase, or preparing a plan to share with investors, partners, or even just to clarify your own strategy. Covers executive summary, market analysis, competitive positioning, revenue model, operations plan, financial projections, and risk assessment — all adapted for a one-person business. Trigger on "write a business plan", "business plan", "create my plan", "business plan template", "update my business plan", "plan for my business", "investor pitch plan".
Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.
Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design.
B2B SaaS competitive intelligence with 24 scenarios across Sales/HR/Fintech/Ops Tech
Be the CFO with financial planning, cash management, fundraising, capital allocation, and strategic financial leadership.