К основному содержанию
скилл CX Codex

war-room — скилл для Claude Code: что делает и как установить

Скилл war-room созывает совет из нескольких LLM для проверки труднообратимых архитектурных решений через оценку обратимости и оппонирование.

MIT 1 установок ★ 350 обновлён 2026-10-29

Установить в Claude Code · Через Skills CLI (Vercel) Все способы и платформы ↓
npx skills add athola/claude-night-market --skill war-room -a claude-code
Открыть на GitHub

Что делает war-room

Скилл оценивает показатель обратимости по пяти факторам: цене отката, временной блокировке, радиусу поражения, потере данных и репутационным рискам. При минимальном риске задача решается в экспресс-режиме за пару минут. Для критичных изменений с показателем выше 0.60 запускается совет из семи специализированных ролей: от стратега и разведчика до Red Team.

Внутри действует двухэтапный регламент. Сначала собираются разведданные и варианты действий, затем Red Team атакует слабые места, проводится премортем-анализ и верховный координатор на базе Claude Opus сводит итоги. Если моделей не хватает, система прямо сообщает об ошибке делегирования и не позволяет одной Claude имитировать консенсус нескольких систем.

Для запуска панели нужны внешние провайдеры через conjure:delegation-core (Gemini, Qwen, GLM-5.3). Сессии и доктрины сохраняются локально по пути ~/.claude/memory-palace/strategeion/.

Какие задачи решает

  • Рассчитать индекс обратимости архитектурного решения перед изменениями
  • Провести оппонирующий анализ вариантов силами независимых моделей
  • Выявить скрытые сценарии сбоев через премортем-сессию
  • Организовать коллегию экспертов перед сложной миграцией базы данных

Примеры запросов агенту

  • /attune:war-room "Какую архитектуру выбрать для новой платёжной системы?"
  • /attune:war-room "Оптимизация схемы API" --files src/api/**/*.py
  • /attune:war-room "Миграция базы данных на MongoDB" --assess-only

Как установить war-room

1Через Skills CLI (Vercel)

npx skills add athola/claude-night-market --skill war-room -a claude-code

2Вручную: положить файлы

~/.claude/skills/war-room/SKILL.md

Папка скилла целиком; для одного проекта — .claude/skills/war-room/

По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов

Вопросы о war-room

Как установить war-room в Claude Code?

Выполните команду npx skills add athola/claude-night-market --skill war-room -a claude-code. Файл скилла запишется в ~/.claude/skills/war-room/SKILL.md.

Что делает скилл war-room?

Он созывает коллегию из нескольких моделей для поиска рисков, встречной критики и выработки итоговой стратегии по сложным задачам.

Что произойдёт, если сторонние модели недоступны?

Скилл остановит процесс и перечислит недоступные сервисы. Он принципиально отказывается заполнять все места одной моделью Claude, чтобы не имитировать искусственное единодушие.

Исходный текст

SKILL.md · MIT
---
name: war-room
description: Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions. Use when reversibility score is low and adversarial review is warranted.
alwaysApply: false
# Custom metadata (not used by Claude for matching):
category: strategic-planning
tags: [deliberation, multi-llm, strategy, decision-making, council, reversibility]
complexity: advanced
model_hint: deep
estimated_tokens: 2500
progressive_loading: true
modules:
  - modules/reversibility-assessment.md
  - modules/expert-roles.md
  - modules/deliberation-protocol.md
  - modules/merkle-dag.md
  - modules/discussion-publishing.md
  - modules/deferred-capture.md
  - modules/configuration.md
dependencies:
  - conjure:delegation-core
  - leyline:git-platform
tools: []
role: entrypoint
---
## Overview

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.

### Philosophy

> "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

## Reversibility-Based Routing

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:**
- Can be A/B tested? → Type 2
- Requires data migration? → Type 1
- Public commitment required? → Type 1A+

See `modules/reversibility-assessment.md` for full scoring guide.

## When To Use

- Architectural decisions with major trade-offs
- Multi-stakeholder problems requiring diverse perspectives
- High-stakes choices with significant consequences (RS > 0.60)
- Novel problems without clear precedent
- When brainstorming produces multiple strong competing approaches

## When NOT To Use

- Simple questions with obvious answers
- Routine implementation tasks
- Well-documented patterns with clear solutions
- Time-critical decisions requiring immediate action
- **Type 2 decisions** (RS ≤ 0.40): use Express mode or skip War Room entirely

## Expert Panel

### Default (Lightweight Mode)

| 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 |

### Full Council (Escalated)

| Role | Model | Purpose |
|------|-------|---------|
| Supreme Commander | Claude Opus | Final synthesis |
| Chief Strategist | Claude Sonnet | Approach generation |
| Intelligence Officer | Gemini 3.1 Pro (preview) | Large context analysis (1M) |
| Field Tactician | GLM-5.3 | Implementation feasibility |
| Scout | Qwen `coder-model` | Quick data gathering |
| Red Team Commander | Gemini 3.8 Flash | Adversarial challenge |
| Logistics Officer | Qwen `coder-model` | Resource estimation |

## Deliberation Protocol

### Two-Round Default

```
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
  - Phase 8: Discussion Publishing
```

### Delphi Extension (High-Stakes)

For high-stakes decisions, extend to iterative Delphi convergence:
- Multiple rounds until expert consensus
- Convergence threshold: 0.85

## Integration

### With Brainstorm

**War Room is AUTOMATICALLY INVOKED** from `Skill(attune:project-brainstorming)` after Phase 3 (Approach Generation).

The brainstorm skill passes all context to War Room:
- Problem statement and constraints
- Generated approaches with pros/cons
- Comparison matrix
- Reversibility assessment (automatically calculated)

**Bypass conditions** (only if ALL true):
- RS ≤ 0.40 (Type 2 decision - clearly reversible)
- Single obvious approach with no meaningful trade-offs
- Low complexity with well-documented pattern
- User explicitly declines after seeing RS assessment

```bash
# 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?"
```

### With Memory Palace

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
```

### With Conjure

Experts are invoked via conjure delegation:
- `conjure:gemini-delegation` for Gemini models
- `conjure:qwen-delegation` for Qwen models
- Direct CLI for GLM-5.3 (`ccgd` or `claude-glm`, via `get_glm_command()`)

Delegation being on by default changes nothing here, because a War Room
delegates by construction: a panel is external models or it is not a
panel.

What does change is the fallback. `conjure:delegation-core` now returns
a `fallback_reason` instead of raising when no provider answers or when
an operator has declined delegation, and Claude answering every seat is
the wrong way to spend that result.

**A panel that could not reach external models is not a panel.** When
delegation is off or the chain is exhausted:

1. Say so before deliberating, naming the reason and the providers tried.
2. Do not fill the empty seats with Claude and present the output as a
   multi-model panel. Seven roles played by one model produce agreement
   that looks like consensus and is not.
3. Offer the choice: run a single-model review labeled as one, or stop
   until a provider is available.

This is the one place in the repository where a silent local fallback
would misrepresent the result rather than merely slow it down.

## Usage

### Basic Invocation

```bash
/attune:war-room "What architecture should we use for the new payment system?"
```

### With Context

```bash
/attune:war-room "Best approach for API versioning" --files src/api/**/*.py
```

### Reversibility Assessment Only

Quick assessment without full deliberation:

```bash
/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]
```

### Force Express Mode (Type 2)

Skip to rapid decision for clearly reversible choices:

```bash
/attune:war-room "Which logging library to use" --express
```

### Force Full Council

Override RS assessment for critical decisions:

```bash
/attune:war-room "Migration strategy" --full-council
```

### Delphi Mode

For highest-stakes irreversible decisions:

```bash
/attune:war-room "Long-term platform decision" --delphi
```

### Resume Session

```bash
/attune:war-room --resume war-room-20260120-153022
```

## Output

### Decision Document

The War Room produces a Supreme Commander Decision document:

```markdown
## 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]
```

### Session Artifacts

Saved to Strategeion:
- Intelligence reports
- Situation assessment
- All COAs (with full attribution after unsealing)
- Red Team challenges
- Premortem analysis
- Final decision

### Record the Tradeoff (decision journal)

The Supreme Commander Decision is a tradeoff record by construction: a selected
approach, the COAs weighed against it, and the dissenting views. Mirror it into
`docs/tradeoffs.md` so the reasoning stays with the code, not only in
Strategeion (draft and confirm):

- If leyline is installed, invoke `Skill(leyline:decision-journal)` and append
  a tradeoff entry. Map directly: Selected Approach to `decision`, the RS and
  rationale to a Y-statement, the rejected COAs to `options`, and Dissenting
  Views to `consequences_negative`. Set `phase` to the originating phase (for
  example `plan`). Record the RS in the entry links. Append on confirmation.
- Fallback (leyline absent): append to `docs/tradeoffs.md` using the in-file
  ENTRY TEMPLATE; assign the next `TR-NNN` id.

If the decision is architectural enough to warrant a numbered ADR in
`docs/adr/`, write the ADR and reference its number from the tradeoff entry
rather than duplicating it.

## Anonymization

Expert contributions are anonymized during deliberation using Merkle-DAG:
- Responses labeled as "Response A, B, C..." during review
- Attribution revealed only after decision is made
- Hash verification ensures integrity

See `modules/merkle-dag.md` for details.

## Escalation

### Automatic (Reversibility-Based)

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 and Delphi |

### Manual Override

The Supreme Commander may override automatic classification when:
- High complexity detected (multiple architectural trade-offs)
- Significant disagreement between initial experts
- Novel problem domain requiring specialized analysis
- Precedent-setting decision (future decisions will follow pattern)
- Political/organizational sensitivity beyond technical scope

**Escalation requires written justification with RS assessment.**

### De-escalation

Equally important: identify decisions being over-deliberated:
- If RS ≤ 0.40, recommend Express mode or immediate execution
- Challenge "false irreversibility" ("we can't change this later" without evidence)
- Track de-escalation rate as team health metric

## Configuration

User settings and the hook auto-trigger conditions:
[`modules/configuration.md`](modules/configuration.md).

## Agent Teams Execution Mode

### Overview

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.

### When Agent Teams Helps

| 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.

### Team Configuration

```bash
# 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.

### Deliberation Flow with Agent Teams

1. **Lead creates team** → spawns teammates in tmux panes
2. **Phase 1 (Intel)**: Lead assigns intel tasks to scout and intel-officer via inbox
3. **Phase 3 (COA)**: Lead broadcasts situation assessment; teammates develop COAs independently; messaging allows clarifying questions mid-development
4. **Phase 4 (Red Team)**: Red-team teammate receives all COAs, posts challenges; other teammates can **respond to challenges in real-time**
5. **Phase 5 (Voting)**: Lead broadcasts ballot; teammates rank via inbox messages
6. **Phase 6 (Premortem)**: All teammates receive selected COA; can build on each other's failure scenarios
7. **Phase 7 (Synthesis)**: Lead collects all artifacts, produces decision
8. **Phase 8 (Discussion Publishing)**: After the
   Supreme Commander Decision document is finalized,
   you MUST execute `modules/discussion-publishing.md`
   to publish the decision to GitHub Discussions.
   Publishing is the default. The user can decline
   with "n". See the "Discussion Publishing (REQUIRED)"
   section below for the full step-by-step workflow.

### Falling Back to Conjure Delegation

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.

### Cost Considerations

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.

### Discussion Publishing (REQUIRED)

After Phase 7 synthesis completes (in any execution
mode), you MUST execute the discussion publishing
workflow. This is not optional unless the user
explicitly declines.

**Execute these steps in order:**

1. Read `modules/discussion-publishing.md` for the
   full GraphQL workflow
2. Ask the user: "Publishing this decision to GitHub
   Discussions. [Y/n]"
3. If the user says "n", skip to Related Skills.
   Otherwise proceed with steps 4-6.
4. Run the `gh api graphql` commands from the module
   to create a Discussion in the "Decisions" category
5. Post phase summaries as threaded comments on the
   Discussion
6. Update the local strategeion file with the
   Discussion URL

If GitHub Discussions are unavailable (non-GitHub
platform, Discussions disabled, `gh` not authenticated),
warn the user and skip. Publishing failures never
block the war room workflow.

## Exit Criteria

- [ ] A Reversibility Score and decision type are computed and recorded.
- [ ] A Supreme Commander Decision document with a selected approach,
  rationale, and dissenting views is produced.
- [ ] The decision is mirrored to `docs/tradeoffs.md` (and to a numbered ADR
  in `docs/adr/` if architectural).
- [ ] Premortem watch points and, for Type 1 decisions, a reversal plan are
  captured.

## Related Skills

- `Skill(attune:project-brainstorming)` - Pre-War Room ideation
- `Skill(imbue:scope-guard)` - Scope management
- `Skill(imbue:rigorous-reasoning)` - Reasoning methodology
- `Skill(conjure:delegation-core)` - Expert dispatch
- `Skill(conjure:agent-teams)` - Agent teams coordination (Full Council / Delphi)

## Related Commands

- `/attune:war-room` - Invoke this skill
- `/attune:brainstorm` - Pre-War Room ideation

## References

### Strategic Foundations
- Sun Tzu - Art of War (intelligence gathering)
- Clausewitz - On War (friction and fog)
- Robert Greene - 33 Strategies of War (unity of command)
- MDMP - U.S. Army (structured decision process)
- Gary Klein - Premortem (failure mode analysis)
- Karpathy - LLM Council (anonymized peer review)

### Reversibility Framework
- [Jeff Bezos - Type 1 vs Type 2 Decisions](https://ashikuzzaman.com/2025/03/03/amazons-type-1-vs-type-2-decisions-a-framework-for-effective-decision-making/) (Amazon shareholder letters)
- [Farnam Street - Reversible and Irreversible Decisions](https://fs.blog/reversible-irreversible-decisions/) (STOP-LOP-KNOW framework)
- [Tapan Desai - One-Way and Two-Way Door Decision-Making](https://tapandesai.com/one-way-two-way-doors-decision-making/) (practical application)

© athola · MIT · athola/claude-night-market

Похожие скиллы

Все скиллы по теме «Настройка агента: память, контекст, субагенты» →
scenario-war-room Alireza Rezvani Скилл scenario-war-room для Claude Code моделирует цепочки последствий, когда несколько рисков могут сработать одновременно. Он подключается к сложным сценариям и стратегическим решениям с серьёзными рисками. CX Codex +1 574установок product-launch-war-room OneWave-AI Скилл product-launch-war-room для Claude Code собирает экспертные и клиентские мнения о запуске и выдаёт решение с планом выката. Запускайте его перед запуском продукта, сменой цены или позиционирования. CX Codex +1 159установок maoxuan-skill-cognitive-framework reason-machines Скилл maoxuan-skill-cognitive-framework, который даёт агенту набор моделей мышления из работ Мао Цзэдуна: искать главное противоречие, строить стратегию от слабой стороны, собирать союзников. CX Codex +1 520установок boardroom Alireza Rezvani Скилл boardroom собирает совет из C-level агентов над одним стратегическим брифом и выдаёт меморандум с голосами, разногласиями и критериями остановки. CX Codex +1 421установок strategy-red-team phuryn Скилл strategy-red-team проверяет PRD и стратегии на прочность: находит ключевые допущения, атакует их сильные версии и предлагает дешёвые проверки. CX Codex +1 9 700установок strategy-board tronghieu Скилл strategy-board для Claude Code собирает виртуальный совет профильных субагентов для проверки бизнес-решений, оценки рисков и подготовки стратегических презентаций. CX Codex +1 ★ 117звёзд репо

Из того же набора7

war-room-checkpoint Скилл war-room-checkpoint считает, насколько дорого откатить решение, и решает, нужен ли полный разбор War Room или хватит быстрой рекомендации. CX Codex +1 2установок shell-review Скилл shell-review аудирует шелл-скрипты на маскировку кодов возврата, переносимость POSIX и безопасность перед коммитом. CX Codex +1 1установок review-chamber Скилл review-chamber сохраняет важные выводы из ревью PR и помогает находить их при дальнейшей работе. Подходит для фиксации архитектурных решений, повторяющихся проблем и стандартов кода. CX Codex +1 1установок delegation-core Скилл delegation-core делегирует задачи восьми внешним CLI (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer). Оставляет проектирование и архитектуру локально, отправляет исполнение. CX Codex +1 1установок skills-eval Скилл skills-eval для Claude Code проверяет структуру, расход токенов и интеграцию инструментов в других скиллах. Находит проблемы и составляет план исправлений. CX Codex +1 1установок precommit-setup Скилл precommit-setup настраивает трёхуровневую систему pre-commit хуков: линтинг, проверку типов и тесты перед каждым коммитом. CX Codex +1 1установок

Спонсоры проекта

Компании, которые помогают держать аналитику открытой