Claude Code Game Studios — 리서치 노트
조회일: 2026-03-23 출처: https://github.com/Donchitos/Claude-Code-Game-Studios 저장소 설명: Turn Claude Code into a full game dev studio — 48 AI agents, 36 workflow skills, and a complete coordination system mirroring real studio hierarchy.
저장소 기본 정보
| 항목 | 내용 |
|---|---|
| 소유자 | Donchitos |
| 생성일 | 2026-02-12 |
| 최근 업데이트 | 2026-03-22 |
| Stars | 2,162 |
| Forks | 277 |
| 주요 언어 | Shell |
| 라이선스 | MIT |
| 템플릿 저장소 | Yes |
| 토픽 | ai-agents, anthropic, claude, claude-code, game-development, godot, unity, unreal-engine 외 |
README 전문
Claude Code Game Studios
Turn a single Claude Code session into a full game development studio.
48 agents. 37 workflows. One coordinated AI team.
Why This Exists
Building a game solo with AI is powerful — but a single chat session has no structure. No one stops you from hardcoding magic numbers, skipping design docs, or writing spaghetti code. There’s no QA pass, no design review, no one asking “does this actually fit the game’s vision?”
Claude Code Game Studios solves this by giving your AI session the structure of a real studio. Instead of one general-purpose assistant, you get 48 specialized agents organized into a studio hierarchy — directors who guard the vision, department leads who own their domains, and specialists who do the hands-on work. Each agent has defined responsibilities, escalation paths, and quality gates.
The result: you still make every decision, but now you have a team that asks the right questions, catches mistakes early, and keeps your project organized from first brainstorm to launch.
What’s Included
| Category | Count | Description |
|---|---|---|
| Agents | 48 | Specialized subagents across design, programming, art, audio, narrative, QA, and production |
| Skills | 37 | Slash commands for common workflows (/start, /sprint-plan, /code-review, /brainstorm, etc.) |
| Hooks | 8 | Automated validation on commits, pushes, asset changes, session lifecycle, agent audit, and gap detection |
| Rules | 11 | Path-scoped coding standards enforced when editing gameplay, engine, AI, UI, network code, and more |
| Templates | 29 | Document templates for GDDs, ADRs, sprint plans, economy models, faction design, and more |
Studio Hierarchy
Agents are organized into three tiers, matching how real studios operate:
Tier 1 — Directors (Opus)
creative-director technical-director producer
Tier 2 — Department Leads (Sonnet)
game-designer lead-programmer art-director
audio-director narrative-director qa-lead
release-manager localization-lead
Tier 3 — Specialists (Sonnet/Haiku)
gameplay-programmer engine-programmer ai-programmer
network-programmer tools-programmer ui-programmer
systems-designer level-designer economy-designer
technical-artist sound-designer writer
world-builder ux-designer prototyper
performance-analyst devops-engineer analytics-engineer
security-engineer qa-tester accessibility-specialist
live-ops-designer community-manager
Engine Specialists
| Engine | Lead Agent | Sub-Specialists |
|---|---|---|
| Godot 4 | godot-specialist | GDScript, Shaders, GDExtension |
| Unity | unity-specialist | DOTS/ECS, Shaders/VFX, Addressables, UI Toolkit |
| Unreal Engine 5 | unreal-specialist | GAS, Blueprints, Replication, UMG/CommonUI |
Slash Commands (37개)
Reviews & Analysis
/design-review /code-review /balance-check /asset-audit /scope-check /perf-profile /tech-debt
Production
/sprint-plan /milestone-review /estimate /retrospective /bug-report
Project Management
/start /project-stage-detect /reverse-document /gate-check /map-systems /design-system
Release
/release-checklist /launch-checklist /changelog /patch-notes /hotfix
Creative
/brainstorm /playtest-report /prototype /onboard /localize
Team Orchestration (coordinate multiple agents on a single feature)
/team-combat /team-narrative /team-ui /team-release /team-polish /team-audio /team-level
Getting Started
Prerequisites
- Git
- Claude Code (
npm install -g @anthropic-ai/claude-code) - Recommended: jq (for hook validation) and Python 3 (for JSON validation)
Setup
git clone https://github.com/Donchitos/Claude-Code-Game-Studios.git my-game
cd my-game
claudeRun /start — the system asks where you are and guides you to the right workflow.
How It Works
Agent Coordination
- Vertical delegation — directors delegate to leads, leads delegate to specialists
- Horizontal consultation — same-tier agents can consult each other but can’t make binding cross-domain decisions
- Conflict resolution — disagreements escalate up to the shared parent
- Change propagation — cross-department changes are coordinated by
producer - Domain boundaries — agents don’t modify files outside their domain without explicit delegation
Collaborative, Not Autonomous
Every agent follows a strict collaboration protocol:
- Ask — agents ask questions before proposing solutions
- Present options — agents show 2-4 options with pros/cons
- You decide — the user always makes the call
- Draft — agents show work before finalizing
- Approve — nothing gets written without your sign-off
Automated Safety (Hooks)
| Hook | Trigger | What It Does |
|---|---|---|
validate-commit.sh | git commit | Checks for hardcoded values, TODO format, JSON validity, design doc sections |
validate-push.sh | git push | Warns on pushes to protected branches |
validate-assets.sh | File writes in assets/ | Validates naming conventions and JSON structure |
session-start.sh | Session open | Loads sprint context and recent git activity |
detect-gaps.sh | Session open | Detects fresh projects and missing documentation |
pre-compact.sh | Context compression | Preserves session progress notes |
session-stop.sh | Session close | Logs accomplishments |
log-agent.sh | Agent spawned | Audit trail of all subagent invocations |
Path-Scoped Rules
| Path | Enforces |
|---|---|
src/gameplay/** | Data-driven values, delta time usage, no UI references |
src/core/** | Zero allocations in hot paths, thread safety, API stability |
src/ai/** | Performance budgets, debuggability, data-driven parameters |
src/networking/** | Server-authoritative, versioned messages, security |
src/ui/** | No game state ownership, localization-ready, accessibility |
design/gdd/** | Required 8 sections, formula format, edge cases |
tests/** | Test naming, coverage requirements, fixture patterns |
prototypes/** | Relaxed standards, README required, hypothesis documented |
Design Philosophy
- MDA Framework — Mechanics, Dynamics, Aesthetics analysis for game design
- Self-Determination Theory — Autonomy, Competence, Relatedness for player motivation
- Flow State Design — Challenge-skill balance for player engagement
- Bartle Player Types — Audience targeting and validation
- Verification-Driven Development — Tests first, then implementation
파일 구조
Claude-Code-Game-Studios/
├── CLAUDE.md # Master configuration
├── UPGRADING.md # 버전 마이그레이션 가이드
├── LICENSE # MIT License
├── Claude Code Game Studios.code-workspace
├── .gitignore
├── .claude/
│ ├── settings.json # Hooks, permissions, safety rules
│ ├── agents/ # 48 agent definitions
│ ├── skills/ # 37 slash commands
│ ├── hooks/ # 8 hook scripts
│ ├── rules/ # 11 path-scoped coding standards
│ └── docs/
│ ├── quick-start.md
│ ├── agent-roster.md
│ ├── agent-coordination-map.md
│ ├── setup-requirements.md
│ └── templates/ # 28 document templates
├── .github/
├── docs/
│ ├── COLLABORATIVE-DESIGN-PRINCIPLE.md
│ ├── WORKFLOW-GUIDE.md
│ ├── session-state/
│ ├── engine-reference/
│ └── examples/
├── production/ # Sprint plans, milestones, release tracking
├── src/ # Game source code
├── assets/ # Art, audio, VFX, shaders, data files
├── design/ # GDDs, narrative docs, level designs
├── tests/ # Test suites
├── tools/ # Build and pipeline tools
└── prototypes/ # Throwaway prototypes
에이전트 전체 목록 (48개)
Tier 1 — Directors
creative-directortechnical-directorproducer
Tier 2 — Department Leads
art-directoraudio-directorgame-designerlead-programmerlocalization-leadnarrative-directorqa-leadrelease-manager
Tier 3 — Specialists
accessibility-specialistai-programmeranalytics-engineercommunity-managerdevops-engineereconomy-designerengine-programmergameplay-programmerlevel-designerlive-ops-designernetwork-programmerperformance-analystprototyperqa-testersecurity-engineersound-designersystems-designertechnical-artisttools-programmerui-programmerux-designerworld-builderwriter
Engine Specialists — Godot 4
godot-specialistgodot-gdscript-specialistgodot-shader-specialistgodot-gdextension-specialist
Engine Specialists — Unity
unity-specialistunity-dots-specialistunity-shader-specialistunity-addressables-specialistunity-ui-specialist
Engine Specialists — Unreal Engine 5
unreal-specialistue-gas-specialistue-blueprint-specialistue-replication-specialistue-umg-specialist
Skills (Slash Commands) 전체 목록 (37개)
| 스킬명 | 카테고리 |
|---|---|
architecture-decision | Project Management |
asset-audit | Reviews & Analysis |
balance-check | Reviews & Analysis |
brainstorm | Creative |
bug-report | Production |
changelog | Release |
code-review | Reviews & Analysis |
design-review | Reviews & Analysis |
design-system | Project Management |
estimate | Production |
gate-check | Project Management |
hotfix | Release |
launch-checklist | Release |
localize | Creative |
map-systems | Project Management |
milestone-review | Production |
onboard | Creative |
patch-notes | Release |
perf-profile | Reviews & Analysis |
playtest-report | Creative |
project-stage-detect | Project Management |
prototype | Creative |
release-checklist | Release |
retrospective | Production |
reverse-document | Project Management |
scope-check | Reviews & Analysis |
setup-engine | Project Management |
sprint-plan | Production |
start | Project Management |
team-audio | Team Orchestration |
team-combat | Team Orchestration |
team-level | Team Orchestration |
team-narrative | Team Orchestration |
team-polish | Team Orchestration |
team-release | Team Orchestration |
team-ui | Team Orchestration |
tech-debt | Reviews & Analysis |
이 문서는 GitHub API를 통해 자동으로 생성되었습니다.