Claude Code Solo Studio
Ghraven/Claude-Code-Solo-Studio
6 agentes, zero overhead — 95% de tokens para código de jogo
Ver no GitHubTemplate otimizado para game devs solo que trabalham com Claude Code, reduzindo overhead de tokens através de 6 agentes especializados sem hierarquia e 10 comandos práticos. Suporta Godot 4 e Unity com setup automático baseado em plataforma, dimensão e gênero.
Instalação
npx convez-ai Ghraven/Claude-Code-Solo-Studio1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Desenvolvimento de jogos 2D/3D indie com orçamento de tokens limitado
- Prototipagem rápida com setup automático por plataforma e gênero
- Code review, QA e otimização de performance em projeto solo
Veredito

Solução prática que inverte o problema usual de templates multi-agente (overhead de coordenação) focando em maximizar tokens para código real. Bem estruturado para o caso específico de devs solo com limites semanais de API, embora exija familiaridade com Claude Code e engines de jogo.
README
A tradução para o português deste README ainda está na fila.
v1.2 — Session-stop hook now warns about uncommitted changes. GDD gains a monetization section for mobile devs.
game-designergets mobile interruption design guidance.new-featureskill scans Known Issues before starting work.qa-checkcross-references Known Issues to avoid duplicate bug reports.
The Problem
Most AI coding templates burn your token budget on coordination before a single line of code gets written. 49 agents debating with directors and leads just to decide what to do next works great for a studio with unlimited API credits.
For a solo dev on a weekly limit, it burns your cap with nothing to show.
The Solution
This template strips everything down to what actually matters:
| Typical multi-agent | Solo Studio | |
|---|---|---|
| Agents | 20–49 | 6 |
| Hierarchy | Director → Lead → Worker | None — direct specialists |
| Inter-agent calls | Constant | Zero |
| Slash commands | 20+ | 10 practical ones |
| Token overhead | High | Near zero |
| Token budget going to code | ~30–50% | ~95% |
6 specialists. No hierarchy. No coordination overhead. Nearly 100% of your tokens go to actual game code.
Quick Start
Prerequisites
- Claude Code —
npm install -g @anthropic-ai/claude-code - Godot 4 or Unity installed
- Git
Setup
git clone https://github.com/Ghraven/Claude-Code-Solo-Studio my-game
cd my-game
claude
Then in Claude Code:
/setup
Answer 4 questions. Your project is ready in seconds.
/setup — What It Does
The setup command asks:
- Platform — Android · PC · Web
- Dimension — 2D · 3D
- Genre — Platformer · RPG · Puzzle · Shooter · Other
- Engine — Godot 4 · Unity (with a tip card to help you choose)
Then generates in one shot:
CLAUDE.mdfilled with your project config- Full folder structure (
src/·assets/·design/·docs/·tests/) - Starter scene and script files for your engine
design/gdd.md— Game Design Document stub ready to fill in
Slash Commands
| Command | What it does |
|---|---|
/setup | Initialize project — platform · genre · engine · starter files |
/new-feature | Start a feature (breaks into max 5 focused tasks) |
/level-design | Design a level with scene structure |
/ui-design | Design a menu · HUD · screen |
/code-review | Review code for bugs, engine-specific patterns, quality |
/qa-check | Full quality check before moving on |
/bug-report | Log a bug with severity, diagnosis, and regression test |
/performance | Profiling check, bottleneck diagnosis, and optimization strategy |
/build | Export/build checklist for your target platform |
/status | Sprint snapshot — tasks, open bugs, next focus |
/help | Show all commands with descriptions |
Agents
Use agents when you want deep focused work on a single domain. Slash commands handle most everyday tasks — agents are for when you need a specialist to go all-in on one area.
| Agent | Use for |
|---|---|
game-designer | Mechanics · balancing · GDD updates |
programmer | All code — GDScript or C# |
level-designer | Level layouts · scene structure |
ui-designer | Menus · HUD · screen design |
qa | Code review · bugs · test cases |
release | Builds · exports · versioning |
Every agent reads CLAUDE.md for project context — no re-explaining your engine, platform, or genre every session.
Project Structure
my-game/
├── CLAUDE.md Your project brain — update this as you build
├── .claude/
│ ├── agents/ 6 specialist agent prompts
│ ├── skills/ 10 slash commands
│ ├── hooks/ 3 hooks (session start/stop, commit check)
│ └── settings.json Hook wiring and permissions
├── design/
│ └── gdd.md Game Design Document
├── src/ Game source code
├── assets/ Art · audio · fonts
├── docs/ Technical notes
└── tests/ Test cases
How the Token Efficiency Works
Agents don't talk to each other. Each one has full context baked into its prompt and reads CLAUDE.md for project state. There's no coordination layer, no approval chains, no "consulting" step.
You stay in control. Claude starts coding immediately.
- Hooks only fire when relevant (commit hook exits instantly if not a commit)
CLAUDE.mdcarries context across sessions — no context re-setup- Specialists go straight to work — no meta-discussion about what to build
Customization
Everything is plain Markdown — edit freely:
# Add a new agent
touch .claude/agents/my-agent.md
# Edit a slash command
nano .claude/skills/new-feature/prompt.md
# Add a hook
touch .claude/hooks/my-hook.sh
# Wire it in .claude/settings.json
The default Claude Code permissions allow common read-only navigation tools, including rg, so agents can search the project quickly without broad shell access.
Credits
Inspired by Claude-Code-Game-Studios by Donchitos.
Rebuilt from scratch for solo devs on limited API budgets.
Contributing
See CONTRIBUTING.md — adding a slash command or agent is straightforward.
Changelog
See CHANGELOG.md for release history.
AI Assistance Transparency
I use AI-assisted development tools, including Codex and Claude, while building and maintaining this project. All code, design decisions, testing, commits, and releases are reviewed and shipped by me as the repository owner; AI tools are not listed as project contributors.
License
MIT — see LICENSE