Claude Code Game Studios is a setup that organizes Claude Code into a coordinated game-development team of specialized AI agents. It supports game projects across design, programming, art, audio, narrative, quality assurance, and production, with skills and workflows for coordinating that work.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/donchitos/claude-code-game-studios/claude-mdgit clone --depth 1 https://github.com/Donchitos/Claude-Code-Game-StudiosWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/donchitos/claude-code-game-studios/claude-md)<a href="https://agentmods.dev/instructions/donchitos/claude-code-game-studios/claude-md"><img src="https://agentmods.dev/badge/instructions/donchitos/claude-code-game-studios/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00381 | $0.00381 |
| Opus 5 | $0.00191 | $0.00191 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
Claude-Code-Game-Studios CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- Claude-Code-Game-Studios CLAUDE.md — 92% identical, 2 lines differ
- youtube-example-ai-studio CLAUDE.md — 88% identical, 12 lines differ
What it actually says
Claude Code Game Studios -- Game Studio Agent Architecture
Indie game development managed through 49 coordinated Claude Code subagents. Each agent owns a specific domain, enforcing separation of concerns and quality.
Technology Stack
- Engine: [CHOOSE: Godot 4 / Unity / Unreal Engine 5]
- Language: [CHOOSE: GDScript / C# / C++ / Blueprint]
- Version Control: Git with trunk-based development
- Build System: [SPECIFY after choosing engine]
- Asset Pipeline: [SPECIFY after choosing engine]
Note: Engine-specialist agents exist for Godot, Unity, and Unreal with dedicated sub-specialists. Use the set matching your engine.
Project Structure
@.claude/docs/directory-structure.md
Engine Version Reference
@docs/engine-reference/godot/VERSION.md
Technical Preferences
@.claude/docs/technical-preferences.md
Coordination Rules
@.claude/docs/coordination-rules.md
Collaboration Protocol
User-driven collaboration, not autonomous execution. Every task follows: Question -> Options -> Decision -> Draft -> Approval
- Agents MUST ask "May I write this to [filepath]?" before using Write/Edit tools
- Agents MUST show drafts or summaries before requesting approval
- Multi-file changes require explicit approval for the full changeset
- No commits without user instruction
See docs/COLLABORATIVE-DESIGN-PRINCIPLE.md for full protocol and examples.
First session? If the project has no engine configured and no game concept, run
/startto begin the guided onboarding flow.
Coding Standards
@.claude/docs/coding-standards.md
Context Management
@.claude/docs/context-management.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 55 lines · 381 tokens per session scan A a734e23d0c54
Claude-Code-Game-Studios CLAUDE.md is an instructions file published in the GitHub repository Donchitos/Claude-Code-Game-Studios (24,800 stars, last pushed 3mo ago), licensed MIT. It adds 381 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
novel-to-game AGENTS.md
Instructions for zenstory-ai/novel-to-game, covering noveltogame engineering guide, rules and verification.
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
game-design-lenses AGENTS.md
Instructions for EthanM2025/game-design-lenses, covering how to install (codex / generic), integration block (copy this into your project's agents.md), game design lens review (game-design-lenses) and notes.
game-superpowers AGENTS.md
Instructions for mike007jd/game-superpowers, covering agents.md, repo conventions, editing policy and collection entrypoint.
game-superpowers GEMINI.md
Instructions for mike007jd/game-superpowers, a project described as: Skills-first game development superpowers for Claude Code and Codex: build, audit, polish, and productionize game projects with reusable Agent Skills.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).