Back to directory

Claude Code Game Studios

A collection of specialized Claude Code subagents, skills, hooks and rules that organizes a single Claude Code session into a coordinated game development studio.

Claude Code Game Studios

Claude Code Game Studios turns a single Claude Code session into a structured game development studio. Instead of one general-purpose assistant, it provides 49 specialized agents organized into a studio hierarchy, with directors who guard the overall vision, department leads who own their domains, and specialists who do hands-on design, programming, art, audio, narrative, QA and production work, each with defined responsibilities, escalation paths and quality gates.

It also includes many skills as slash commands for each workflow phase, such as starting a project, designing systems, and creating and completing stories; automated hooks that validate commits, pushes, asset changes, session lifecycle and agent activity; path-scoped coding rules enforced when editing gameplay, engine, AI, UI or network code; and document templates for game design documents, UX specs, architecture decision records and sprint plans. Each agent's frontmatter names a model tier, with some agents inheriting the user's own session model.

It targets engines such as Godot, Unity and Unreal Engine, and is written mainly in Shell under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.