Donchitos/Claude-Code-Game-Studios

▲ 2,381 stars today★ 39,118⑂ 5,092

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

About Donchitos/Claude-Code-Game-Studios

Donchitos/Claude-Code-Game-Studios is an open-source project on GitHub, mainly written in Shell. Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy. It currently holds 39,118 stars and 5,092 forks with 95 open issues, and was last pushed on 2026-11-09 (repository created 2026-02-12).

Project Overview

Git Homed tracks it on the AI Agent Skills Trending board and on the AI AI Agent Skills Trending list.

GitHub Repository Details

Repository Donchitos/Claude-Code-Game-Studios · default branch main · size 5612 KB · watchers 267 · source: GitHub REST API and repository README

README

Claude Code Game Studios

Describe a game. Claude Code asks a few questions, writes a one-page brief, and builds a playable browser game from it.
Then you change it, grow it and finish it, one step at a time.

https://github.com/Donchitos/Claude-Code-Game-Studios/blob/HEAD/MIT License https://github.com/Donchitos/Claude-Code-Game-Studios/blob/HEAD/Built for Claude Code https://github.com/Donchitos/Claude-Code-Game-Studios/blob/HEAD/Buy Me a Coffee https://github.com/Donchitos/Claude-Code-Game-Studios/blob/HEAD/GitHub Sponsors

---

Make me a game

Open Claude Code in a copy of this repository and say what you want:

/prototype a fishing game where the rare fish only bite at dusk

1. A few questions. One round, picked from the genre: the choices that shape the game, how it should feel, how it looks, how hard it is, the goal. Each has a usual answer, so "you pick" works. A vague idea ("a racing game") gets two or three one-line pitches to choose from first. 2. A one-page brief. design/game-brief.md: your words kept as you typed them, the look, the first minute, the challenge, the features and what is left for later. You read it and say Build it, or change something first. 3. A first build. A browser game in prototypes// that opens with a double-click: every figure drawn, no emoji art, no copy of another game, and not trivially easy. Your session builds it at its own effort ("build it at medium" is cheaper and thinner). 4. Checked before you get it. A few scripted key presses in a headless browser show it opens with no errors and responds; text that is too small, overlapping or off screen and screens that freeze are fixed in one round; and every line of the brief is marked built, missing or broken from the screenshots and the code, or not assessed when it could not be checked. Your play is the real test: the handover card says what passed, what is still broken and what was guessed, and ends "Not yet played by a person".

Then it is yours to play. After that:

keep and to avoid, and each one you accept is a checkpoint you can go back to. Ask to tune it and it gains a tweak panel with a slider for every value. for itch.io or a link. TypeScript, its values in data files, tests and a build), and you add to it one feature a sitting: say the next feature, and it is built, checked and committed. After every feature the same seeded run is played again and any change is shown to you. Stories (/create-stories, /dev-story, /story-done) only when you ask for them. when the game is to sell.

Already have a browser game? /prototype --from brings a copy in as it is, so it can be changed and grown the same way.

What it has been shown to do

made from its questions was picked over a hand-written brief all three times. All six games built from the two kinds of brief were ones the tester said they would build on, so on the games themselves the two kinds of brief tied. into a game the tester would keep building. That is one game, not yet a pattern. system with a design document. Both are built and pass the framework's own checks, but neither has had a test like the two above.

The games themselves are deliberately not shipped here: this is a template you clone to start your own project, and somebody else's game in your repo is clutter, not evidence.

---

Table of Contents

---

Getting Started

Prerequisites

Hooks fail gracefully if optional tools are missing — you just lose validation — with one deliberate exception: a commit that stages data JSON is blocked when there is no Python to validate it.

Setup

1. Clone or use as template:

   git clone https://github.com/Donchitos/Claude-Code-Game-Studios.git my-game
   cd my-game
   

2. Open Claude Code in the project's root folder (the one holding CLAUDE.md and project.yaml) and start a session:

   claude
   
Starting it in a subfolder such as src/ skips the project's hooks, deny rules and ask-first permission mode.

3. Type /prototype and your idea, or run /start, which asks where you are (make me a game, an idea or none yet, clear design, existing work) and guides you to the right workflow. No assumptions.

Other ways in:

Engines

| Engine | engine.name | Code root | Notes | |--------|---------------|-----------|-------| | Web | Web | src/ | The default for a new project. A one-shot needs no engine at all; a grown game is a web project. /setup-engine web offers a starter: nothing extra, three.js, Phaser or PixiJS | | Godot 4 | Godot | src/ | GDScript, C# or GDExtension | | Unity | Unity | Assets/ | Unity compiles only Assets/ and Packages/ | | Unreal Engine 5 | Unreal | Source// | C++ and Blueprints |

/setup-engine pins the engine version and writes its reference docs (docs/engine-reference//). With no engine set, /prototype builds in the browser first; you pick an engine after you have played the game. Each engine's folders and default commands come from one table, .claude/engines/engines.tsv. If your code or tests live somewhere else, set engine.code_root or engine.test_root in project.yaml.

Configuration

project.yaml at the repo root is the single source of truth for how the studio behaves on your project — engine, naming conventions, and a modes block that controls how much process every skill enforces. /start writes it for you; you rarely need to hand-edit it.

The one question that matters most is modes.rigor — minimal, standard, or full. It's a single front door over six separate knobs (workflow — which GDD sections are required, docs.density, qa.level, story_granularity, review_mode — how many director agents review your work, and team.size), so /start asks it once instead of six times:

minimal is the default because the heavier tier costs more to reach working code without producing a better result, and gives nothing back when someone new picks the project up. Raise it in one /project-settings call when your project grows — /next-step and /gate-check will suggest it when they see the signs.

Two escape hatches keep one setting from being a blunt instrument. system_overrides holds a single system to a higher standard than the rest of the project — your combat system gets the full treatment while everything else stays light. testing.strict sets, per test type (logic, integration, visual, UI, config), whether missing evidence blocks a story or merely warns.

Any of the six underlying knobs can still be set individually if you want a mix (e.g. workflow: full with docs.density: terse — comprehensive but compact). Two of them — review_mode (full / lean / solo) and team.size — are also personal: rigor sets the team-wide default, but you can override them per-developer in a gitignored project.local.yaml without touching the shared config. modes.automation (how often the AI pauses to ask before it acts) sits outside rigor and is likewise personally overridable. project.goal (a jam game, a hobby, a game to sell, and so on) is what you want from the game; /start guesses it, and /cut reads it.

View or change any setting with the /project-settings skill:

/project-settings                              # view effective config
/project-settings modes.review_mode            # view one setting
/project-settings modes.rigor=full             # write to project.yaml (team-wide)
/project-settings --local modes.review_mode=solo   # write to project.local.yaml (just you)

Full schema and per-setting behavior: .claude/docs/effects-map.md.

Upgrading

Already using an older version of this template? See UPGRADING.md for step-by-step migration instructions, a breakdown of what changed between versions, and which files are safe to overwrite vs. which need a manual merge.

Project Structure

CLAUDE.md                           # Master configuration
project.yaml                        # Project settings: engine, modes, goal
.claude/
  settings.json                     # Hooks, permissions, safety rules
  agents/                           # 49 agent definitions (markdown + YAML frontmatter)
  skills/                           # 75 skills, plus three old names (a subdirectory each)
  hooks/                            # 18 scripts (bash) — 15 event hooks, two helpers they
                                    #   source (yaml-helper.sh, update-check.sh), and one
                                    #   opt-in diagnostic you wire yourself
  scripts/                          # Helper scripts the skills and hooks run; each .sh has --help
  rules/                            # 14 path-scoped coding standards
  genres/                           # Genre sheets and look guidance /prototype asks and
                                    #   builds from
  engines/                          # The engine table (engines.tsv) and the web starter
  statusline.sh                     # Status line script (context%, model, stage, epic breadcrumb)
  docs/
    workflow-catalog.yaml           # 7-phase pipeline definition (read by /next-step)
    templates/                      # 62 document templates (+ per-section guidance)
prototypes/                         # One-shots, one folder each (isolated from src/)
references/                         # Optional: images and sounds you like, for /prototype
src/                                # Game source code (Godot, Web). The code root is
                                    #   ENGINE-SPECIFIC: Unity compiles only
                                    #   Assets/, Unreal builds from Source//
assets/                             # Art, audio, VFX, shaders, data files
design/                             # The game brief, GDDs, narrative docs, level designs
docs/                               # Technical documentation, ADRs, engine references
tests/                              # Test suites (unit, integration, performance, playtest)
tools/                              # Build and pipeline tools
production/                         # Sprint plans, milestones, release tracking
studio-tests/                       # QA for the skills and agents themselves — see below

Testing your customizations

Claude Code Game Studios is a template you are meant to edit. studio-tests/ is how you check that an edited or newly written skill still holds up — a catalog of all 75 skills and 49 agents, per-category quality rubrics, behavioral specs, and templates for writing specs of your own.

/skill-test static [name]     # structural linter — 7 compliance checks
/skill-test category [name]   # category-specific quality rubric
/skill-test spec [name]       # behavioral spec assertions
/skill-test audit             # coverage report across skills and agents
/skill-improve [name]         # test-fix-retest loop; keeps or reverts on score change

It tests the framework, never your game — game tests live in tests/.

Hooks, Permissions and Rules

Hooks run automatically on every session:

| Hook | Trigger | What It Does | |------|---------|--------------| | validate-commit.sh | PreToolUse (Bash, PowerShell) | Checks for hardcoded values, TODO format, JSON validity, design doc sections — exits early if the command is not git commit | | validate-push.sh | PreToolUse (Bash, PowerShell) | Warns on pushes to protected branches, and on git tag, git merge, gh release, butler push and steamcmd +run_app_build — exits early for any other command | | validate-read.sh | PreToolUse (Read) | Refuses a whole-file read of a design doc over 40 KB and answers with its headings, so the retry reads one section (features.read_guard) | | validate-write.sh | PreToolUse (Write/Edit) | Warns, never blocks, when a write would break a rule the skills state: a file they never overwrite, the config guard, the prototype boundary, a localization freeze | | validate-registry.sh | PreToolUse (Write/Edit) | Warns when a write to the entity or TR-ID registry would delete or renumber an entry, or set a status its header does not list | | validate-assets.sh | PostToolUse (Write/Edit) | Checks data-file JSON under assets/, Assets/ or Content/, and asset naming in Godot's assets/ only — exits early if the file is under none of them | | session-start.sh | Session open | Shows current branch and recent commits for orientation | | detect-gaps.sh | Session open | Detects fresh projects (suggests /start) and missing design docs when code or prototypes exist | | pre-compact.sh | Before compaction | Logs the compaction (its output does not reach Claude — session-start.sh restores context afterwards) | | notify.sh | Permission prompt, or idle about a minute | Shows Windows toast notification via PowerShell | | session-stop.sh | Every response end, in the background | Archives active.md to session log and records git activity | | log-agent.sh | Agent spawned | Audit trail start — logs subagent invocation | | log-agent-stop.sh | Agent stops | Audit trail stop — completes subagent record | | validate-agent-artifact.sh | Agent stops | Warns when a subagent stops without writing the file its brief named | | validate-skill-change.sh | PostToolUse (Write/Edit) | Advises running /skill-test after any .claude/skills/ change |

Note: validate-commit.sh, validate-push.sh, validate-read.sh, validate-write.sh, validate-registry.sh, validate-assets.sh and validate-skill-change.sh fire on every Bash, PowerShell, Read, Write or Edit tool call and exit immediately (exit 0) when the command or file path is not relevant. This is normal hook behavior — not a performance concern.

Permission rules in settings.json auto-allow test runs and the framework's read-only helper scripts, and block dangerous operations (force push, rm -rf, reading .env files) in both the Bash and PowerShell tools. Read-only commands such as git status, git log and ls need no rule: Claude Code runs them without asking. The git rules match anywhere after git, so a git command whose text only mentions push followed later by + or -f, clean followed by -f, or reset followed by --hard — a commit message such as git commit -m "push + pull" included — is denied too: reword the message.

Path-Scoped Rules

Coding standards are automatically enforced based on file location. The paths below are Godot's. Each rule also matches the Unity and Unreal layouts: the code rules match C# under Assets//Gameplay/ and C++ under Source//Gameplay/ (and Core, AI, Networking, UI), data matches JSON under Assets//Data/ and Content//Data/, shaders match by file type, and tests match C# under Assets/Tests/ and C++ under Source//Tests/.

| 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 sections per modes.workflow, formula format, edge cases | | design/narrative/ | Lore consistency, character voice, canon levels | | assets/data/**/*.json | JSON validity, naming conventions, schema rules | | assets/shaders/ | Naming conventions, performance targets, cross-platform rules | | /*.tscn, **/*.tres | Scene and resource files changed in the editor where possible; safe hand-edit rules | | tests/ | Test naming, coverage requirements, fixture patterns | | prototypes/ | A one-shot's tuning values in config.js and seeded randomness; relaxed standards for engine and paper prototypes |

Studio Mode

Everything above is the light path: one brief, a game you play, one feature a sitting as it grows. For a team, a long project, or a person who wants the paperwork, the same project also has studio mode: 49 specialized agents in a studio hierarchy, a design document per system, architecture decisions, epics and sprints, phase gates, and team-* pipelines that coordinate several agents on one feature. /next-step suggests it once when a grown game gets big (about nine stories or features).

What's Included

| Category | Count | Description | |----------|-------|-------------| | Agents | 49 | Specialized subagents across design, programming, art, audio, narrative, QA, and production | | Skills | 75 | Slash commands for every workflow phase (/prototype, /start, /design-system, /create-epics, /create-stories, /dev-story, /story-done, etc.) | | Hooks | 15 | Automated validation on commits, pushes, asset changes, design-doc reads, writes and registries, session lifecycle, agent audit trail, and gap detection | | Rules | 14 | Path-scoped coding standards enforced when editing gameplay, engine, AI, UI, network code, scene and asset files, and more | | Templates | 62 | Document templates for GDDs, UX specs, ADRs, sprint plans, HUD design, accessibility, and more |

Studio Hierarchy

Agents are organized into three tiers, matching how real studios operate:

Tier 1 — Directors
  creative-director    technical-director    producer

Tier 2 — Department Leads game-designer lead-programmer art-director audio-director narrative-director qa-lead release-manager localization-lead

Tier 3 — Specialists 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

Each agent declares a model in its frontmatter: the three directors ask for Opus, lead-programmer and fifteen specialists name Sonnet, and the remaining thirty inherit your session's model. Treat the tiers as seniority of role, not as a billing plan — most of the studio runs on whatever model you are already using.

Engine Specialists

The template includes agent sets for the three major engines. Use the set that matches your project (a web project uses the general programmers):

| 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

Type / in Claude Code to access all 75 skills (plus three old names that point to their new ones):

Make a Game /prototype /cut

Onboarding & Navigation /start /next-step /project-stage-detect /setup-engine /adopt /project-settings

Game Design /brainstorm /map-systems /design-system /quick-design /review-all-gdds /propagate-design-change

Art & Assets /art-bible /asset-spec /asset-audit

UX & Interface Design /ux-design /ux-review

Architecture /create-architecture /architecture-decision /architecture-review /create-control-manifest

Stories & Sprints /create-epics /create-stories /dev-story /sprint-plan /sprint-status /story-readiness /story-done /estimate

Reviews & Analysis /design-review /code-review /balance-check /content-audit /scope-check /perf-profile /tech-debt /gate-check /consistency-check /security-audit

QA & Testing /qa-plan /smoke-check /soak-test /regression-suite /test-setup /test-helpers /test-evidence-review /test-flakiness /skill-test /skill-improve

Production /milestone-review /retrospective /bug-report /bug-triage /reverse-document /playtest-report

Release /release-checklist /launch-checklist /write-changelog /patch-notes /hotfix /day-one-patch

Creative & Content /vertical-slice /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 /team-live-ops /team-qa

Does studio mode produce games

GitHub Stars & Activity

39,118Stars
5,092Forks
95Open issues
ShellLanguage

GitHub Popularity

GitHub stars39,118
Forks5,092
Open issues95
Primary languageShell
LicenseMIT
Stars gained today2,381
Created2026-02-12
Last pushed2026-11-09

Trending History

Weekly boardrank #22 · ▲ 2,381 stars
Monthly boardrank #21 · ▲ 13,212 stars

Related GitHub Projects

1

obsidianmd / obsidian-skills

Shell★ 53,009⑂ 0
→
2

morluto / rea

TypeScript★ 465,160⑂ 0
→
3

affaan-m / ECC

JavaScript★ 304,932⑂ 0
→
4

deepseek-ai / deepseek-harness

TypeScript★ 282,715⑂ 0
→
5

NousResearch / hermes-agent

Python★ 264,057⑂ 0
→
6

firecrawl / firecrawl

TypeScript★ 202,471⑂ 0
→
7

anthropics / skills

Python★ 196,375⑂ 0
→
8

DietrichGebert / ponytail

JavaScript★ 192,510⑂ 0
→

More Trending Repositories