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 skills add Donchitos/Claude-Code-Game-Studios --skill soak-testgit 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/skills/donchitos/claude-code-game-studios/soak-test)<a href="https://agentmods.dev/skills/donchitos/claude-code-game-studios/soak-test"><img src="https://agentmods.dev/badge/skills/donchitos/claude-code-game-studios/soak-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/donchitos/claude-code-game-studios/soak-test"><img src="https://agentmods.dev/badge/skills/donchitos/claude-code-game-studios/soak-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 7 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 5.1 | $0.00030 | $0.03223 |
| Opus 5.5 | $0.00012 | $0.01289 |
| Sonnet 5.5 | $0.00006 | $0.00645 |
| Haiku 4.5 | $0.00003 | $0.00322 |
Grade A, and why
soak-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys automation,workflow
Automation mode: Resolve modes.automation (project.local.yaml →
project.yaml → default collaborative). Every AskUserQuestion call and
every file write follows .claude/docs/automation-modes.md
(collaborative asks always · guided major-only · autonomous logs and proceeds;
automation_always_ask categories always prompt).
Soak Test
A soak test (also called an endurance test) is an extended play session run with specific observation goals. Unlike a smoke check (broad critical path, ~10 min) or a single-feature playtest (~30 min), a soak test runs for 30 minutes to several hours to surface:
- Memory leaks — gradual heap growth that only appears after scene transitions
- Performance drift — frame time degradation that worsens over time
- State accumulation bugs — issues that only appear after N repetitions of a mechanic (inventory full, score overflow, AI state corruption)
- Fun fatigue — mechanics that feel good in a first session but grow repetitive over extended play
- Content exhaustion — the point where players run out of novel content
This skill generates the observation protocol and analysis harness — the human does the actual playing.
Output: production/qa/soak-test-[date]-[duration].md
When to run:
- Polish phase — before
/gate-check release - After fixing a memory or stability issue (regression soak)
- When extended play has not been formally tracked
1. Parse Arguments
Duration (default: 1h):
30m— short soak; suitable for testing a single mechanic or scene1h— standard soak; covers most common leak categories2h— extended soak; recommended for first full Polish soak4h— deep soak; required for games with long session design (RPGs, sims)
Focus (default: all):
memory— focus on heap size, object count, leak patternsstability— focus on crash/freeze/hang detectionbalance— focus on fun fatigue, content exhaustion, difficulty perceptionall— all of the above
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.
- 2d ago Changed · -6 lines cd1ad9ab08b9
- 13d ago Changed d66cd1f07782
- 22d ago Changed · +11 lines b0268c95cc39
- 27d ago Changed 1530c16102ca
- 28d ago Changed · +44 lines · -24 tokens per session 99725d971fa3
- 1mo ago First seen · 285 lines · 54 tokens per session scan A 9f090f0e3957
soak-test is a skill published in the GitHub repository Donchitos/Claude-Code-Game-Studios (27,059 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 3,223 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
game-qa
Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed outcome, restart, and explicit limitations without dressing subjective fun up as a certain verdict. Use for test a generated game, QA a game build, check whether the…
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
unity-testing
Use when writing or structuring tests — EditMode vs PlayMode test decisions, test architecture, what to test in Unity, mocking strategies, and CI integration for Unity tests.
game-design
How game development works as a process — roles, subtasks, workflows and role descriptions, especially (but not only) for Roblox. Use this skill when it's about the ORGANIZATION of game dev rather than concrete code: Which roles exist (Creative Director, Engineer, Artist, Polish/Audio, Business, QA-Tester, Game…
rbx-dev
Meta-skill for complete Roblox game development with Rojo — the entry point that knows and unifies the three specialist skills /rojo (filesystem→Studio sync, project setup), /rbx-studio (editor, MCP, assets, malware scan) and /game-design (roles, workflows, GDD). Use this skill for ANY Roblox game-dev undertaking…
unity-tests-write
Use when writing Unity tests, including EditMode tests, PlayMode tests, performance testing, and code coverage.