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 skills/frabcd/codex-ai-game-studio/setup-macos-editionnpx skills add frabcd/codex-ai-game-studio --skill setup-macos-editiongit clone --depth 1 https://github.com/frabcd/codex-ai-game-studioWrote 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/frabcd/codex-ai-game-studio/setup-macos-edition)<a href="https://agentmods.dev/skills/frabcd/codex-ai-game-studio/setup-macos-edition"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/setup-macos-edition.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 5.1 | $0.00072 | $0.01050 |
| Opus 5 | $0.00036 | $0.00525 |
| Sonnet 5 | $0.00014 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
setup-macos-edition scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up the macOS edition
Use the core standard-library Python CLI and the installed plugin's validated
macos edition descriptor. Treat detection, planning, applying, disabling, and
rollback as separate phases.
Detect without changing the host
Resolve PLUGIN_ROOT to this plugin's installed root, then run its native launcher:
"${PLUGIN_ROOT}/scripts/ai-game-studio-macos.sh" doctor --project <root>
Confirm that the host reports Darwin and either arm64 or x86_64. Inspect only OS and architecture metadata, zsh/POSIX availability, Homebrew or MacPorts presence, Metal/MPS/Core ML/CPU capability, free disk space, project markers, existing MCP configuration, and installed Unity, Godot, Unreal, Blender, Aseprite, Pixelorama, or Tiled applications. Check credential environment-variable names only; never read secret values. Detection must report mutation_performed: false.
Stop if the host is not Darwin or its architecture is unsupported. Do not apply the macOS edition from Windows, Linux, or WSL.
Produce one exact proposal
Run:
"${PLUGIN_ROOT}/scripts/ai-game-studio-macos.sh" plan --project <root> --output <plan.json>
Present the complete transaction: detected environment, exact state-file actions, MIT license, permissions, backups, rollback operations, expiry, and canonical digest. Explain that edition selection installs no editor, package manager, MCP server, model, or Rosetta component. Wait for the user to repeat the full digest verbatim.
Any external tool, editor, runtime, model, hosted service, or MCP setup needs its own later proposal with exact source pin, license, download size, permissions, privacy implications, health checks, and rollback. Never combine that proposal with edition selection.
Adapt platform-bound tooling
Apply the descriptor's rules in this order:
- Prefer a native source adaptation only when the source, license, build system, architecture, and required application APIs support it. Preserve tokenized arguments, bounded paths, output formats, and equivalent quality gates.
- Otherwise compare verified capability-equivalent native alternatives by capability, quality, cost, performance, license, privacy, and limitations.
- Otherwise propose a hosted or manual fallback and disclose network transfer, data retention, rights, cost, and reproducibility limits.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 77 lines · 72 tokens per session scan A 4efc539e87f1
setup-macos-edition is a skill published in the GitHub repository frabcd/codex-ai-game-studio (9 stars, last pushed 5d ago), licensed MIT. It adds 72 tokens to every session and 1,050 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
game-build
Build a risk-matched whitebox or the approved production game for its target runtime. Turn GAMEDESIGN, and ARTDIRECTION when production begins, into a minimal BUILDBRIEF and a runnable candidate that can be iterated with replayable evidence. Use for prototype the riskiest design question, implement the approved game…
game-concept
Design game concepts from a novel. From SOURCEBIBLE and PRODUCTBRIEF, generate three genuinely different directions on the dimensions still unlocked, then pick the most worthwhile playable prototype using hard vetoes and explicit trade-offs. Use for what game should this novel become, compare game concepts, choose a…
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…
3d_scene
Choose how to build a 3dscene asset. Do not default to one pipeline for every task: what the user specified about the scene's appearance matters more than the scene type, and generative reconstruction is the least stable route here.
cinematic-cutscene
Use when generating a non-interactive cutscene clip — opening scene, story beat, character intro, ending. Locks the look with a reference image, image-to-videos a 5-10s shot, optionally adds TTS dialogue, and wires it as a VideoStreamPlayer that fades in/out. Trigger on "cutscene", "intro cinematic", "opening scene"…
lightning
Use when authoring a lightning bolt visual effect — procedural jagged path drawn via ImmediateMesh, glow shader, sparks at endpoints, screen shake. Trigger on "lightning bolt", "chain lightning", "electric attack", "tesla coil", "shock spell", "thunderbolt", "energy beam".