game-architecture

game-architecture is a skill for Claude Code, Codex from vucinatim/air-jam. It costs 40 tokens per session (436 once invoked), scanned A, original, MIT.

A set of rules for organising gameplay code in an Air Jam project. It explains where host, controller, game rules, engine code and visual code should live.

In plain words
What is it for?
Use it when adding gameplay systems, moving code between parts of the project, or deciding whether code belongs to the host, controller, game rules, engine or rendering layer.
Why use it?
It prevents unrelated responsibilities from becoming tangled, making new systems and refactoring safer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding gameplay systems, moving code between parts of the project, or deciding whether code belongs to the host, controller, game rules, engine or rendering layer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vucinatim/air-jam/game-architecture
Install

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.

Any agent
npx skills add vucinatim/air-jam --skill game-architecture
Clone the repo
git clone --depth 1 https://github.com/vucinatim/air-jam

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for game-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/vucinatim/air-jam/game-architecture/github.svg)](https://agentmods.dev/skills/vucinatim/air-jam/game-architecture)
Your own site
<a href="https://agentmods.dev/skills/vucinatim/air-jam/game-architecture"><img src="https://agentmods.dev/badge/skills/vucinatim/air-jam/game-architecture/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.

agentmods 80×15 button for game-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/vucinatim/air-jam/game-architecture"><img src="https://agentmods.dev/badge/skills/vucinatim/air-jam/game-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00436
Opus 5 $0.00020 $0.00218
Sonnet 5 $0.00008 $0.00087
Haiku 4.5 $0.00004 $0.00044

Measured 12d ago against content hash 8f88e9692967, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

game-architecture 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 12d 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.

packages/cli/template-assets/bootstrap/skills/game-architecture/SKILL.md · 59 lines

What it actually says

Game Architecture

Use this skill when adding new systems or moving code between boundaries.

Read First

  1. docs/airjam/generated/project-structure.md
  2. docs/airjam/generated/architecture.md

Boundary Model

Prefer this split:

  1. src/airjam.config.ts for catalog metadata plus runtime config such as controllerPath and input schema
  2. src/app.tsx for mounting explicit host/controller runtime boundaries
  3. src/host/ for host-only composition
  4. src/controller/ for controller-only composition
  5. src/game/domain/ for pure rules
  6. src/game/engine/ for orchestration
  7. src/game/systems/ for focused gameplay systems
  8. src/game/adapters/ for framework integration
  9. src/game/ui/ for reusable game-facing UI
  10. src/game/debug/ for debug helpers

Keep runtime ownership explicit:

  1. mount airjam.Host / airjam.Controller once at the boundary
  2. use consumer hooks like useAirJamHost() and useAirJamController() only below that boundary
  3. keep gameplay code out of runtime setup and transport bootstrap

Decision Rule

Ask:

  1. is this pure gameplay logic
  2. is this runtime orchestration
  3. is this rendering integration
  4. is this host-only or controller-only

Put the code where the answer is clearest.

Refactor-First Rule

If new work would harden a mixed boundary, split the structure first or split the task into:

  1. boundary cleanup
  2. feature implementation

Anti-Patterns

  1. one large file that mixes host, controller, domain, and rendering concerns
  2. React components as the only home for gameplay logic
  3. adapter code becoming the real game model
Changes

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.

  1. 12d ago First seen · 59 lines · 40 tokens per session scan A 8f88e9692967

Subscribe to this mod's changes

game-architecture is a skill published in the GitHub repository vucinatim/air-jam (6 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 436 once invoked, about $0.0002 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.