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 vucinatim/air-jam --skill canvas-2d-gameplaygit clone --depth 1 https://github.com/vucinatim/air-jamWrote 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/vucinatim/air-jam/canvas-2d-gameplay)<a href="https://agentmods.dev/skills/vucinatim/air-jam/canvas-2d-gameplay"><img src="https://agentmods.dev/badge/skills/vucinatim/air-jam/canvas-2d-gameplay/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/vucinatim/air-jam/canvas-2d-gameplay"><img src="https://agentmods.dev/badge/skills/vucinatim/air-jam/canvas-2d-gameplay.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00367 |
| Opus 5 | $0.00023 | $0.00183 |
| Sonnet 5 | $0.00009 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
canvas-2d-gameplay 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.
What it actually says
Canvas 2D Gameplay
Use this skill for 2D gameplay rendered on canvas.
Read First
docs/airjam/canvas-2d-gameplay.mddocs/airjam/generated/state-and-rendering.mddocs/airjam/generated/project-structure.md
Core Rule
Use canvas as the gameplay render surface, and keep React/DOM for shell UI and overlays.
Do not try to run the whole game through DOM layout.
Structure Rules
- keep simulation separate from drawing
- keep world coordinates separate from screen and CSS coordinates
- keep HUD and menus in reusable UI modules above the canvas
- keep input interpretation out of the render code
Asset Rules
- LLM-generated SVGs are fine for icons, pickups, simple props, and UI art if they are cleaned up and curated
- keep a consistent visual language across sprites, SVGs, and UI
- prefer a small curated asset set over random mixed-generation output
Movement And Collision Rule
For most 2D games, prefer simple custom movement and collision before reaching for a heavyweight physics layer.
Add a physics engine only when the mechanic truly needs it.
Anti-Patterns
- gameplay logic buried inside draw calls
- DOM elements used as the main simulation surface
- inconsistent scaling between world units and canvas pixels
- random SVGs with mismatched stroke, color, and perspective language
- overcomplicated physics for simple arcade movement
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.
- 12d ago First seen · 48 lines · 47 tokens per session scan A c8d84a6bc015
canvas-2d-gameplay is a skill published in the GitHub repository vucinatim/air-jam (6 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 367 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.
Other skills, from other repositories
design-lenses
Critique a game's design through Schell's lenses, MDA and systems thinking, ranking findings by severity with fixes. Design-level review, not bugs or feel tuning.
teach-me
Teach the user to build browser games themselves across sessions, by building real games together. Not for building a game for them.
gaming-expert
Build comprehensive game systems including gameplay mechanics, multiplayer infrastructure, analytics tracking, and monetization features. Use when the user mentions game development, Unity or Unreal, gameplay mechanics, multiplayer netcode, game analytics, or in-game monetization.
pc-games
PC and console game development principles. Engine selection, platform features, optimization strategies.
game-development
Game development orchestrator. Routes to platform-specific skills based on project needs.
game-design
Game design principles. GDD structure, balancing, player psychology, progression.