create-arc-game

create-arc-game is a skill for Claude Code, Codex from theredbluepill/arc-interactive. It costs 0 tokens per session (3,361 once invoked), scanned A, original, MIT.

A guide for creating games for ARC-AGI-3, a benchmark where an agent solves interactive grid-based puzzles. It explains how to define actions, organize related game variants, and register new games in the project.

In plain words
What is it for?
Use it when building an ARC-AGI-3 game, mapping actions to movement or other controls, adding a new game family, or registering a variant in the repository.
Why use it?
It helps avoid inconsistent action meanings and naming when adding a new game. It also gives structure for documenting and implementing each game's rules.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/theredbluepill/arc-interactive/create-arc-game
Any agent
npx skills add theredbluepill/arc-interactive --skill create-arc-game
Clone the repo
git clone --depth 1 https://github.com/theredbluepill/arc-interactive

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 create-arc-game

README.md
[![agentmods](https://agentmods.dev/badge/skills/theredbluepill/arc-interactive/create-arc-game.svg)](https://agentmods.dev/skills/theredbluepill/arc-interactive/create-arc-game)
Your own site
<a href="https://agentmods.dev/skills/theredbluepill/arc-interactive/create-arc-game"><img src="https://agentmods.dev/badge/skills/theredbluepill/arc-interactive/create-arc-game.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.03361
Opus 5 $0.00000 $0.01681
Sonnet 5 $0.00000 $0.00672
Haiku 4.5 $0.00000 $0.00336

Measured 6d ago against content hash dee009551001, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

create-arc-game 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.

skills/create-arc-game/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Create ARC-AGI-3 Game

Overview

This skill guides the creation of ARC-AGI-3 games based on established patterns from environment_files/.

Abstract actions (ACTION1–7)

Per the ARC-AGI-3 Actions spec, each game defines what ACTION1ACTION7 do: grid movement, rotation, no-op, idle, clicks, etc. The official docs describe ACTION1ACTION4 as simple actions that vary by game; the up/down/left/right wording is for human keybinding in the UI, not a requirement that your step() implements cardinal movement.

Many games in this repo map ACTION1ACTION4 to grid movement—that is a convention, not a platform rule. If your design uses those IDs for something else (e.g. ACTION1 = rotate clockwise), document it in GAMES.md and implement it explicitly in step().

New stems vs family variants

  • Prefer a new two-letter prefix (xx01) when the verb is genuinely new (e.g. nw01 arrow tiles, bd01 no-revisit).
  • Use xx02 / xx03 only for alternate rules within the same family (pb, fs, tp, ic, va alongside their xx01). Cap at 03 unless a project plan explicitly adds 04+ (keeps variants meaningfully distinct).

Registry similarity (distinctiveness)

  • After multi-stem or template-heavy changes, run uv run python devtools/similar_games_report.py --only-games-md --top-k 12 --min-score 0.25 (optional: --suspicious-min-score 0.40). See devtools/SIMILARITY_TRIAGE.md for triage steps and Resolved notes.
  • New stem checklist: GAMES.md lead sentence states the unique rule; metadata.json tags / physics_rules match step(); HUD shows constraints not obvious from tiles; avoid copy-pasting unrelated levels = … literals; smoke with devtools/smoke_games.py. On large changes, regenerate the report.

Game Structure

environment_files/{game_id}/{version}/
├── {game_id}.py          # Main game file
└── metadata.json         # Game metadata

Read the full file on GitHub · 373 lines

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. 6d ago First seen · 373 lines · 0 tokens per session scan A dee009551001

Subscribe to this mod's changes

create-arc-game is a skill published in the GitHub repository theredbluepill/arc-interactive (55 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,361 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

unity-addressables

Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).

Besty0728/Unity-Skills · 25 tokens

playtest-report

Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

Donchitos/Claude-Code-Game-Studios · 35 tokens

unity-manual-component

Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.

Besty0728/Unity-Skills · 36 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens