levels

levels is a skill for Claude Code, Codex from vchelaru/FlatRedBall2. It costs 52 tokens per session (2,486 once invoked), scanned A, original, MIT.

A guide for building game levels in FlatRedBall2 from TMX files, the map format used by the Tiled level editor. It covers loading maps, creating solid collision areas from tile layers, and moving between levels.

In plain words
What is it for?
Use it when loading level maps, setting their position, generating collision, controlling map layers, or implementing level progression.
Why use it?
It provides the project-specific steps for turning saved map data into a playable level instead of requiring developers to work out the engine setup themselves.

Skill for Claude CodeCodex

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

Good fit Use it when loading level maps, setting their position, generating collision, controlling map layers, or implementing level progression.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vchelaru/flatredball2/levels
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 vchelaru/FlatRedBall2 --skill levels
Clone the repo
git clone --depth 1 https://github.com/vchelaru/FlatRedBall2

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 levels

README.md
[![agentmods](https://agentmods.dev/badge/skills/vchelaru/flatredball2/levels/github.svg)](https://agentmods.dev/skills/vchelaru/flatredball2/levels)
Your own site
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/levels"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/levels/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 levels

Your own site · 80×15
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/levels"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/levels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,486 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.02486
Opus 5.5 $0.00021 $0.00994
Sonnet 5.5 $0.00010 $0.00497
Haiku 4.5 $0.00005 $0.00249

Measured 7d ago against content hash b0b7fd770f7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

levels 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 7d 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.

frb-skills/levels/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Level Data in FlatRedBall2

Levels are defined as TMX files using the Tiled map format. Use the tmx skill to create or edit TMX files.

Level Setup in a Screen

Load a TMX file with TileMap, add it to the screen, and generate collision:

using FlatRedBall2.Tiled;

public class GameScreen : Screen
{
    private TileShapes _solidCollision = null!;

    public override void CustomInitialize()
    {
        var map = new TileMap("Content/Tiled/Level1.tmx", Engine.GraphicsDevice);
        map.CenterOn(0, 0); // center map on world origin
        Add(map);

        _solidCollision = map.GenerateCollisionFromClass("SolidCollision");
        Add(_solidCollision);
    }
}

Key types (all in FlatRedBall2.Tiled):

  • TileMap — loads a TMX file, wraps layers, generates collision
  • TileMapLayer — per-layer Z, visibility, and render layer control
  • TileShapes — collision grid (FlatRedBall2.Collision)

TileMap Position

TileMap.X and TileMap.Y define the top-left corner of the map (Tiled convention). Default (0, 0) places the top-left at the world origin; the map extends right (+X) and down (−Y).

CenterOn(worldX, worldY) repositions the map so its center is at the given point.

Layer Z-Order

Layers are assigned Z values automatically: 1 apart in TMX order, with GameplayLayer at Z = 0 if it exists. Entities at Z = 0 naturally interleave at the gameplay layer. Override per-layer Z only when needed:

map.GetLayer("Foreground").Z = 100f;

Multiple Collision Types

var solid = map.GenerateCollisionFromClass("SolidCollision");
var jumpThrough = map.GenerateCollisionFromClass("JumpThroughCollision");
Add(solid);
Add(jumpThrough);

Each collection can have its own collision relationship. For jump-through platforms, set OneWayDirection = OneWayDirection.Up and CanDropThrough = true on the relationship — the player passes through from below, lands from above, and can drop down with Down+Jump. For hard one-way barriers (OneWayCollision tile class — Yoshi-style ratchet doors), set OneWayDirection = OneWayDirection.Up and leave CanDropThrough = false. See the collision-relationships skill for details. By default all tile layers and object layers are scanned — hand-drawn rectangle/polygon <object>s with a matching Class are collision sources too, not just painted tiles (see "Collision from hand-drawn object-layer shapes" below). Passing layerName restricts the scan to a single tile layer, skipping object layers entirely:

Read the full file on GitHub · 164 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. 7d ago Changed · +8 lines b0b7fd770f7b
  2. 13d ago Changed 0081cd8c02c9
  3. 1mo ago First seen · 156 lines · 52 tokens per session scan A fd1314efb21e

Subscribe to this mod's changes

levels is a skill published in the GitHub repository vchelaru/FlatRedBall2 (15 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,486 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

playtest-report

Structured playtest report template, or turn existing playtest notes into structured feedback.

Donchitos/Claude-Code-Game-Studios · 20 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

motion

Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.

OpenDCAI/GameFactory-3A · 0 tokens

unity-addressables

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

Besty0728/Unity-Skills · 25 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

threejs-exposure-color-grading

Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.

scottstts/Threejs-Awesome-Graphics-Agent-Skills · 60 tokens