tmx

tmx is a skill for Claude Code, Codex from vchelaru/FlatRedBall2. It costs 60 tokens per session (3,431 once invoked), scanned A, original, MIT.

A guide to TMX files, the map format used by the Tiled level editor, for FlatRedBall2 game levels.

In plain words
What is it for?
Use it to create or edit map layers, place collision tiles, resize maps, and reload tile data during development.
Why use it?
It helps create valid map scaffolding and explains how tile changes, collision data, and hot reload affect the running game.

Skill for Claude CodeCodex

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

Good fit Use it to create or edit map layers, place collision tiles, resize maps, and reload tile data during development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vchelaru/flatredball2/tmx
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 tmx
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 tmx

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/tmx"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/tmx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,431 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Output Handling · line 154
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 $0.00060 $0.03431
Opus 5 $0.00030 $0.01716
Sonnet 5 $0.00012 $0.00686
Haiku 4.5 $0.00006 $0.00343

Measured 5d ago against content hash 77a0f4a1610d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tmx 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 5d 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/tmx/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TMX Map Files in FlatRedBall2

See content-boundary skill first. TMX files are a human-edited content format — AI should scaffold a minimal valid TMX and tell the user to open it in Tiled for real level design. Do not try to author detailed levels in XML.

TMX files are the standard level format. A base template and standard tileset live in .claude/templates/Tiled/.

Hot-reload — see content-hot-reload skill

TileMap.TryReloadFrom(path) applies tile-data changes (cell GID/flip changes) in place; structural changes (resize, layer set, tilesets, object layers) return false so the caller falls back to RestartScreen(RestartMode.HotReload). Hand-authored mutations to a TSC after GenerateCollisionFromClass / GenerateCollisionFromProperty (e.g. tsc.AddPolygonTileAtCell(...) to extend the generated collision) are wiped on in-place reload — those live in CustomInitialize, which only re-runs on a full screen restart.

Communication convention — reference tiles by numeric ID

When discussing a tile (its polygon, class, position, collision shape, etc.), always refer to it by its numeric tile ID — e.g., "tile ID 11's polygon" rather than "the slope triangle". The ID is the unambiguous handle that matches the .tsx file and Tiled's editor; descriptions alone are ambiguous when multiple tiles have similar shapes.

Setup — Copying Template Files

When a game needs a TMX level, copy these three files into the game's content directory:

  1. base.tmx → rename to the level name (e.g., Level1.tmx)
  2. StandardTileset.tsx → copy alongside the .tmx
  3. StandardTilesetIcons.png → copy alongside the .tsx

The .tmx references the .tsx by relative path (source="StandardTileset.tsx"), so they must be in the same directory.

.csproj — Copy Tiled Files to Output

TMX files are loaded at runtime via ParseFromFile, not the content pipeline. All Tiled files must be copied to the output directory. Add this to the .csproj:

<ItemGroup>
  <Content Include="Content/Tiled/**" CopyToOutputDirectory="PreserveNewest" />
</ItemGroup>

Read the full file on GitHub · 180 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. 5d ago First seen · 180 lines · 60 tokens per session scan A 77a0f4a1610d

Subscribe to this mod's changes

tmx is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 3,431 once invoked, about $0.0003 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 2026-09-04.