XnaFiddle: Skill for Claude Code

.claude/skills/file-loading/SKILL.md

file-loading is a skill for Claude Code from vchelaru/XnaFiddle. It costs 65 tokens per session (3,308 once invoked), scanned A, original, MIT.

A guide to loading files and other assets into XnaFiddle, a browser-based environment for running XNA examples. It describes embedded files, fetched URLs, drag-and-drop files, and Gist imports, all stored in memory.

In plain words
What is it for?
Use it when adding asset formats, importing files, supporting drag-and-drop, loading content from a Gist, or exporting projects.
Why use it?
It explains how assets are handled when there is no normal disk or content pipeline. This helps prevent code from assuming that files can be read from a traditional project folder.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vchelaru/XnaFiddle's own configuration. It tells Claude Code how to work on XnaFiddle itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything XnaFiddle configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vchelaru/XnaFiddle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vchelaru/XnaFiddle/main/.claude/skills/file-loading/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vchelaru/XnaFiddle

Made for: Claude Code.

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 file-loading

README.md
[![agentmods](https://agentmods.dev/badge/skills/vchelaru/xnafiddle/file-loading.svg)](https://agentmods.dev/skills/vchelaru/xnafiddle/file-loading)
Your own site
<a href="https://agentmods.dev/skills/vchelaru/xnafiddle/file-loading"><img src="https://agentmods.dev/badge/skills/vchelaru/xnafiddle/file-loading.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,308 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 $0.00065 $0.03308
Opus 5 $0.00032 $0.01654
Sonnet 5 $0.00013 $0.00662
Haiku 4.5 $0.00006 $0.00331

Measured 2d ago against content hash 248b790b27be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

file-loading 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 2d 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.

.claude/skills/file-loading/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File Loading

XnaFiddle has no disk or traditional content pipeline. All assets live in memory and are loaded through InMemoryContentManager, a custom ContentManager subclass that serves files from a static Dictionary<string, byte[]>.

Four entry paths, one destination

Source Mechanism Ends up in SourceUrl set?
Example assets Embedded resources in the assembly, loaded by ExampleGallery.LoadAssets() RegisterContentFile() Yes — points to wwwroot/examples/{ExampleName}/{file}
URL-fetched assets FetchAndAddAssetUrl(url) via &assets= share param or URL input RegisterContentFile() Yes — the fetched URL
User drag-and-drop JS fileDropInterop -> OnFileDropped JSInvokable RegisterContentFile() No — cannot be re-fetched
Gist import LoadFromGistId: each gist file whose ext is in SupportedAssetExtensions is base64-decoded by DecodeGistAssetAsync (fetches raw_url when truncated) and registered via RegisterGistAsset RegisterContentFile() No (issue #82)

All four paths converge on RegisterContentFile(fileName, bytes) in Index.razor.cs, which does two things:

  1. InMemoryContentManager.AddFile(fileName, bytes) — stores data under the original filename AND the extension-stripped name (so Content.Load<Texture2D>("KniIcon") works without knowing the extension)
  2. contentFileCache.register(fileName, base64) via JS interop — registers the file in the JS-side XHR cache so TitleContainer.OpenStream() can resolve it (see below)

Supported formats

Controlled by SupportedAssetExtensions in Index.razor.cs:

  • .png — loaded as Texture2D via Texture2D.FromStream()
  • .wav — loaded as SoundEffect via SoundEffect.FromStream()
  • .fnt — BMFont text format; stored as raw bytes. The UI parses page lines to show which texture files the font references (so users know what companion .png files to also drop)
  • .ttf — TrueType font; stored as raw bytes for FontStashSharp
  • .ember — stored as raw bytes
  • .tmx .tsx .world .ldtk .ogmo .json .txt .xml — text/data formats (tilemap & level-editor files plus generic data); stored as raw bytes and read by user code via TitleContainer.OpenStream (no Load<T> branch)

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 65 tokens per session scan A 248b790b27be

Subscribe to this mod's changes

file-loading is a skill published in the GitHub repository vchelaru/XnaFiddle (13 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 3,308 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.