XnaFiddle: Skill for Claude Code

.claude/skills/project-export/SKILL.md

project-export is a skill for Claude Code from vchelaru/XnaFiddle. It costs 72 tokens per session (3,231 once invoked), scanned A, original, MIT.

A project guide for XnaFiddle's export system, which turns browser-created game projects into downloadable projects for other platforms and runtimes. It explains where export targets, generated project files, and dependencies are handled.

In plain words
What is it for?
Use it when changing export targets, generated project files or archives, or checking whether a library belongs in an exported project.
Why use it?
Browser execution and exported projects use different runtimes, so treating them as the same can lead to incorrect implementation decisions.

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/project-export/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 project-export

README.md
[![agentmods](https://agentmods.dev/badge/skills/vchelaru/xnafiddle/project-export.svg)](https://agentmods.dev/skills/vchelaru/xnafiddle/project-export)
Your own site
<a href="https://agentmods.dev/skills/vchelaru/xnafiddle/project-export"><img src="https://agentmods.dev/badge/skills/vchelaru/xnafiddle/project-export.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,231 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 $0.00072 $0.03231
Opus 5 $0.00036 $0.01615
Sonnet 5 $0.00014 $0.00646
Haiku 4.5 $0.00007 $0.00323

Measured yesterday against content hash d4c0fac80411, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project-export 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 yesterday.

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/project-export/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Export

Read this first: in-browser runtime vs. export targets

XnaFiddle always runs the user's code in the browser via KNI's BlazorGL platform — pure-managed, rendering to WebGL through JS interop, no native code. There is exactly one browser runtime.

"Supports MonoGame and KNI" does not mean two browser runtimes. KNI, MonoGame, and FNA are export targets: the export feature generates a buildable project for a chosen platform/runtime. A fiddle authored against KNI-in-browser can be exported to, e.g., MonoGame DesktopGL — a different library and a different runtime that builds and runs outside the browser.

Consequence: a question about "supporting library X" is about the exported project's generated csproj, not about running X in the browser. Do not analyze native P/Invoke-in-WASM constraints for an export target — that is the wrong question. (A past agent wrongly assumed FNA would need to run in the browser and went down exactly that dead end. Preventing that mistake is half the reason this skill exists.)

Where to look

  • XnaFiddle.Core/ProjectExporter.cs — generates the zip: builds the package list, emits .slnx / .csproj / entry points / Game1.cs per target.
  • XnaFiddle.Core/IExportableLibrary.cs — plugin hook. Third-party libraries implement it to declare (a) how to detect their usage in source and (b) which NuGet packages to emit per ExportTarget. Also defines ExportTargetExtensions.IsKni().

The target matrix

ExportTarget enum is the full list of supported targets:

  • KNI: DesktopGL, WindowsDX, Android, BlazorGL
  • MonoGame: DesktopGL, WindowsDX, Android
  • FNA: Desktop only (single target FnaDesktop, via the FNA.NET NuGet package — an opinionated third-party fork that bundles native libs)

One runtime family per export — platforms never mix

The export dialog has a single runtime selector (_exportRuntime: KNI / MonoGame / FNA); the platform checkboxes are within that family. So a multi-platform export is always one family — KNI and MonoGame can never be combined, and FNA is single-target. This is enforced in the UI (SetExportRuntime, the runtime radios), so ExportMultiPlatform's shared common project only ever sees one family. The exporter itself hard-blocks only the FNA-mixing case (Export(targets,…) throws); the KNI/MonoGame split is a UI guarantee. Design consequence: per-target logic never has to reconcile two framework families in one solution.

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 72 tokens per session scan A d4c0fac80411

Subscribe to this mod's changes

project-export is a skill published in the GitHub repository vchelaru/XnaFiddle (13 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 3,231 once invoked, about $0.0004 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.