XnaFiddle: Skill for Claude Code

.claude/skills/share-snippet/SKILL.md

share-snippet is a skill for Claude Code from vchelaru/XnaFiddle. It costs 43 tokens per session (1,115 once invoked), scanned A, original, MIT.

A reference for sharing code snippets in XnaFiddle, including how code is reduced to a compact model and rebuilt later. It explains which parts survive sharing and which parts are dropped.

In plain words
What is it for?
Use it when implementing or reviewing the SnippetReverter and SnippetExpander round trip, or when choosing between code, snippet, and Gist sharing.
Why use it?
It helps developers avoid losing code or adding unwanted changes when converting between full source code and a snippet.

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/share-snippet/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 share-snippet

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vchelaru/xnafiddle/share-snippet"><img src="https://agentmods.dev/badge/skills/vchelaru/xnafiddle/share-snippet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,115 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 $0.00043 $0.01115
Opus 5 $0.00022 $0.00558
Sonnet 5 $0.00009 $0.00223
Haiku 4.5 $0.00004 $0.00112

Measured 4d ago against content hash aea0dfa38b72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

share-snippet 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 4d 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/share-snippet/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Share / Snippet round-trip

Three ways to share a fiddle. They differ in fidelity — this is the part that bites.

Mode URL Fidelity
Code (ShareAsCode) #code=<source> Lossless — stores the editor source verbatim
Snippet #snippet=<model> Lossy by design — round-trips through SnippetReverter -> SnippetModel -> SnippetExpander; only scaffold-shaped content survives
Gist external Partial; see the shaders skill

Shaders travel in all three. That is the shaders skill's territory — point there, don't re-document.

The fidelity contract (the snippet codec)

SnippetExpander and SnippetReverter are exact inverses around a fixed scaffold (a FiddleGame : Game skeleton). Only what fits a SnippetModel field survives the trip; anything the scaffold can't represent is dropped. The codec is symmetric: every line the expander injects is a line the reverter must strip, or sharing-then-resharing bloats.

  • Scaffold-owned boilerplate. The expander owns the constructor and a GraphicsDeviceManager graphics; field, plus the canonical method-body lines (base.Initialize/Update/Draw, GraphicsDevice.Clear(...)). The reverter strips exactly these back out (InjectedMembers set + the IsInjected* statement predicates). Keep the two sides in lockstep when editing either.
  • Constructor handoff (issue #83 — the crux). A custom constructor used to be dropped outright. Now SnippetModel.Constructor carries it: when present, the expander steps aside — emits neither its own graphics field nor the default ctor and reproduces the user's verbatim. The reverter captures the ctor body only when it differs from the canonical scaffold ctor (IsScaffoldConstructor, compared on whitespace-collapsed text), so scaffold-shaped snippets stay compact. Subtlety: once a custom ctor is captured, a user field literally named graphics must be kept rather than mistaken for the injected one.
  • Presets are inferred from using directives. IsGum/IsAposShapes/IsMonoGameExtended are detected on revert from the namespaces present (not stored explicitly), and each injects its members + method-body lines on expand / is stripped on revert. The flag set drives which injected lines the reverter recognizes.

Read the full file on GitHub · 47 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. 4d ago First seen · 47 lines · 43 tokens per session scan A aea0dfa38b72

Subscribe to this mod's changes

share-snippet is a skill published in the GitHub repository vchelaru/XnaFiddle (13 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 1,115 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens