XnaFiddle: Skill for Claude Code

.claude/skills/intellisense/SKILL.md

intellisense is a skill for Claude Code from vchelaru/XnaFiddle. It costs 67 tokens per session (3,583 once invoked), scanned A, original, MIT.

An in-browser IntelliSense service for C# that connects Roslyn language analysis to the Monaco editor through Blazor WebAssembly. IntelliSense means editor help such as autocomplete, hover details, signature help, and live error indicators.

In plain words
What is it for?
Use it to add C# completion, symbol hover information, function-parameter help, and live compiler diagnostics to Monaco, with XML documentation formatted for the editor.
Why use it?
It lets a browser-based code editor provide compiler-aware feedback instead of treating code as plain text, including diagnostics based on the same references used for compilation.

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/intellisense/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 intellisense

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vchelaru/xnafiddle/intellisense"><img src="https://agentmods.dev/badge/skills/vchelaru/xnafiddle/intellisense.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,583 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 $0.00067 $0.03583
Opus 5 $0.00034 $0.01792
Sonnet 5 $0.00013 $0.00717
Haiku 4.5 $0.00007 $0.00358

Measured 4d ago against content hash 3505fda2cdbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

intellisense 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/intellisense/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture

One IntellisenseService singleton (DI, app lifetime) holds an AdhocWorkspace + a single User.cs document. Every JSInvokable call swaps document text via Solution.WithDocumentText(_documentId, ...) + _workspace.TryApplyChanges(...), then drives Roslyn:

  • Completion: CompletionService.GetService(document).GetCompletionsAsync(...)
  • Hover: SemanticModel.GetDeclaredSymbol / GetSymbolInfo + custom SymbolDisplayFormat
  • Signature help: walk syntax tree for enclosing InvocationExpressionSyntax, resolve via SemanticModel.GetSymbolInfo, format manually
  • Live diagnostics: Project.GetCompilationAsync().GetDiagnostics()

SignatureHelpService and QuickInfoService are internal in Roslyn 4.14, so hover and sig help bypass them and drive the SemanticModel directly. Metadata references are pulled from CompilationService.GetMetadataReferencesAsync so the completion surface exactly matches the compile surface.

Key files

File Purpose
XnaFiddle.BlazorGL/IntellisenseService.cs Singleton; workspace, CTS-per-op, all four JSInvokables
XnaFiddle.BlazorGL/Intellisense/XmlDocFormatter.cs XML doc -> Monaco-flavor markdown
XnaFiddle.BlazorGL/Intellisense/SignatureFormatter.cs Builds label + per-param offset ranges
XnaFiddle.BlazorGL/Intellisense/ActiveParameterLocator.cs Top-level-comma counter for active param
XnaFiddle.BlazorGL/wwwroot/js/monaco-interop.js Monaco providers, debounce, cache, marker layers
XnaFiddle.BlazorGL/Pages/Index.razor[.cs] DI wiring, warmup kickoff, loading indicator
XnaFiddle.Tests/Intellisense/*Tests.cs Tests for the pure-logic helpers only

WASM single-thread constraint (critical)

All Roslyn work runs on the one WASM thread; a long call blocks typing. Three layered mitigations:

  1. JS-side tiered debounce in _registerCompletions:
    • . (member access): 50ms
    • Ctrl+Space on empty word: 0ms (fire immediately)
    • Typing with word length >= 3: 400ms
    • Typing with word length < 3: skipped entirely (returns {suggestions: []})
  2. Word-start cache (_completionCache, keyed by {sourcePrefix, wordStartOffset}): while the user types inside the same word, Monaco filters client-side against the cached result and no .NET call happens.
  3. Per-op CancellationTokenSource in IntellisenseService (_currentCompletionCts, _currentSignatureHelpCts, _currentHoverCts, _currentDiagnosticsCts): a new request on the same channel cancels the prior one mid-flight. Separate CTS per op means sig help and completion don't cancel each other.

Read the full file on GitHub · 132 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 · 132 lines · 67 tokens per session scan A 3505fda2cdbe

Subscribe to this mod's changes

intellisense is a skill published in the GitHub repository vchelaru/XnaFiddle (13 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 3,583 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.

Related

Other skills, from other repositories

avalonia-viewmodels-zafiro

Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI.

sickn33/agentic-awesome-skills · 26 tokens

avalonia-zafiro-development

Mandatory skills, conventions, and behavioral rules for Avalonia UI development using the Zafiro toolkit.

sickn33/agentic-awesome-skills · 27 tokens

convert-blazor-server-to-webapp

Guides conversion of a pre-.NET 8 Blazor Server app into a .NET 8+ Blazor Web App. USE FOR: migrating apps that use AddServerSideBlazor and MapBlazorHub to the AddRazorComponents/MapRazorComponents model, converting Host.cshtml to an App.razor root component, replacing blazor.server.js with blazor.web.js, migrating…

dotnet/skills · 176 tokens

create-blazor-project

Create a new ASP.NET Core web application or web site using Blazor. USE FOR: creating a new Blazor web app, scaffolding a new web project, starting a new web site, choosing render modes (Static SSR, Interactive Server, Interactive WebAssembly, Auto), running dotnet new blazor with the right options, setting up initial…

dotnet/skills · 104 tokens

use-js-interop

Add, review, or fix JavaScript interop in Blazor components. USE FOR: calling JavaScript from Blazor, calling .NET from JavaScript, collocated .razor.js modules, IJSRuntime, IJSObjectReference lifecycle, DotNetObjectReference, ElementReference, timing rules for when JS is available, IAsyncDisposable disposal of JS…

dotnet/skills · 114 tokens

coordinate-components

Share state between components that don't have a direct parent-child parameter relationship, using cascading values, scoped services with change events, or CascadingValueSource via DI. USE WHEN the user needs a CascadingParameter or CascadingValue that works across render mode boundaries, a shopping cart or…

dotnet/skills · 182 tokens