using-dotnet

using-dotnet is a skill for Claude Code, Codex from novotnyllc/dotnet-artisan. It costs 126 tokens per session (2,172 once invoked), scanned C, original, MIT.

A routing guide for .NET work, covering technologies such as C#, ASP.NET Core, Entity Framework Core, Blazor, and related tools. It detects .NET tasks from the request or project files and loads the appropriate guidance.

In plain words
What is it for?
Use it as the first step for .NET development, testing, debugging, security, performance, deployment, and tooling requests.
Why use it?
It ensures .NET tasks begin with the right version-specific standards and specialist instructions. It also encourages simple solutions and avoids unnecessary layers.

Skill for Claude CodeCodex

Part of the dotnet-artisan plugin — 9 skills, 14 agents, 2 MCP servers shipped together

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.

agentmods
npx agentmods add skills/novotnyllc/dotnet-artisan/using-dotnet
Any agent
npx skills add novotnyllc/dotnet-artisan --skill using-dotnet
Clone the repo
git clone --depth 1 https://github.com/novotnyllc/dotnet-artisan

Made for: Claude Code, Codex.

Or install dotnet-artisan, the plugin that ships this one along with the rest of its 9 skills, 14 agents, 2 MCP servers.

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 using-dotnet

README.md
[![agentmods](https://agentmods.dev/badge/skills/novotnyllc/dotnet-artisan/using-dotnet.svg)](https://agentmods.dev/skills/novotnyllc/dotnet-artisan/using-dotnet)
Your own site
<a href="https://agentmods.dev/skills/novotnyllc/dotnet-artisan/using-dotnet"><img src="https://agentmods.dev/badge/skills/novotnyllc/dotnet-artisan/using-dotnet.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00126 $0.02172
Opus 5 $0.00063 $0.01086
Sonnet 5 $0.00025 $0.00434
Haiku 4.5 $0.00013 $0.00217

Measured 4d ago against content hash 174b8ba77e59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

using-dotnet scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

3. **Check SDK availability** — If `dotnet --version` fails and no `DOTNET_ROOT` is set, install the SDK before proceeding. This takes under a minute with no privileges required. See `dotnet-tooling`'s `references/dotnet

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **Check SDK availability** — If `dotnet --version` fails and no `DOTNET_ROOT` is set, install the SDK before proceeding. This takes under a minute with no privileges required. See `dotnet-tooling`'s `references/dotnet
plugins/dotnet-artisan/skills/using-dotnet/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.

using-dotnet

Scope

  • Establishing .NET/C# routing discipline before clarifying questions, planning, command execution, or edits.
  • Detecting .NET intent from prompt and repository signals (.sln, .slnx, .csproj, global.json, .cs).
  • Enforcing first-step routing through dotnet-advisor and baseline loading order.
  • Defining priority and rigidity rules for downstream skill invocation.

Out of scope

  • C# implementation details and coding-standard specifics -> dotnet-csharp
  • Deep domain implementation patterns -> dotnet-api, dotnet-ui, dotnet-testing, dotnet-devops, dotnet-tooling, dotnet-debugging
  • Specialist deep-review workflows -> dotnet-security-reviewer, dotnet-performance-analyst, dotnet-testing-specialist

Simplicity First (KISS)

Write the simplest code that solves the problem. Agents consistently over-engineer — more abstractions, more layers, more indirection than the task warrants.

  • Do the direct thing. If you need a file, create it — don't write code that generates it. If you need data, put it where it belongs — don't assemble it from embedded strings at runtime. When you catch yourself building something indirect (a generator, a template, a wrapper), stop and ask: "Can I just do this directly?"
  • Write readable code, not clever code. A plain if/else over a chain of ternaries. A foreach over a hard-to-read LINQ expression. A flat method over nested callbacks. Clear beats compact. This does NOT mean avoiding modern C# — use latest language features ([..4], list patterns, primary constructors, raw string literals, collection expressions). Modern syntax is concise AND readable. The target is convoluted logic, not concise syntax.
  • Don't add what wasn't asked for. No extra config options, no "while we're at it" refactors, no preemptive error handling for impossible scenarios, no comments or XML docs on code unrelated to the current task.
  • Match architecture to scope. Simple CRUD doesn't need DDD, MediatR, CQRS, or a pipeline of behaviors. A 20-line handler doesn't need 5 files. Scale the pattern to the problem.
  • Earn every abstraction. Don't create IOrderService for one OrderService. Don't extract a helper for something that happens once. Three similar lines of code are fine — extract only when a real pattern emerges across 3+ call sites.
  • Use what the framework gives you. DbContext is your Unit of Work. DbSet<T> is your repository. .NET has TimeProvider, ILogger<T>, IHttpClientFactory, System.Text.Json. Use them directly — don't wrap, don't abstract, don't add a NuGet package for something the framework already does.
  • Fewer files, fewer layers. In new or small projects, don't split into Controller + Service + Repository + DTO + Mapper + Interface when one or two files will do. In existing codebases, follow the established patterns. Add layers only when the code gets hard to understand without them.

Read the full file on GitHub · 132 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 126 tokens per session scan C 174b8ba77e59

Subscribe to this mod's changes

using-dotnet is a skill published in the GitHub repository novotnyllc/dotnet-artisan (228 stars, last pushed 17d ago), licensed MIT. It adds 126 tokens to every session and 2,172 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

agents-sdk-dotnet

Use when any code imports Microsoft.Agents.Hosting.AspNetCore, Microsoft.Agents.Builder, or related Agents SDK packages, or when the user is building, configuring, or asking questions about a Microsoft 365 Agents SDK agent in C# / .NET. Trigger on questions about appsettings.json, connection configuration…

microsoft/Agents · 112 tokens

agents-sdk-dotnet-otel

Use when adding, configuring, validating, or troubleshooting OpenTelemetry observability for a Microsoft 365 Agents SDK application in C# / .NET. Trigger when the user mentions OpenTelemetry, OTel, telemetry, traces, metrics, logs, OTLP, Aspire Dashboard, Application Insights, Azure Monitor, distributed tracing…

microsoft/Agents · 86 tokens

bf-to-agents-sdk-dotnet-migration

Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.

microsoft/Agents · 56 tokens

agents-sdk-dotnet-debugging

Use when troubleshooting an agent built with the Microsoft Agents SDK (Microsoft.Agents.Hosting.AspNetCore and related packages) in C# / .NET. Trigger on any of these symptoms: build or C# compile errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, appsettings.json…

microsoft/Agents · 136 tokens

code-review-csharp

Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".

pnp/copilot-prompts · 66 tokens