.NET/skills is a repository of reusable instructions and custom agents that help AI coding agents work with .NET and C#. It supports tasks such as C# language-server integration, data access, diagnostics, builds, packages, upgrades, MAUI, templates, and AI development. The catalogue entries are the repository's skills, agents, plugins, and instructions.
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.
git clone --depth 1 https://github.com/dotnet/skillsWrote 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.
[](https://agentmods.dev/plugins/dotnet/skills/dotnet-diag)<a href="https://agentmods.dev/plugins/dotnet/skills/dotnet-diag"><img src="https://agentmods.dev/badge/plugins/dotnet/skills/dotnet-diag/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.
<a href="https://agentmods.dev/plugins/dotnet/skills/dotnet-diag"><img src="https://agentmods.dev/badge/plugins/dotnet/skills/dotnet-diag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dotnet-diag 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 11d 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.
What it actually says
{
"name": "dotnet-diag",
"version": "0.1.3",
"description": "Skills for .NET performance investigations, debugging, and incident analysis.",
"skills": ["./skills/"],
"agents": ["./agents/optimizing-dotnet-performance.agent.md"]
}
What it installs
The manifest is a name and a version. 7 skills, 1 agent travel with it, and installing the plugin installs all of them — 932 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill clr-activation-debugging A 102 tokens
- Skill analyzing-dotnet-performance A 64 tokens
- Skill microbenchmarking A 142 tokens
- Skill android-tombstone-symbolication A 176 tokens
- Skill apple-crash-symbolication A 217 tokens
- Skill dump-collect A 96 tokens
- Skill dotnet-trace-collect A 59 tokens
- Agent optimizing-dotnet-performance A 76 tokens
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.
- 11d ago Changed a728582903ce
- 1mo ago Changed c85612f01edc
- 1mo ago First seen · 8 lines scan A cbd394e771af
dotnet-diag is a plugin published in the GitHub repository dotnet/skills (5,660 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
memorylens
On-demand .NET memory profiling with concrete code fix suggestions — no profiler to install.
sherlock
Sherlock MCP server plus a skill for inspecting .NET assemblies, types, members and call graphs.
resharper-cli-mcp
JetBrains ReSharper command-line inspection and cleanup for C#, over MCP. Unofficial — not affiliated with or endorsed by JetBrains.
glidermcp
Connect coding agents to the local GliderMCP C# semantic analysis server.
eplan-tools marketplace
Plugin marketplace listing 1 plugin: eplan-development.
code-review
Autonomous C#/.NET code review — fail-fast pipeline with mechanical checks + AI sub-agents (performance, architecture, correctness, UI/Blazor).