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.
/plugin marketplace add peterblazejewicz/claude-pluginsnpx agentmods add plugins/peterblazejewicz/claude-plugins/dotnet-skillsgit clone --depth 1 https://github.com/peterblazejewicz/claude-pluginsWrote 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/peterblazejewicz/claude-plugins/dotnet-skills)<a href="https://agentmods.dev/plugins/peterblazejewicz/claude-plugins/dotnet-skills"><img src="https://agentmods.dev/badge/plugins/peterblazejewicz/claude-plugins/dotnet-skills.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
dotnet-skills 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.
What it actually says
{
"name": "dotnet-skills",
"version": "2.6.0",
"description": "Agent skills for .NET 8+ (Avalonia, ASP.NET Core, Blazor, MAUI, EF Core, xUnit/MSTest). Adapted from addyosmani/agent-skills (MIT).",
"author": {
"name": "Piotr Błażejewicz",
"email": "[email protected]"
},
"license": "MIT",
"repository": "https://github.com/peterblazejewicz/claude-plugins",
"homepage": "https://github.com/peterblazejewicz/claude-plugins/tree/main/plugins/dotnet-skills",
"keywords": [
"dotnet",
"csharp",
"agent-skills",
"avalonia",
"aspnetcore",
"blazor",
"maui",
"efcore",
"xunit",
"mstest",
"tdd"
],
"category": "developer-tools",
"skills": "./skills/",
"commands": "./commands/"
}
What it installs
The manifest is a name and a version. 24 skills, 9 commands, 4 agents travel with it, and installing the plugin installs all of them — 2,563 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill performance-optimization-dotnet A 105 tokens
- Skill test-driven-development A 103 tokens
- Skill api-and-interface-design A 64 tokens
- Skill ci-cd-and-automation A 105 tokens
- Skill code-review-and-quality A 68 tokens
- Skill code-simplification A 69 tokens
- Skill shipping-and-launch A 95 tokens
- Skill using-agent-skills A 89 tokens
- Skill context-engineering A 80 tokens
- Skill deprecation-and-migration A 62 tokens
- Skill documentation-and-adrs A 68 tokens
- Skill git-workflow-and-versioning A 76 tokens
- Skill source-driven-development A 70 tokens
- Skill incremental-implementation A 71 tokens
- Skill observability-and-instrumentation A 83 tokens
- Skill spec-driven-development A 82 tokens
- Skill idea-refine A 73 tokens
- Skill security-and-hardening B 99 tokens
- Skill integration-testing-dotnet B 113 tokens
- Skill planning-and-task-breakdown B 75 tokens
- Skill frontend-ui-engineering-avalonia C 110 tokens
- Skill debugging-and-error-recovery A 84 tokens
- Skill doubt-driven-development A 74 tokens
- Skill interview-me A 108 tokens
- Command ship A 27 tokens
- Command dotnet-skills A 75 tokens
- Command build A 42 tokens
- Command webperf A 23 tokens
- Command code-simplify A 16 tokens
- Command plan A 24 tokens
- Command review A 22 tokens
- Command test A 30 tokens
- Command spec A 19 tokens
- Agent web-performance-auditor A 69 tokens
- Agent code-reviewer A 68 tokens
- Agent test-engineer A 73 tokens
- Agent security-auditor B 49 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.
- 4d ago First seen · 29 lines scan A 9467e6617564
dotnet-skills is a plugin published in the GitHub repository peterblazejewicz/claude-plugins (7 stars, last pushed 2mo ago), 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 2026-08-31.
Other plugins, from other repositories
godot-prompter
Agentic skills framework for Godot 4.x game development — 55 domain-specific skills for GDScript and C#.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.