agentmods.dev

DotNetAnalyzer CLAUDE.md

DotNetAnalyzer CLAUDE.md is an instructions file for coding agents from CartapenaBark/DotNetAnalyzer. It costs 584 tokens per session, scanned A, original, MIT.

Project instructions for DotNetAnalyzer, a .NET tool that uses Microsoft’s Roslyn code-analysis system to inspect C# code and provide an MCP server. MCP is a way for an AI assistant to call external tools.

In plain words
What is it for?
Use it when developing DotNetAnalyzer, running its tests and formatting checks, creating its NuGet package, installing it, or starting its MCP server.
Why use it?
It gives contributors the commands, coding rules, testing requirements, and safety checks needed to build, package, install, and run the tool consistently.

Instructions file

not rated 2 4mo ago A scan 584 tokens original MIT
View the source file CartapenaBark/DotNetAnalyzer
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 instructions/cartapenabark/dotnetanalyzer/claude-md
Clone the repo
git clone --depth 1 https://github.com/CartapenaBark/DotNetAnalyzer

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 DotNetAnalyzer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cartapenabark/dotnetanalyzer/claude-md.svg)](https://agentmods.dev/instructions/cartapenabark/dotnetanalyzer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cartapenabark/dotnetanalyzer/claude-md"><img src="https://agentmods.dev/badge/instructions/cartapenabark/dotnetanalyzer/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 584 This file is loaded in full into every session.
When invoked 584 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.00584 $0.00584
Opus 5 $0.00292 $0.00292
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00058 $0.00058

Measured 5d ago against content hash 2d5cad4355c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

DotNetAnalyzer CLAUDE.md 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 5d 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.md · 42 lines

What it actually says

CLAUDE.md

DotNetAnalyzer — .NET MCP 服务器，通过 Roslyn API 使 Claude Code 分析 C# 代码。 架构详情见 @docs/ARCHITECTURE.md，编码规范见 @docs/CODING_STANDARDS.md。

常用命令

构建和测试

  • dotnet build -c Release — 构建项目
  • dotnet test -c Release — 运行所有测试
  • dotnet test -c Release --filter "FullyQualifiedName~TestName" — 运行特定测试
  • dotnet format --verify-no-changes — 验证格式（CI 使用）

打包和安装

  • dotnet pack -c Release — 打包 NuGet（输出到 Bin/nupkg）
  • dotnet tool install --global --add-source ./Bin/nupkg DotNetAnalyzer — 安装
  • dotnet tool uninstall --global DotNetAnalyzer — 卸载

MCP 服务器

  • dotnet-analyzer mcp serve — 启动 MCP 服务器

提交前检查清单

  1. dotnet format --verify-no-changes
  2. dotnet build -c Release -warnaserror
  3. dotnet test -c Release

开发约定

  • 测试框架：xUnit + Moq + FluentAssertions，命名：MethodName_ExpectedBehavior_StateUnderTest
  • CI 跳过性能测试（Category!=Performance），多平台：Ubuntu/Windows/macOS
  • 所有路径必须通过 PathValidator.ValidateProjectPath/ValidateSolutionPath 验证
  • 版本号仅在 @src/DotNetAnalyzer.Cli/DotNetAnalyzer.Cli.csproj 中定义，不硬编码
  • 条件编译：NET8_0/NET9_0/NET10_0；C# 版本 12.0/13.0/14.0
  • 日志使用 ILogger<T> + LoggerMessage.Define() 模式
  • 配置使用 appsettings.json + IOptions<T> 模式
  • MCP 工具使用 [McpServerToolType] + [McpServerTool] 属性
  • 开发工作流详见 @docs/development-workflow.md

相关文档

@README.md | @docs/CODING_STANDARDS.md | @docs/development-workflow.md | @docs/api-guide.md | @CONFIGURATION.md | @CHANGELOG.md | @docs/analysis-credibility.md | @eng/product-metadata.json | https://github.com/CartapenaBark/DotNetAnalyzer/tree/develop/plugin

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. 5d ago First seen · 42 lines · 584 tokens per session scan A 2d5cad4355c3

Subscribe to this mod's changes

DotNetAnalyzer CLAUDE.md is an instructions file published in the GitHub repository CartapenaBark/DotNetAnalyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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 2026-08-31.

architectureclaude-codeclaude-code-plugincode-analysisdotnet
Related

Other instructions, from other repositories

truecourse CLAUDE.md

Claude Code instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.

truecourse-ai/truecourse · 8,118 tokens

graphify-dotnet copilot-instructions.md

Instructions for elbruno/graphify-dotnet, covering graphify-dotnet repository conventions, repository structure, ⚠️ critical rule: all code lives under src/, solution format and project conventions.

elbruno/graphify-dotnet · 2,171 tokens

RoselineMCP CLAUDE.md

Claude Code instructions for Atypical-Consulting/RoselineMCP, covering claude.md, project overview, documentation alignment (required), architecture and service layer architecture.

Atypical-Consulting/RoselineMCP · 10,398 tokens

dekko CLAUDE.md

Claude Code instructions for aahlijia/dekko, covering claude.md, what this project is, working in this repo and evaluation reports: test-repos/reports/.

aahlijia/dekko · 1,613 tokens

own-planner AGENTS.md

Instructions for am-space/own-planner, covering agents.md, common commands, verify only one stack, single test project, class, or method and run the console chat loop (type exit to quit).

am-space/own-planner · 1,768 tokens

codebase-intelligence CLAUDE.md

Instructions for bntvllnt/codebase-intelligence, covering codebase intelligence - claude code rules, project overview, architecture, pipeline and key conventions.

bntvllnt/codebase-intelligence · 2,108 tokens