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.
npx agentmods add instructions/jongalloway/dotnet-mcp/copilot-instructionsgit clone --depth 1 https://github.com/jongalloway/dotnet-mcpWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03736 | $0.03736 |
| Opus 5 | $0.01868 | $0.01868 |
| Sonnet 5 | $0.00747 | $0.00747 |
| Haiku 4.5 | $0.00374 | $0.00374 |
Grade A, and why
dotnet-mcp copilot-instructions.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for .NET MCP Server
Project Overview
This project is an MCP (Model Context Protocol) server that integrates with the .NET SDK. It provides both CLI command execution and direct SDK integration through official NuGet packages, offering rich metadata access and type-safe operations.
Important: This package is designed exclusively as an MCP server for AI assistants. It is not intended for use as a library or for programmatic consumption in other .NET applications. The only supported use case is running it as an MCP server via dnx or dotnet run.
Key Technologies
- .NET 10.0: The latest version of .NET (LTS - Long Term Support)
- Model Context Protocol SDK: Version 1.0.0
- Stdio Transport: Communication via standard input/output
- Microsoft.Extensions.Hosting: For application lifecycle management
- Microsoft.TemplateEngine.*: Direct integration with .NET Template Engine (v10.0.101)
- Microsoft.Build.*: MSBuild integration for framework validation (v18.0.2)
Architecture
The server uses a hybrid architecture:
- SDK Integration - For metadata, discovery, and validation (Template Engine, MSBuild)
- CLI Execution - For actual command execution (proven, reliable)
Code Style and Conventions
Naming Conventions
- Use PascalCase for class names, method names, and public members
- Use camelCase for local variables and parameters
- Use descriptive names that clearly indicate purpose
- Consolidated tool method names follow the pattern:
Dotnet{Noun}(e.g.,DotnetProject,DotnetPackage,DotnetSolution)- Each consolidated tool accepts an
actionparameter to specify the operation - This aligns with the consolidated tool design for better AI orchestration
- Each consolidated tool accepts an
- Helper class methods should be descriptive:
GetInstalledTemplatesAsync,IsLtsFramework
Attribute Usage
- Mark tool classes with
[McpServerToolType] - Mark tool methods with
[McpServerTool] - Prefer XML doc comments (
/// <summary>,/// <param>) for tool and parameter descriptions - Tool methods should be
partialso the MCP SDK analyzers can generate toolDescriptionmetadata from XML docs - Avoid manual
[Description("...")]on tools/parameters unless explicitly required for compatibility - Keep descriptions clear and concise
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.
- 2d ago First seen · 404 lines · 3,736 tokens per session scan A b5e230b5821f
dotnet-mcp copilot-instructions.md is an instructions file published in the GitHub repository jongalloway/dotnet-mcp (31 stars, last pushed 16d ago), licensed MIT. It adds 3,736 tokens to every session, about $0.0187 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 2026-08-30.
Other instructions, from other repositories
AgentEval maf-updates.instructions.md
Instructions for detecting and adapting to Microsoft Agent Framework (MAF) breaking changes.
CrestApps.AgentSkills copilot-instructions.md
Instructions for CrestApps/CrestApps.AgentSkills, covering crestapps.agentskills development instructions, project overview, four source projects, build & test and build (treat warnings as errors, run analyzers).
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
airi copilot-instructions.md
Copilot instructions for moeru-ai/airi, covering copilot repository instructions, general rules, validation and output format.
entroly CLAUDE.md
Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.
autonomous-os AGENTS.md
Instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.