dotnet-template-mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

dotnet-template-mcp copilot-instructions.md is an instructions file for GitHub Copilot from YuliiaKovalova/dotnet-template-mcp. It costs 456 tokens per session, scanned A, original, MIT.

Rules for using .NET project-generation tools when a user asks to create or set up a project, solution, or template. They direct the agent to use the server's template tools instead of direct dotnet new commands.

In plain words
What is it for?
Use them to resolve a project description to a template, inspect or compare templates, preview files, instantiate projects, analyze solutions, and upgrade NuGet packages.
Why use it?
They provide smart defaults, parameter validation, previews, and template lookup that direct command use does not provide.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is YuliiaKovalova/dotnet-template-mcp's own configuration. It tells GitHub Copilot how to work on dotnet-template-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dotnet-template-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to YuliiaKovalova/dotnet-template-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/YuliiaKovalova/dotnet-template-mcp/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/YuliiaKovalova/dotnet-template-mcp

Made for: GitHub Copilot.

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 dotnet-template-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yuliiakovalova/dotnet-template-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/yuliiakovalova/dotnet-template-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/yuliiakovalova/dotnet-template-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/yuliiakovalova/dotnet-template-mcp/copilot-instructions/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.

agentmods 80×15 button for dotnet-template-mcp copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yuliiakovalova/dotnet-template-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/yuliiakovalova/dotnet-template-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 456 This file is loaded in full into every session.
When invoked 456 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00456 $0.00456
Opus 5 $0.00228 $0.00228
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00046 $0.00046

Measured 9d ago against content hash 43403383e517, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dotnet-template-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 9d 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.

.github/copilot-instructions.md · 28 lines

What it actually says

When the user asks to create, scaffold, or set up a .NET project, template, or solution:

  • Use the template_from_intent MCP tool to resolve their natural-language description to the best template and parameters — do NOT use dotnet new directly.
  • Use template_inspect to show template details instead of dotnet new --help.
  • Use template_compare to compare 2+ templates side by side when the user is deciding between options (e.g., webapi vs webapp, blazorserver vs blazorwasm).
  • Use template_dry_run to preview files before creating.
  • Use template_instantiate to create projects instead of dotnet new.
  • Use template_search to find templates instead of dotnet new list.

These MCP tools provide smart defaults, parameter validation, and auto-resolve from NuGet — capabilities that dotnet new alone does not have.

When the user asks about their solution or project structure:

  • Use solution_analyze to inspect solution structure, target frameworks, CPM status, and NuGet config.

When the user wants to update or upgrade NuGet package versions:

  • Use packages_upgrade to scan a project, solution, or directory for outdated PackageReference/PackageVersion entries and report (or apply) upgrades to the latest stable versions. It is CPM-aware (updates Directory.Packages.props), defaults to a report-only preview, and only writes changes when called with apply=true.

When the user is authoring, reviewing, or debugging a custom dotnet template:

  • Use template_validate to check template.json for errors BEFORE publishing or testing. It catches missing required fields, invalid parameters, choice conflicts, constraint issues, and common authoring mistakes.
  • Use template_create_from_existing to reverse-engineer a reusable template from an existing .csproj that matches repo conventions (SDK type, analyzers, CPM, build props).

When the user wants to create multiple items together (e.g., project + gitignore + editorconfig):

  • Use template_compose to execute a sequence of template operations in one call instead of running multiple dotnet new commands.
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. 9d ago First seen · 28 lines · 456 tokens per session scan A 43403383e517

Subscribe to this mod's changes

dotnet-template-mcp copilot-instructions.md is an instructions file published in the GitHub repository YuliiaKovalova/dotnet-template-mcp (8 stars, last pushed 18d ago), licensed MIT. It adds 456 tokens to every session, about $0.0023 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.