skunit copilot-instructions.md

skunit copilot-instructions.md is an instructions file for GitHub Copilot from mehrandvd/skunit. It costs 2,101 tokens per session, scanned A, original, MIT.

A set of project instructions for skUnit, a .NET testing framework that checks chat and AI components using test scenarios written in Markdown files.

In plain words
What is it for?
Use it when working on skUnit: restoring dependencies, building the solution, running offline or full tests, formatting code, and handling demo projects or configuration.
Why use it?
It gives the coding agent the project's setup, build, testing, formatting, and configuration rules in one place. This reduces guesswork when changing or checking the code.

Instructions file for GitHub Copilot

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/mehrandvd/skunit/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/mehrandvd/skunit

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 skunit copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mehrandvd/skunit/copilot-instructions.svg)](https://agentmods.dev/instructions/mehrandvd/skunit/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/mehrandvd/skunit/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mehrandvd/skunit/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,101 This file is loaded in full into every session.
When invoked 2,101 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 $0.02101 $0.02101
Opus 5 $0.01051 $0.01051
Sonnet 5 $0.00420 $0.00420
Haiku 4.5 $0.00210 $0.00210

Measured 5d ago against content hash 2e0621000752, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skunit 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 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.

.github/copilot-instructions.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skUnit - Semantic Testing Framework for IChatClient and SemanticKernel

skUnit is a .NET testing framework for creating semantic tests for IChatClient implementations and SemanticKernel units using markdown scenario files.

ALWAYS reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.

Working Effectively

Bootstrap, Build, and Test

  • Initial setup: dotnet restore src/skUnit.sln -- takes 16 seconds. NEVER CANCEL. Set timeout to 30+ seconds.
  • Build the solution: dotnet build src/skUnit.sln --no-restore -- takes 12 seconds. NEVER CANCEL. Set timeout to 30+ seconds.
  • Run unit tests (works offline): dotnet test src/skUnit.sln --no-build --filter "FullyQualifiedName~JsonCheckAssertionTests|FullyQualifiedName~FunctionCallAssertionTests|FullyQualifiedName~ParseChatScenarioTests" -- takes 1 second
  • Full test suite (requires API keys): dotnet test src/skUnit.sln --no-build -- requires Azure OpenAI configuration

Code Quality

  • Format code: dotnet format src/skUnit.sln -- takes 8 seconds. NEVER CANCEL. Set timeout to 30+ seconds.
  • Verify formatting: dotnet format src/skUnit.sln --verify-no-changes -- fails if formatting needed
  • ALWAYS run dotnet format src/skUnit.sln before committing changes or CI will have formatting issues

Demo Projects

  • TDD REPL Demo: Located in demos/Demo.TddRepl/
    • Build: cd demos/Demo.TddRepl && dotnet restore Demo.TddRepl.sln && dotnet build Demo.TddRepl.sln --no-restore
    • Shows how to use skUnit for test-driven development of chat applications
  • MCP Demo: Located in demos/Demo.TddMcp/
    • Shows integration with Model Context Protocol tools
  • Shop Demo: Located in demos/Demo.TddShop/
    • Complex multi-scenario chat testing

Requirements and Configuration

System Requirements

  • .NET 8.0 (verified working with 8.0.118)
  • Azure OpenAI API access (for integration tests and semantic validation)

Read the full file on GitHub · 188 lines

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 · 188 lines · 2,101 tokens per session scan A 2e0621000752

Subscribe to this mod's changes

skunit copilot-instructions.md is an instructions file published in the GitHub repository mehrandvd/skunit (181 stars, last pushed 1mo ago), licensed MIT. It adds 2,101 tokens to every session, about $0.0105 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.