AgentEval copilot-instructions.md

A contributor guide for AgentEval, a .NET toolkit for evaluating AI agents built around Microsoft Agent Framework. It explains the project's folders, architecture, setup, and build and test conventions.

In plain words
What is it for?
Use it when navigating AgentEval, choosing the right project for a change, configuring the development environment, or running builds and tests.
Why use it?
It gives coding assistants and developers the project context they need before making changes. This lowers the risk of putting code in the wrong package or breaking the repository's structure.

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/agentevalhq/agenteval/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/AgentEvalHQ/AgentEval

Made for: GitHub Copilot.

Per session 2,994 This file is loaded in full into every session.
When invoked 2,994 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 $0.02994 $0.02994
Opus 5 $0.01497 $0.01497
Sonnet 5 $0.00599 $0.00599
Haiku 4.5 $0.00299 $0.00299

Measured yesterday against content hash 66a5d6ea958e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentEval 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 yesterday.

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 · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentEval - AI Coding Agent Instructions

AgentEval is the comprehensive .NET evaluation toolkit for AI agents, built primarily for Microsoft Agent Framework (MAF) with Microsoft.Extensions.AI. What RAGAS and DeepEval do for Python, AgentEval does for .NET—plus tool chain evaluation, behavioral policies, and calibrated multi-judge scoring.

Architecture Overview

AgentEval/
├── src/
│   ├── AgentEval.Abstractions/  # Public contracts: IMetric, IEvaluableAgent, models
│   ├── AgentEval.Core/          # Implementations: metrics, assertions, comparison, tracing
│   ├── AgentEval.DataLoaders/   # Data loaders, exporters, output formatting
│   ├── AgentEval.MAF/           # Microsoft Agent Framework integration
│   ├── AgentEval.RedTeam/       # Security scanning, attack types, compliance
│   └── AgentEval/               # Umbrella packaging project (NuGet: AgentEval)
├── tests/AgentEval.Tests/       # xUnit tests, mirrors src/ structure
└── samples/AgentEval.Samples/   # runnable samples (organised in groups A–J)

All library sub-projects use RootNamespace=AgentEval to preserve original namespaces. Only the umbrella is IsPackable=true; the single NuGet package embeds every sub-project DLL per TFM. The CLI lives in this repository at src/AgentEval.Cli/ and is the canonical source for the AgentEval.Cli NuGet package (packed as the agenteval dotnet tool); the former external AgentEvalHQ/AgentEval.Cli repository is being retired.

Environment Setup

Required environment variables for samples and integration tests:

$env:AZURE_OPENAI_ENDPOINT = "https://your-resource.openai.azure.com/"
$env:AZURE_OPENAI_API_KEY = "your-api-key"
# Optional: Secondary models for comparison
$env:AZURE_OPENAI_DEPLOYMENT = "gpt-4o"           # Primary model
$env:AZURE_OPENAI_DEPLOYMENT_2 = "gpt-4o-mini"    # Secondary model

Build & Test Commands

dotnet build                 # Build all projects
dotnet test                  # Run all tests (×3 TFMs)
dotnet run --project samples/AgentEval.Samples  # Run samples
dotnet pack src/AgentEval   # Create NuGet package

Read the full file on GitHub · 307 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. yesterday First seen · 307 lines · 2,994 tokens per session scan A 66a5d6ea958e

Subscribe to this mod's changes

AgentEval copilot-instructions.md is an instructions file published in the GitHub repository AgentEvalHQ/AgentEval (138 stars, last pushed yesterday), licensed MIT. It adds 2,994 tokens to every session, about $0.0150 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.