It helps compare framework versions, document required fixes in MAF/MAF-Upgrade-Plan.md, and prepare the later upgrade work.

It separates investigation from implementation, so developers can identify breaking or behavioral changes before changing the project’s NuGet dependency.

AgentEval maf-upgrade-preparation.instructions.md — Instructions file for GitHub Copilot by AgentEvalHQ: A set of instructions for preparing

Q: What is AgentEval maf-upgrade-preparation.instructions.md?

A set of instructions for preparing an upgrade to Microsoft Agent Framework, a .NET framework for building AI agents. It compares the current and newer source versions and produces an upgrade plan before package changes are made.

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/maf-upgrade-preparation

Clone the repo

git clone --depth 1 https://github.com/AgentEvalHQ/AgentEval

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/agentevalhq/agenteval/maf-upgrade-preparation.svg)](https://agentmods.dev/instructions/agentevalhq/agenteval/maf-upgrade-preparation)

Your own site

<a href="https://agentmods.dev/instructions/agentevalhq/agenteval/maf-upgrade-preparation"><img src="https://agentmods.dev/badge/instructions/agentevalhq/agenteval/maf-upgrade-preparation.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,594 This file is loaded in full into every session.

When invoked 3,594 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.

Model	Per session	Once invoked
Fable 5	$0.03594	$0.03594
Opus 5	$0.01797	$0.01797
Sonnet 5	$0.00719	$0.00719
Haiku 4.5	$0.00359	$0.00359

Measured 4d ago against content hash 595b274418df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentEval maf-upgrade-preparation.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 4d 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/instructions/maf-upgrade-preparation.instructions.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAF Upgrade Preparation

When to Use

This instruction is triggered when the user says any of:

"prepare for MAF upgrade"
"diff MAF vs MAFvnext"
"produce a MAF update plan"
"assess MAF changes"
"analyze the new MAF version"

What This Does

This is Phase 1 of a two-phase MAF upgrade workflow:

Phase 1 (this file):  Diff source → produce plan document
Phase 2 (maf-updates.instructions.md):  Update NuGet → implement plan → run tests

The output of Phase 1 is a markdown document (MAF/MAF-Upgrade-Plan.md) that serves as input to Phase 2.

Prerequisites

/MAF/ contains the current (or recent prior) MAF source for reference
/MAFVnext/ contains the newer MAF source to upgrade to
Both directories are gitignored and local-only
The version pinned in Directory.Packages.props is the authoritative current version
Do NOT update Directory.Packages.props yet — that happens in Phase 2

Solution Structure (Post-Modularization)

AgentEval is modularized into 7 sub-projects (see ADR-016). MAF dependencies are compile-time isolated in a separate project:

src/
├── AgentEval.Abstractions/   ← Interfaces, models — zero external deps
├── AgentEval.Core/           ← Metrics, assertions, comparison — no MAF deps
├── AgentEval.DataLoaders/    ← Dataset loading, exporters — no MAF deps
├── AgentEval.MAF/            ← MAF adapters + evaluators — ONLY project with MAF deps
│   ├── MAF/                  ← 7 adapter files (MAF type dependencies)
│   │   ├── MAFAgentAdapter.cs              ← Microsoft.Agents.AI
│   │   ├── MAFIdentifiableAgentAdapter.cs  ← Microsoft.Agents.AI
│   │   ├── MAFWorkflowEventBridge.cs       ← Microsoft.Agents.AI.Workflows (heaviest)
│   │   ├── MAFGraphExtractor.cs            ← Microsoft.Agents.AI.Workflows + Checkpointing
│   │   ├── MAFWorkflowAdapter.cs           ← Microsoft.Agents.AI.Workflows (factory only)
│   │   ├── MAFEvaluationHarness.cs         ← NO MAF deps (works through interfaces)
│   │   └── WorkflowEvaluationHarness.cs    ← NO MAF deps (works through interfaces)
│   └── Evaluators/           ← 6 files: MEAI IEvaluator "light path" bridge (no MAF deps, uses Microsoft.Extensions.AI.Evaluation)
│       ├── AdditionalContextHelper.cs
│       ├── AgentEvalEvaluator.cs
│       ├── AgentEvalEvaluators.cs
│       ├── AgentEvalMetricAdapter.cs
│       ├── ConversationExtractor.cs
│       └── ResultConverter.cs
├── AgentEval.Memory/         ← Memory evaluation — no direct MAF deps (gets MAF transitively)
├── AgentEval.RedTeam/        ← Security scanning — no MAF deps
└── AgentEval/                ← Umbrella NuGet package (embeds all sub-project DLLs)

Read the full file on GitHub · 285 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.

4d ago First seen · 285 lines · 3,594 tokens per session scan A 595b274418df

Subscribe to this mod's changes

AgentEval maf-upgrade-preparation.instructions.md is an instructions file published in the GitHub repository AgentEvalHQ/AgentEval (139 stars, last pushed yesterday), licensed MIT. It adds 3,594 tokens to every session, about $0.0180 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.

Planning agent agentic evals evaluations framework net

AgentEval maf-upgrade-preparation.instructions.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

MAF Upgrade Preparation

When to Use

What This Does

Prerequisites

Solution Structure (Post-Modularization)

What this file has done since we first saw it

Other instructions, from other repositories

zeroclaw CLAUDE.md

nuwax AGENTS.md

framework AGENTS.md

hands-on-modern-rl AGENTS.md

AgentGo AGENTS.md

elephant-agent copilot-instructions.md