Borrowing it
Nothing to install: this file belongs to AgentEvalHQ/AgentEval. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AgentEvalHQ/AgentEval/main/.github/instructions/maf-upgrade-preparation.instructions.mdgit clone --depth 1 https://github.com/AgentEvalHQ/AgentEvalWrote 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.
[](https://agentmods.dev/instructions/agentevalhq/agenteval/maf-upgrade-preparation)<a href="https://agentmods.dev/instructions/agentevalhq/agenteval/maf-upgrade-preparation"><img src="https://agentmods.dev/badge/instructions/agentevalhq/agenteval/maf-upgrade-preparation/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.03594 | $0.03594 |
| Opus 5.5 | $0.01438 | $0.01438 |
| Sonnet 5.5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00359 | $0.00359 |
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 2mo 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 — 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.propsis the authoritative current version - Do NOT update
Directory.Packages.propsyet — 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)
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.
- 2mo ago First seen · 285 lines · 3,594 tokens per session scan A 595b274418df
AgentEval maf-upgrade-preparation.instructions.md is an instructions file published in the GitHub repository AgentEvalHQ/AgentEval (157 stars, last pushed 4d ago), licensed MIT. It adds 3,594 tokens to every session, about $0.0144 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.