maui-labs AGENTS.md

A repository guide for experimental .NET MAUI packages arranged as a multi-product monorepo, meaning one repository containing several related products. It describes the products, package layout, technology stack, build process, and command-line tools.

In plain words
What is it for?
Use it when changing the MAUI command-line tool, Android or Apple platform management, device and emulator support, startup profiling, project versioning, port diagnostics, DevFlow automation, or related packages and tests.
Why use it?
It helps coding agents find the correct product, solution, package, and workflow before making a change. This reduces accidental edits to the wrong component and clarifies how the shared MAUI tooling is divided.

Instructions file for CodexOpenCode

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/dotnet/maui-labs/agents-md
Clone the repo
git clone --depth 1 https://github.com/dotnet/maui-labs

Made for: Codex, OpenCode.

Per session 5,419 This file is loaded in full into every session.
When invoked 5,419 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 $0.05419 $0.05419
Opus 5 $0.02710 $0.02710
Sonnet 5 $0.01084 $0.01084
Haiku 4.5 $0.00542 $0.00542

Measured yesterday against content hash 2445a9fc3cbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maui-labs AGENTS.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.

AGENTS.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Instructions for GitHub Copilot and other AI coding agents working with the maui-labs repository.

Repository Overview

This repository hosts experimental .NET MAUI packages. It is a multi-product mono-repo — each product lives under src/{Product}/ with its own version, solution filter, and CI workflow.

Products

Product Package / Tool Description
Cli Microsoft.Maui.Cli (global tool: maui), Microsoft.Maui.ProfilingHelper Unified MAUI command-line tool: environment diagnostics (maui doctor), Android SDK/JDK/emulator management, Apple platform management, device listing, maui go for rapid prototyping, maui profile startup for performance tracing, maui project version for project version management, maui port check for TCP port diagnostics, and the maui devflow automation surface. Microsoft.Maui.ProfilingHelper is a lightweight helper library injected by the CLI to drive the startup profiling exit-control handshake; it can also be referenced directly to mark startup completion via MauiProfilingMarker.Complete().
DevFlow Microsoft.Maui.DevFlow.* packages plus the unified maui devflow CLI surface Runtime MAUI automation toolkit. In-app agent with HTTP API, visual tree inspection, CDP bridge for Blazor WebViews, MCP server for AI agents, cross-platform driver library.
Comet Comet, Comet.SourceGenerator, Comet.Layout.Yoga Experimental MVU UI framework for .NET MAUI — C# fluent UI, signals/reactive state, Yoga layout.
Go Microsoft.Maui.Go.Server + Comet Go companion app Single-file Comet apps server and companion app for rapid prototyping (alpha; sister to Comet).
Essentials.AI Microsoft.Maui.Essentials.AI On-device AI for .NET MAUI — semantic search, chat completion, embeddings, and tool use against local models.
AIExtensions Microsoft.Maui.AI.Attributes Source-generated AI tool bindings — turns decorated C# methods into Microsoft.Extensions.AI-callable tools using Roslyn, with DI parameter binding and AOT support.
AppProjectReference Microsoft.Maui.Build.AppProjectReference MSBuild SDK extension that enables referencing MAUI app projects from test and tooling projects.
Linux GTK4 Microsoft.Maui.Platforms.Linux.Gtk4 + associated packages .NET MAUI platform backend for Linux using GTK4 — handler, Essentials, BlazorWebView, and project templates.
macOS AppKit Microsoft.Maui.Platforms.MacOS + associated packages .NET MAUI platform backend for macOS AppKit — handler, Essentials, BlazorWebView, and project templates.
WPF Microsoft.Maui.Platforms.Windows.WPF + associated packages .NET MAUI platform backend for WPF — handler, Essentials, and project templates.

Read the full file on GitHub · 345 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 · 345 lines · 5,419 tokens per session scan A 2445a9fc3cbc

Subscribe to this mod's changes

maui-labs AGENTS.md is an instructions file published in the GitHub repository dotnet/maui-labs (212 stars, last pushed 3d ago), licensed MIT. It adds 5,419 tokens to every session, about $0.0271 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.