maui sandbox.instructions.md

A set of instructions for testing the .NET MAUI Sandbox app, a sample app used to check app behavior on devices and reproduce reported problems.

In plain words
What is it for?
Use it to test pull requests, reproduce issues, deploy the Sandbox app to iOS or Android, and confirm behavior through device logs.
Why use it?
It provides a required process for validating results instead of treating a connected device or an HTTP response as proof that a test passed.

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

Made for: GitHub Copilot.

Per session 7,693 This file is loaded in full into every session.
When invoked 7,693 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.07693 $0.07693
Opus 5 $0.03846 $0.03846
Sonnet 5 $0.01539 $0.01539
Haiku 4.5 $0.00769 $0.00769

Measured 2d ago against content hash d4726bba73de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

maui sandbox.instructions.md scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf CustomAgentLogsTmp/Sandbox/
.github/instructions/sandbox.instructions.md · 820 lines

How it starts

The opening of the file, as written. The whole thing — 820 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandbox Testing Guide

Comprehensive guide for working with the .NET MAUI Sandbox app for manual testing, PR validation, issue reproduction, and experimentation with MAUI features.

When This Applies

This guide applies when you:

  • Work with files in src/Controls/samples/Controls.Sample.Sandbox/
  • User asks to "test this PR" or "validate PR #XXXXX" in Sandbox
  • User asks to "reproduce issue #XXXXX" in Sandbox
  • User wants to deploy to iOS/Android for manual testing
  • User mentions Sandbox app by name in testing context

🚨 CRITICAL VALIDATION RULES - READ FIRST

YOU MUST FOLLOW THESE RULES WHEN RUNNING SANDBOX TESTS:

What You NEVER Do (Absolute Rules)

  • NEVER assume test completion without validation
  • NEVER claim success based on HTTP 200 responses alone (element found ≠ test completed)
  • NEVER skip the mandatory validation checklist
  • NEVER proceed without verifying device logs show expected behavior
  • NEVER assume Appium connection means test finished
  • NEVER claim button was tapped without checking device logs
  • NEVER switch branches (e.g., git checkout main) during reproduction - stay on current branch

What You ALWAYS Do (Mandatory Steps)

  • ALWAYS save full output to file for analysis
  • ALWAYS check for errors/exceptions FIRST before claiming success
  • ALWAYS verify "Test completed" marker appears in output
  • ALWAYS verify expected test actions in logs (Tapping, Screenshot, etc.)
  • ALWAYS check device logs for Console.WriteLine markers (e.g., "SANDBOX: ...")
  • ALWAYS verify artifacts exist (screenshots, if test captures them)

Rule 1: NEVER ASSUME TEST COMPLETION

  • DO NOT assume the test completed successfully just because Appium connected
  • DO NOT assume success based on HTTP 200 responses (element found ≠ test completed)
  • DO verify test completion by checking for completion markers in output
  • DO search for "Test completed", "═══════", or final summary messages

Read the full file on GitHub · 820 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. 2d ago First seen · 820 lines · 7,693 tokens per session scan C d4726bba73de

Subscribe to this mod's changes

maui sandbox.instructions.md is an instructions file published in the GitHub repository dotnet/maui (23,317 stars, last pushed 2d ago), licensed MIT. It adds 7,693 tokens to every session, about $0.0385 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

azure-sdk-for-net AGENTS.md

AGENTS.md instructions for Azure/azure-sdk-for-net, covering azure sdk for .net - ai agent guidelines, repository overview, purpose and scope, repository structure and agent interaction guidelines.

Azure/azure-sdk-for-net · 2,836 tokens

azure-sdk-for-net copilot-instructions.md

Copilot instructions for Azure/azure-sdk-for-net, covering project overview, prerequisites, folder structure, azure generator and azure management generator.

Azure/azure-sdk-for-net · 738 tokens

BlazorBindings.Maui AGENTS.md

Instructions for Dreamescaper/BlazorBindings.Maui, covering mobile guidelines, platform, razor and component conventions and blazor bindings generation.

Dreamescaper/BlazorBindings.Maui · 688 tokens

Enclave-Terminal-Breach CLAUDE.md

Instructions for Gwergilius/Enclave-Terminal-Breach, covering enclave terminal breach – claude code configuration, rules and quick reference.

Gwergilius/Enclave-Terminal-Breach · 359 tokens

vscode source-code-organization.instructions.md

VS Code source code organization — layers, target environments, dependency injection, and folder structure conventions. Reference when adding new modules, services, or contributions.

microsoft/vscode · 662 tokens

vscode design-philosophy.instructions.md

VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.

microsoft/vscode · 577 tokens