maui: Skill for Claude Code

.github/skills/azdo-build-investigator/SKILL.md

azdo-build-investigator is a skill for Claude Code, Codex from dotnet/maui. It costs 115 tokens per session (2,030 once invoked), scanned A, original, MIT.

A guide for investigating .NET MAUI continuous-integration failures, where automated builds and tests check whether code is ready to merge.

In plain words
What is it for?
Use it to investigate failing pull-request or nightly builds, inspect Helix test failures, analyze build errors, and assess merge readiness.
Why use it?
It helps connect a red check or failed test to the relevant build logs, device-test results, and binary logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is dotnet/maui's own configuration. It tells Claude Code and Codex how to work on maui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything maui configures →

About the project

.NET MAUI is a C# and XAML framework for building native mobile and desktop applications from one shared codebase. Developers use it to create apps for Android, iOS, iPadOS, macOS, and Windows. The catalogue entries provide skills, instructions, and agents for working with .NET MAUI.

dotnet/maui · 23,323 stars · on GitHub · dot.net

Reuse

Borrowing it

Nothing to install: this file belongs to dotnet/maui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dotnet/maui/main/.github/skills/azdo-build-investigator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dotnet/maui

Made for: Claude Code, Codex.

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.

agentmods badge for azdo-build-investigator

README.md
[![agentmods](https://agentmods.dev/badge/skills/dotnet/maui/azdo-build-investigator/github.svg)](https://agentmods.dev/skills/dotnet/maui/azdo-build-investigator)
Your own site
<a href="https://agentmods.dev/skills/dotnet/maui/azdo-build-investigator"><img src="https://agentmods.dev/badge/skills/dotnet/maui/azdo-build-investigator/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.

agentmods 80×15 button for azdo-build-investigator

Your own site · 80×15
<a href="https://agentmods.dev/skills/dotnet/maui/azdo-build-investigator"><img src="https://agentmods.dev/badge/skills/dotnet/maui/azdo-build-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk warn 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00115 $0.02030
Opus 5 $0.00057 $0.01015
Sonnet 5 $0.00023 $0.00406
Haiku 4.5 $0.00012 $0.00203

Measured 11d ago against content hash 702f21472951, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

azdo-build-investigator 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 11d 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/skills/azdo-build-investigator/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dotnet/maui CI Investigation Context

This skill provides MAUI-specific context for interactive CI investigation — answering "why is CI red?" and "is this PR ready to merge?". Use it together with the ci-analysis skill (loaded from the dotnet-dnceng@dotnet-arcade-skills plugin via .github/copilot/settings.json).

First: invoke the ci-analysis skill — it handles the core investigation workflow using Get-CIStatus.ps1 and gh CLI (with MCP tools as optional enhancements if available). This skill provides MAUI-specific corrections and context on top of that.

For the automated path (a maintainer comments /review tests on a PR), the review-test-failures skill does the same classification deterministically and posts a merge-readiness comment. Both skills reason from the same shared facts below.

MAUI CI facts (canonical)

All MAUI-specific facts live in .github/docs/maui-ci-facts.md — read it. It covers:

  • Pipeline names + definition IDs (maui-pr 302, maui-pr-devicetests 314, maui-pr-uitests 313), org/project, and investigation priority order.
  • AzDO data sources (anonymous public build/timeline/log REST APIs; _apis/test is optional enrichment).
  • XHarness exit-0 blind spot and the Helix aggregated endpoint for hidden device-test failures.
  • Container artifact binlogs (Bearer token + File Container API; mcp-binlog-tool).
  • Test count deduplication (group by test name + OS platform).
  • Baseline comparison (is the failure already red on the base branch?).
  • Visual baseline and platform mismatch guidance.
  • Gradle / Maven / CFSClean signatures and the ./eng/ingest-maven-deps.sh fix.
  • Common failure patterns table.
  • Merge-readiness criteria — the shared definition of Ready to merge / Not ready / Needs human investigation / Insufficient data / No failures found.

Do not restate those facts from memory; change them in the canonical doc only.

Script location

Read the full file on GitHub · 98 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. 11d ago First seen · 98 lines · 115 tokens per session scan A 702f21472951

Subscribe to this mod's changes

azdo-build-investigator is a skill published in the GitHub repository dotnet/maui (23,323 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 2,030 once invoked, about $0.0006 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.