winui-code-review

A local debugging and regression-testing toolkit for TypeScript AI agents. It records run evidence and lets developers check whether an agent followed expected steps.

In plain words
What is it for?
Capturing local run traces, checking expected agent trajectories, creating shareable evidence bundles, and inspecting runs through MCP, a tool connection for AI assistants.
Why use it?
It makes agent behavior inspectable and repeatable instead of relying only on final answers or incomplete logs.

Skill for Claude CodeCodex

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 skills/microsoft/win-dev-skills/winui-code-review
Any agent
npx skills add microsoft/win-dev-skills --skill winui-code-review
Clone the repo
git clone --depth 1 https://github.com/microsoft/win-dev-skills

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,508 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00049 $0.01508
Opus 5 $0.00024 $0.00754
Sonnet 5 $0.00010 $0.00302
Haiku 4.5 $0.00005 $0.00151

Measured 2d ago against content hash 9fba900155a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

winui-code-review 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 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.

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.

plugins/winui/agent-plugin/skills/winui-code-review/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Run a code review after the app builds and before committing. This catches quality issues that aren't build errors and aren't visible in UI tests — patterns that compile and run but are wrong, fragile, or slow.

How to Review

Read through the project's XAML and C# files and check each section below. The Microsoft.WindowsAppSDK.Analyzers Roslyn analyzer ships with the winui-dev-workflow skill and is injected when BuildAndRun.ps1 calls project-mode winapp run. The wrapper supplies a temporary file through the environment-backed MSBuild CustomAfterDirectoryBuildProps hook, preserving SDK composition and each project's normal Directory.Build.props discovery (including referenced projects), then restores the environment and removes the temporary file. Plain winapp run, dotnet build, and Visual Studio do not load the analyzer automatically; to enable it outside the wrapper, add the <Analyzer Include="..." /> and <Import Project="..." /> entries to the project's own Directory.Build.props (or wait for the planned NuGet package).

The analyzer catches a curated set of WinUI 3 / Windows App SDK issues with categorized 4-digit IDs:

  • WUI0xxx — UWP → WinUI 3 API compatibility (UwpXamlNamespace, Window.Current, CoreDispatcher, GetForCurrentView)
  • WUI1xxx — Migration-table data-driven hints (UWP API has WinAppSDK equivalent, no equivalent, feature-area hint)
  • WUI2xxx — Runtime / layout / XAML pitfalls (raw TabView content, nested x:Bind without fallback, x:Bind without Mode, null Converter, missing AutomationId, attached-property syntax)
  • WUI3xxx — MVVM patterns (old [ObservableProperty] field syntax)
  • WUI4xxx — Interop (WebView2 not initialized, removed ONNX Runtime GenAI APIs WUI4101-WUI4103)

Every diagnostic ships at Warning severity (no rule is Error) and includes a helpLinkUri. Suppress noise with #pragma warning disable WUIxxxx or <NoWarn> as usual — the analyzer's SuppressionTests verify that pragma suppression round-trips correctly.

Read the full file on GitHub · 89 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 89 lines · 49 tokens per session scan A 9fba900155a3

Subscribe to this mod's changes

winui-code-review is a skill published in the GitHub repository microsoft/win-dev-skills (406 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 1,508 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

technical-design-doc-creator

Creates comprehensive Technical Design Documents (TDD) with mandatory and optional sections through interactive discovery. Use when user asks to "write a design doc", "create a TDD", "technical spec", "architecture document", "RFC", "design proposal", or needs to document a technical decision before implementation. Do…

tech-leads-club/agent-skills · 86 tokens

spec-driven-eval

Scores how completely an implementation fulfills a PRD/spec, case by case, and produces a single comparable final grade. Invoke only when explicitly named (e.g. run spec-driven-eval); do not auto-trigger. Use when benchmarking spec-driven implementations, grading acceptance criteria, evaluating whether a feature was…

tech-leads-club/agent-skills · 123 tokens

content-to-pipeline

When the user wants to turn content into revenue, build a content-led GTM motion, reverse engineer distribution, or repurpose content across platforms. Also use when the user mentions 'content marketing,' 'content-led growth,' 'content to pipeline,' 'distribution,' 'content repurposing,' 'content strategy,' 'thought…

tech-leads-club/agent-skills · 111 tokens

component-common-domain-detection

Finds duplicate business logic spread across multiple components and suggests consolidation. Use when asking "where is this logic duplicated?", "find common code between services", "what can be consolidated?", "detect shared domain logic", or analyzing component overlap before refactoring. Do NOT use for code-level…

tech-leads-club/agent-skills · 77 tokens

component-flattening-analysis

Detects misplaced classes and fixes component hierarchy problems — finds code that should belong inside a component but sits at the root level. Use when asking "clean up component structure", "find orphaned classes", "fix module hierarchy", "flatten nested components", or analyzing why namespaces have misplaced code.…

tech-leads-club/agent-skills · 86 tokens

decomposition-planning-roadmap

Creates step-by-step decomposition plans and migration roadmaps for breaking apart monolithic applications. Use when asking "what order should I extract services?", "plan my migration", "create a decomposition roadmap", "prioritize what to split", "monolith to microservices strategy", or tracking decomposition…

tech-leads-club/agent-skills · 87 tokens