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.
npx agentmods add skills/microsoft/win-dev-skills/winui-designnpx skills add microsoft/win-dev-skills --skill winui-designgit clone --depth 1 https://github.com/microsoft/win-dev-skillsWrote 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/skills/microsoft/win-dev-skills/winui-design)<a href="https://agentmods.dev/skills/microsoft/win-dev-skills/winui-design"><img src="https://agentmods.dev/badge/skills/microsoft/win-dev-skills/winui-design.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.02712 |
| Opus 5 | $0.00060 | $0.01356 |
| Sonnet 5 | $0.00024 | $0.00542 |
| Haiku 4.5 | $0.00012 | $0.00271 |
Grade A, and why
winui-design 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 3d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search samples before writing XAML
WinApp CLI 0.6+ provides grounded control and sample discovery through winapp find-ui. Front-load lookups, then code:
winapp find-ui "<focused feature>" # compact matches + scenario IDs
winapp find-ui --id <scenario-id> # full XAML/C# + prerequisite notes
winapp find-ui --id <id-1> --id <id-2> --json # batch, structured output
winapp find-ui --list # browse all default-source scenarios
winapp find-ui "<feature>" --refresh # force a corpus refresh
Default search covers the WinUI Gallery, Windows Community Toolkit, and curated core patterns. Reactor's C#-only/MVU samples are opt-in with --source reactor; use them only for Reactor projects. The Gallery/Toolkit/Reactor corpus is fetched and cached by WinApp CLI, while core patterns work offline.
App-shape anchors
Pick the closest shipping app silhouette before laying out a page:
| App type | Anchor controls | Reference apps |
|---|---|---|
| Settings / config tool | NavigationView Left + SettingsCard / SettingsExpander |
Windows Settings, Slack |
| Document / session editor | TabView + full-bleed content, light chrome |
Windows Terminal, VS Code, Notepad |
| Hierarchical browser | TreeView + ListView + BreadcrumbBar |
File Explorer, Outlook |
| Developer tool / dashboard | NavigationView + card layout |
Dev Home, GitHub Desktop |
| Single-purpose utility | Mode switcher + compact grid | Calculator, Snipping Tool |
| Media / canvas / hero | Grid with hero surface, floating commands, no NavigationView |
Photos, Spotify, Clipchamp |
Reach-for-this control map
Before writing XAML, map the requirement to a platform control. These mappings exist to short-circuit cross-framework instincts (WPF DataGrid, web <select>, HTML <input type=date>):
- Navigation: 2–7 sections →
NavigationView; document/session tabs →TabView; breadcrumb trail →BreadcrumbBar; 2–3 modes →SelectorBar. - Data display: Vertical list →
ListView; tiles/grid →GridVieworItemsRepeater+UniformGridLayout; hierarchy →TreeView; tabular →ListViewwith aGrid-basedItemTemplateand a headerGridabove (WinUI has noDataGrid; don't default toCommunityToolkit.WinUI.Controls.DataGrid— its columns can't usex:Bind); master-detail →ListView+ detailGrid. - Input: Text →
TextBox; number →NumberBox; search →AutoSuggestBox; date →CalendarDatePicker; boolean →ToggleSwitch; pick one from 2–3 →RadioButtons; pick one from 4+ →ComboBox. - Feedback: Blocking decision →
ContentDialog; contextual action →Flyout/MenuFlyout; onboarding / hint →TeachingTip; inline status / async progress →InfoBar; system notification →AppNotification.
What ships with it
3 files 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.
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.
- 3d ago First seen · 176 lines · 119 tokens per session scan A dea0912e3e58
winui-design is a skill published in the GitHub repository microsoft/win-dev-skills (406 stars, last pushed 7d ago), licensed MIT. It adds 119 tokens to every session and 2,712 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.
Other skills, from other repositories
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.
new
Create a new project to start development quickly.
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.