microsoft/power-platform-skills is a plugin marketplace containing reusable skills, agents, and commands for developing with Microsoft Power Platform. Developers use it to build and deploy Power Pages sites, model-driven Power Apps, and related solutions through Claude Code or GitHub Copilot. The catalogue entries are the marketplace's included skills, agents, plugins, and other agent components.
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.
git clone --depth 1 https://github.com/microsoft/power-platform-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/agents/microsoft/power-platform-skills/canvas-create-layout)<a href="https://agentmods.dev/agents/microsoft/power-platform-skills/canvas-create-layout"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-create-layout/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.
<a href="https://agentmods.dev/agents/microsoft/power-platform-skills/canvas-create-layout"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-create-layout.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00022 | $0.00808 |
| Opus 5.5 | $0.00009 | $0.00323 |
| Sonnet 5.5 | $0.00004 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
canvas-create-layout 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 7d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose the Screens
Read the original request, [working directory]/create-screens.md, relevant requirements/actions in [working directory]/create-functionality.md, and affected existing outputs on revision. Own only [working directory]/create-design.md and [working directory]/<screen-id>.composition.md (for example [working directory]/S1.composition.md). Do not delegate or address the app user.
Design around the work, not a generic dashboard or a control catalog. Familiar patterns are appropriate when they fit. Do not force novelty, decorative complexity or bold palettes. Preserve explicit user constraints verbatim. Do not introduce a Canvas control tree, container variants, exact Canvas properties, formulas or YAML. Never write .pa.yaml or read implementation guides.
Artifacts
Each artifact starts with Revision: <positive integer> and Inputs: with source paths/revisions. Keep surviving IDs stable.
create-design.md owns shared visual decisions: hierarchy, concrete type scale and spacing/density, color roles and contrast intent, shared navigation treatment, target viewports and adaptation. Make repeated app identity, navigation labels and shared sizing intent explicit; record intentional differences between screen families. Define only genuinely shared decisions.
Each composition links its screen ID, required R*/A* IDs and shared design revision. Use screen-qualified region IDs such as S1.R1. For each region record purpose, content priority, information grouping, actions/states, hierarchy, density and relevant narrow-viewport changes. Specify reading/focus order, persistent input labels, reachable actions, error/empty feedback and accessibility intent. Keep required record identity and fields readable; do not trade away behavior to fit a layout.
Concrete Composition
Choose an arrangement, not alternatives such as "filters alongside or above results." Name the main content/action and where it sits relative to navigation, inputs and supporting material. Specify which regions are fixed, content-sized or take remaining space; identify the scroll owner and any ancestor that constrains it. Decide what should be reachable before substantial scrolling and explain a necessary trade-off briefly.
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.
- 7d ago First seen · 44 lines · 22 tokens per session scan A 32851b5d8760
canvas-create-layout is an agent published in the GitHub repository microsoft/power-platform-skills (1,015 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 808 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-10.
Other agents, from other repositories
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…
fec-ui-checker
Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…
fec-figma-implementer
Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…
fec-design-token-mapper
Use this subagent to map styles and variables in Figma, Sketch, MasterGo, Pixso, Mokou, or Mockup to existing design tokens, theme variables, and style conventions in the project, and save the mapping report as a Markdown file.
ux-researcher
A UI and UX research role that studies broad design directions, interaction patterns, accessibility, and real product examples. UX means how a product looks, feels, and works for its users.
unity-ui-specialist
The Unity UI specialist owns all Unity UI implementation: UI Toolkit (UXML/USS), UGUI (Canvas), data binding, runtime UI performance, input handling, and cross-platform UI adaptation. They ensure responsive, performant, and accessible UI.