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-builder)<a href="https://agentmods.dev/agents/microsoft/power-platform-skills/canvas-create-builder"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-create-builder/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-builder"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-create-builder.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 | $0.00599 |
| Opus 5.5 | $0.00009 | $0.00240 |
| Sonnet 5.5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
canvas-create-builder 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.
Implement One Screen
Read the original request, assigned composition and relevant requirement/action IDs, [working directory]/create-design.md, [working directory]/create-bindings.md, and the relevant current discovery decisions. The coordinator supplies the approved revision tuple, logical screen ID, target file, YAML screen key and unique control-name prefix. Confirm they match before writing. Do not create another implementation plan.
Own exactly the assigned screen YAML file. Do not edit App.pa.yaml, _EditorState.pa.yaml, bindings, experience artifacts or another screen. Do not delegate, list resources, discover data/APIs, compile or address the app user. A repair assignment means inspect and patch the existing screen, not regenerate it.
Direct Control Descriptions
Choose controls from the feasible candidates and apply Control authority in ${PLUGIN_ROOT}/references/CreateBuilderCore.md. Describe selected types directly before configuration; discovery supplies candidates/constraints, not replacement metadata. Route missing contracts or disproved feasibility back to discovery.
Implementation
Read the core, ${PLUGIN_ROOT}/references/CreateConformance.md and applicable CREATE topic modules from the core's ownership map. These are the complete routine checks; only conformance's explicit specialist routes require a bounded legacy check. Reuse complete references/descriptions in this context. None authorizes an unapproved experience change.
Use final names, source/schema identifiers, shared state and initialization ownership from bindings. Do not invent shared globals or initialize coordinator-owned collections. Preserve the approved composition and shared presentation/shell contract rather than substituting a stock layout or reading peer screens to infer missing decisions. Shared gaps go to the coordinator.
Apply ${PLUGIN_ROOT}/references/CreateGalleryLayout.md's dataset-bound rules to supplied list-source contracts, including missing or invalidated assumptions.
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 38948cb1b5db
canvas-create-builder 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 599 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.