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.
/plugin marketplace add microsoft/power-platform-skillsnpx agentmods add plugins/microsoft/power-platform-skills/power-apps-mobile-extensiongit 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/plugins/microsoft/power-platform-skills/power-apps-mobile-extension)<a href="https://agentmods.dev/plugins/microsoft/power-platform-skills/power-apps-mobile-extension"><img src="https://agentmods.dev/badge/plugins/microsoft/power-platform-skills/power-apps-mobile-extension.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
power-apps-mobile-extension 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 yesterday.
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.
What it actually says
{
"name": "power-apps-mobile-extension",
"version": "0.1.0",
"description": "Build third-party Power Apps Mobile (PAM) controls into a prebuilt .ppmplugin binary (Android DEX + flat iOS .framework + manifest.json) for the wrap runtime. Public tooling only; recommended build entry point /generate-ppmplugin.",
"author": {
"name": "Microsoft",
"url": "https://www.microsoft.com"
},
"homepage": "https://github.com/microsoft/power-platform-skills/",
"repository": "https://github.com/microsoft/power-platform-skills/",
"license": "MIT",
"keywords": [
"power-apps",
"power-apps-mobile-extension",
"pam",
"control",
"ppmplugin",
"wrap",
"pcf",
"ios",
"android",
"microsoft"
]
}
What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 2,060 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill test-native-extension A 211 tokens
- Skill audit-ppmplugin A 112 tokens
- Skill debug-extension A 108 tokens
- Skill build-android-binary A 150 tokens
- Skill generate-ppmplugin-manifest A 194 tokens
- Skill generate-ppmplugin A 107 tokens
- Skill assemble-ppmplugin A 199 tokens
- Skill generate-pcf-companion C 206 tokens
- Skill generate-native-extension C 198 tokens
- Skill design-native-extension-feature C 171 tokens
- Skill publish-pcf-companion C 204 tokens
- Skill build-ios-binary C 200 tokens
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.
- yesterday First seen · 25 lines scan A 3493e411b75c
power-apps-mobile-extension is a plugin published in the GitHub repository microsoft/power-platform-skills (814 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
canvas-apps-tools
AI skills for Power Apps Canvas Apps - generate, modify, and integrate.
maestro-mobile-validator
iOS and Android mobile app validation via Maestro flows with simulator management and CI patterns.
hotwire-codex-skills
Unofficial skillset inspired by The Rails and Hotwire Codex (by Ayush Newatia), published with the author's permission. Skills and runnable checkers for Rails + Hotwire apps that ship to web/PWA, iOS, and Android. Unique vs other Rails plugins (which are LLM coders/reviewers): every skill ships a deterministic…
opinionated-apple-development
Apple platform development: Swift language (Swift 6+ concurrency, protocol-oriented programming) and macOS platform patterns (SwiftUI/AppKit, sandboxing).
swiftui
SwiftUI patterns and critique for iOS, macOS, and visionOS apps.
sprint
Orchestrate staged milestones with native subagents on Claude Code or Oh My Pi, plus codex or mimo executors on Claude Code.