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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/power-platform-skillsnpx agentmods add skills/microsoft/power-platform-skills/test-native-extensionWrote 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/power-platform-skills/test-native-extension)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/test-native-extension"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/test-native-extension/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/skills/microsoft/power-platform-skills/test-native-extension"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/test-native-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 136 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 615 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 724 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00211 | $0.16517 |
| Opus 5.5 | $0.00084 | $0.06607 |
| Sonnet 5.5 | $0.00042 | $0.03303 |
| Haiku 4.5 | $0.00021 | $0.01652 |
Grade A, and why
test-native-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 1mo 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 — 729 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/test-native-extension
Runs the 4-layer validation ladder for a third-party control repo — the one that ships as a .ppmplugin binary bundle, not as a TypeScript extension. Layers 1–4 are automated; Layer 5 is interactive (requires a real device or simulator and the Companion PCF deployed to a test environment).
| Layer | What | Mode | Speed | Requires |
|---|---|---|---|---|
| 0 | Holistic contract consistency (native ↔ manifest ↔ PCF cross-check) | Automated, warn-only | seconds | at least a native module on disk |
| 1 | Native-source structure asserts (Android getName() ↔ iOS +moduleName ↔ manifest) |
Automated, grep/parse | seconds | android/ and/or ios/ |
| 2 | Manifest validation (ppmplugin-format §4 rules) |
Automated | seconds (skipped only if no manifest on disk) | ./manifest.json (committed; else staged copy) |
| 3 | Native-source contract asserts (request/response/error grep cross-check) | Automated | seconds | native module(s) |
| 4 | PCF compile (npm run build in pcf/<Pascal>PCF/) |
Automated | seconds (after first install) | pcf/<Pascal>PCF/ must exist (skipped otherwise) |
| 5 | Manual device / simulator end-to-end | Recipe-only — skill prints, user runs on own time | 5–10m, off-skill | pcf/ must exist + PCF deployed |
Run order is layer-by-layer for Layers 1–4. Stop on the first failure in the automated layers. Layer 5 is not gated by the skill — it prints the device recipe and exits; the user runs it on their own time and updates .extension-state.md manually.
What this skill does NOT validate: native code compilation into a loadable DEX / framework. That's the job of
/build-android-binaryand/build-ios-binary— they run the real Gradle / xcodebuild toolchain against the pinned RN version and surface the real compiler error. Standalonepod lib lintand./gradlew assembleDebugfrom this skill would give false-confidence (they resolve dependencies from public CDN/maven, not against the wrap host's pinned versions). This skill is the structural pre-flight that runs in seconds with no toolchain — it asserts the native source is shaped correctly (right base class, right symbols, the AndroidgetName()↔ iOS+moduleName↔ manifest agreement) so the build skills don't fail late on a fixable-in-seconds mistake. There is no TypeScript /INativeExtensionlayer in this track to type-check — a native-only.ppmpluginbundle dispatches straight toNativeModules.<nativeModule>.<method>(ppmplugin-format §2— Runtime dispatch contract).
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.
- 1mo ago First seen · 729 lines · 211 tokens per session scan A 356aa2019447
test-native-extension is a skill published in the GitHub repository microsoft/power-platform-skills (1,025 stars, last pushed today), licensed MIT. It adds 211 tokens to every session and 16,517 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
e2e-scaffold
One-shot XCUITest scaffolding for iOS and macOS SwiftUI apps: ranked TIER-1/2/3 stubs, accessibility-identifier suggestions, xcresult runner. Manual only — modifies project files.
e2e-route
Pure dispatcher for Swift E2E tests. Reads platform, intent and executor pin, names the executor and the next action, then hands off.
ios-testing-patterns
XCTest and XCUITest execution workflows and flaky test detection patterns.
android-emulator-mask-testing
Specialization of android-emulator-harness for CAMERA / segmentation testing: get a real PERSON in front of the emulator camera so MediaPipe / ML Kit selfie segmentation produces an actual mask, then verify background-replacement / blur / shader effects and tune mask threshold by vision. Use when the task is "test the…
ios-device-qa
Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.
xcode-simulator-testing
Use when asked to run /xcode-simulator-testing with a scheme name or current to build and launch an iOS app in a simulator. Not for project regeneration: use ios-build-fix.