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.
npx skills add microsoft/power-platform-skills --skill test-sitegit 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/skills/microsoft/power-platform-skills/test-site)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/test-site"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/test-site/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-site"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/test-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Prompt Injection · line 89 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 185 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 10 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.
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 | $0.00046 | $0.10935 |
| Opus 5.5 | $0.00018 | $0.04374 |
| Sonnet 5.5 | $0.00009 | $0.02187 |
| Haiku 4.5 | $0.00005 | $0.01094 |
Grade A, and why
test-site scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const tokenResponse = await fetch(new URL('/_layout/tokenhtml', window.location.origin).href, { How it starts
The opening of the file, as written. The whole thing — 833 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin check: Run
node "${PLUGIN_ROOT}/scripts/check-version.js"— if it outputs a message, show it to the user before proceeding.
Test Power Pages Site
Test a deployed, activated Power Pages site at runtime. Navigate the site in a browser, crawl all discoverable links, verify pages load correctly, capture network traffic to test API requests, and generate a comprehensive test report.
Prerequisite: This skill expects a deployed and activated Power Pages site. Run
/deploy-siteand/activate-sitefirst if the site is not yet live.
Core Principles
- Non-destructive: This skill is read-only — it does not create, modify, or delete any files or data. It only observes the site via the browser.
- API-first testing: The primary goal beyond page loads is verifying that all
/_api/(Web API / OData) requests return successful responses. - Response-shape discovery: For
/_api/serverlogics/endpoints the test run must also capture and report the actual response body shape so frontend integrations can be written against the real response, not a guessed one. If frontend parsing or field access does not match the observed shape, report the mismatch and describe the parsing or field-access changes needed — this skill does not modify any code. - User-controlled authentication: Never attempt to log in automatically. Always ask the user to log in via the browser window when authentication is required.
- Bounded crawling: Cap page crawling at 25 pages to prevent infinite loops on sites with dynamic or paginated URLs.
Validation Test Categories
Every run produces a categorized test report (docs/alm/last-test-site.json — see Phase 6.7a). Stable category IDs and the source phase that produces each:
Category id |
Display Name | Source phase | What it covers |
|---|---|---|---|
site-load |
Site Load | Phase 2 | Homepage HTTP status, redirect handling, initial render. One card for the homepage; failures are critical. |
authentication |
Authentication | Phase 3 | Anonymous-to-Entra redirect, private-site gate detection, login flow integrity. Critical for private sites. |
page-crawl |
Page Crawl | Phase 4 | One card per page tested (up to 25). Each card carries the page URL, HTTP status, and any console errors. Severity scales with HTTP class (5xx → critical, 4xx on public → high). |
web-api |
Web API | Phase 5 | One card per /_api/ endpoint observed during the run. Captures status code, response shape, and remediation hints (table-permissions / site-settings / inner-error settings). |
auth-pages |
Authenticated Pages | Phase 5.6 | Pages that only became reachable after login. Skipped when the user opts out of authenticated testing. |
auth-api |
Authenticated API | Phase 5.6 | API endpoints that only became callable after login. Skipped when authenticated testing is skipped. |
console |
Console Health | Aggregated | Rolled-up count of console errors observed across all phases. Severity is medium by default. |
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.
- 10d ago Changed · +28 lines a727274b92bc
- 1mo ago First seen · 805 lines · 46 tokens per session scan A 23ea6c6a288f
test-site is a skill published in the GitHub repository microsoft/power-platform-skills (1,048 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 10,935 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
e2e-panther-playwright
Write end-to-end tests with Symfony Panther 2.4 for browser automation or Playwright for complex scenarios.
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.