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/generate-ppmplugin-manifestWrote 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/generate-ppmplugin-manifest)<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/generate-ppmplugin-manifest"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/generate-ppmplugin-manifest/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/generate-ppmplugin-manifest"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/generate-ppmplugin-manifest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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.
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 | $0.00194 | $0.04784 |
| Opus 5 | $0.00097 | $0.02392 |
| Sonnet 5 | $0.00039 | $0.00957 |
| Haiku 4.5 | $0.00019 | $0.00478 |
Grade A, and why
generate-ppmplugin-manifest 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate-ppmplugin-manifest
Stages the manifest.json that goes inside a .ppmplugin bundle — the small descriptor the wrap runtime and upload service read to identify the plugin and route calls into it. In the normal flow the committed ./manifest.json already exists (authored by /generate-native-extension next to the code it describes); this stage's job is to validate it, reconcile its entrypoints to the shipped target(s), and write the staged build copy ppmplugin/staging/manifest.json. It is the "get the strings right" gate: it runs instantly, needs no build tools, and catches common upload failures before any Android build. If the repo has no ./manifest.json (a hand-authored native module that skipped the scaffold), this stage authors it from source as a fallback — see Step 2.
Read shared/ppmplugin-format.md — it is the source of truth for the schema, the derivation table, and the validation rules this skill enforces.
Two manifests, one contract. ./manifest.json (repo root, committed) is the source-of-truth contract — it declares every platform the module supports. ppmplugin/staging/manifest.json (gitignored) is the build copy this stage produces — same contract, but entrypoints trimmed to the platform(s) actually being shipped. The build/assemble skills only ever read the staged copy; the committed root file is what the PCF and humans read.
What this skill does NOT do
- Does not compile anything — no Gradle, no DEX. That's
/build-android-binary. - Does not zip the bundle — that's
/assemble-ppmplugin. - Does not verify a declared platform's binary actually exists — it stages the intended
entrypoints;/assemble-ppmpluginreconciles them against the binaries actually staged and gates on any mismatch. - Does not rewrite the committed
./manifest.jsonon the normal path — it reads it. It only writes./manifest.jsonin the fallback case (no committed manifest existed). It never touchessrc/,ios/,android/, PRD, orpackage.jsonbeyond reading them.
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.
- 5d ago First seen · 161 lines · 194 tokens per session scan A 14f825aaaf21
generate-ppmplugin-manifest is a skill published in the GitHub repository microsoft/power-platform-skills (844 stars, last pushed yesterday), licensed MIT. It adds 194 tokens to every session and 4,784 once invoked, about $0.0010 per session on Opus 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
canvas-apps-ui-gen
Generates paste-ready Power Apps Canvas App YAML. Invoke when the user wants to replicate a UI mockup, improve an existing Canvas app screen, or build a new screen from a text description. Also invoke when the user asks to "improve", "redesign", or "generate YAML" for a Canvas app screen.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.