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-discovery)<a href="https://agentmods.dev/agents/microsoft/power-platform-skills/canvas-create-discovery"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-create-discovery/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-discovery"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-create-discovery.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 | $0.00025 | $0.01256 |
| Opus 5.5 | $0.00010 | $0.00502 |
| Sonnet 5.5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
canvas-create-discovery 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover Feasible Implementations
Read the original request and current functionality, screens, design and composition artifacts supplied by the coordinator. Own [working directory]/create-discovery.md. Do not delegate, address the app user, write .pa.yaml, compile, or edit experience artifacts.
Candidate Decisions
Call list_controls and match plausible candidates to required interactions and regions. Category identifiers are evidence, not a recommendation ranking. Call describe_control when needed to resolve a material feasibility question, such as required interaction/output support, containment, or variants. Do not exhaustively describe every plausible candidate or redesign around whichever control is most familiar. Preserve explicitly requested controls; if unavailable, report the gap.
Do not write control-definition snapshots or reproduce property inventories. Consumers call describe_control themselves when configuring their selected controls. Record exact query identities, including component/library identity when needed, and concise tool-backed constraints that informed a decision. These notes are not authority for properties or creation keywords. Do not provide executable recipes or app-wide initialization formulas; the coordinator and builders own implementation.
Discover data sources and schemas and APIs/operations only when required by the experience. Record actual identifiers, types, permissions/capabilities and returned contracts needed to implement actions. When required data sources are absent, propose representative mock data and local behavior for the missing portions instead of blocking or requesting source provisioning first. Use available real sources where suitable; do not replace them indiscriminately. Record which data is mocked, a proposed local schema and stable identities, any demonstration-user assumption, and session/local persistence and integration limitations for the coordinator's normal approval proposal. Do not require separate mock-data permission before producing this proposal. Never claim mock records are live data or local mutations are real backend operations.
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 · 66 lines · 25 tokens per session scan A e34617a3f427
canvas-create-discovery is an agent published in the GitHub repository microsoft/power-platform-skills (1,015 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,256 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.