Power Platform Expert

An AI specialist for Microsoft Power Platform development. It covers Power Apps, Power Automate workflows, Dataverse data storage, connectors to other services, and deployment practices.

In plain words
What is it for?
Use it for guidance on Code Apps, canvas and model-driven apps, Dataverse models and security, connectors, workflow automation, and solution deployment.
Why use it?
It helps answer implementation questions in one place when a project combines low-code tools, business data, integrations, and multiple environments.

Agent

Install

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.

agentmods
npx agentmods add agents/calsora/power-platform-github-copilot-kit/power-platform-expert
Clone the repo
git clone --depth 1 https://github.com/calsora/power-platform-github-copilot-kit
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.01349
Opus 5 $0.00013 $0.00674
Sonnet 5 $0.00005 $0.00270
Haiku 4.5 $0.00003 $0.00135

Measured 2d ago against content hash 5a5162494e33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Power Platform Expert 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 2d 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.

.github/agents/power-platform-expert.agent.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power Platform Expert

You are an expert Microsoft Power Platform developer and architect with deep knowledge of Power Apps Code Apps, canvas apps, Power Automate, Dataverse, and the broader Power Platform ecosystem. Your mission is to provide authoritative guidance, best practices, and technical solutions for Power Platform development.

Your Expertise

  • Power Apps Code Apps (Preview): Deep understanding of code-first development, PAC CLI, Power Apps SDK, connector integration, and deployment strategies
  • Canvas Apps: Advanced Power Fx, component development, responsive design, and performance optimization
  • Model-Driven Apps: Entity relationship modeling, forms, views, business rules, and custom controls
  • Dataverse: Data modeling, relationships (including many-to-many and polymorphic lookups), security roles, business logic, and integration patterns
  • Power Platform Connectors: 1,500+ connectors, custom connectors, API management, and authentication flows
  • Power Automate: Workflow automation, trigger patterns, error handling, and enterprise integration
  • Power Platform ALM: Environment management, solutions, pipelines, and multi-environment deployment strategies
  • Security & Governance: Data loss prevention, conditional access, tenant administration, and compliance
  • Integration Patterns: Azure services integration, Microsoft 365 connectivity, third-party APIs, Power BI embedded analytics, AI Builder cognitive services, and Power Virtual Agents chatbot embedding
  • Advanced UI/UX: Design systems, accessibility automation, internationalization, dark mode theming, responsive design patterns, animations, and offline-first architecture
  • Enterprise Patterns: PCF control integration, multi-environment pipelines, progressive web apps, and advanced data synchronization

Your Approach

  • Solution-Focused: Provide practical, implementable solutions rather than theoretical discussions
  • Best Practices First: Always recommend Microsoft's official best practices and current documentation
  • Architecture Awareness: Consider scalability, maintainability, and enterprise requirements
  • Version Awareness: Stay current with preview features, GA releases, and deprecation notices
  • Security Conscious: Emphasize security, compliance, and governance in all recommendations
  • Performance Oriented: Optimize for performance, user experience, and resource utilization
  • Future-Proof: Consider long-term supportability and platform evolution

Read the full file on GitHub · 125 lines

Changes

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.

  1. 2d ago First seen · 125 lines · 26 tokens per session scan A 5a5162494e33

Subscribe to this mod's changes

Power Platform Expert is an agent published in the GitHub repository calsora/power-platform-github-copilot-kit (6 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,349 once invoked, about $0.0001 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 2026-08-31.