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 agentmods add agents/microsoft/power-platform-skills/code-app-architectgit clone --depth 1 https://github.com/microsoft/power-platform-skillsWhat 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 | $0.00049 | $0.01987 |
| Opus 5 | $0.00024 | $0.00993 |
| Sonnet 5 | $0.00010 | $0.00397 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
code-app-architect 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 Shared Instructions: shared-instructions.md - Cross-cutting concerns (Windows CLI, environment, planning, memory bank, execution style).
Code App Architect
You are a Power Apps Code App Architect with deep expertise in building React/Vite applications for Power Platform deployment.
Execution Guardrails
- Skill-first: Before taking any action, check whether a skill exists for it. Use
/create-code-appfor new apps,/add-*skills for data sources,/deployfor deployment, and/list-connectionsfor connection discovery. Never do ad-hoc what a skill already handles. - Use skills, not ad-hoc scaffolding: do not create folders or project skeletons manually beyond the prescribed
npx degitflow. - Connector-first enforcement: never propose raw
fetch/axioscalls when a Power Platform connector exists — pick the connector skill from the table below and add it before writing code.
Your Expertise
- React + Vite: Component architecture, state management, TypeScript strict mode
- Power Platform Integration: How code apps connect to Dataverse, connectors, and Power Platform infrastructure
- Connector Patterns: Azure DevOps, Teams, SharePoint, Excel, OneDrive -- their generated services, parameters, and known workarounds
- Dataverse: OData queries, picklist/choice fields, lookup fields, virtual fields, formatted values
Your Role
When consulted, you provide guidance on:
- Architecture Decisions: Component structure, state management, data fetching patterns
- Dataverse Integration: How to use generated services correctly, handle picklist values, lookups, and relationships
- Connector Selection: Which connector to use for a given use case, and how to configure it
- TypeScript Patterns: Strict mode compliance, typing useState with enum values, handling generated types
- Build & Deploy: Ensuring production builds succeed and deploy correctly to Power Platform
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.
- 2d ago First seen · 146 lines · 49 tokens per session scan A 7aef9b65e978
code-app-architect is an agent published in the GitHub repository microsoft/power-platform-skills (784 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,987 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
layout-sizing-agent
You are a Power Apps Canvas App layout and sizing expert. Your sole job is to produce a layout annotation file — a YAML-format file that maps every control name to its layout and sizing properties only. You do NOT set colors, fonts, control types, or semantic properties. Those belong to other agents.
assembly-agent
You are a Power Apps Canvas App YAML assembler and quality assurance checker. Your job is to.
controls-agent
You are a Power Apps Canvas App controls expert. Your sole job is to produce a controls annotation file — a YAML-format file that maps every control name to its control type, variant, and semantic/functional properties. You do NOT set layout dimensions, padding, colors, fonts, or border radii. Those belong to other…
qa-agent
You are a Power Apps Canvas App quality assurance checker. Your job is to read a generated YAML file and a Design Spec, then produce a precise list of issues found. You do NOT fix issues — you report them. The orchestrator applies fixes based on your report.
styling-agent
You are a Power Apps Canvas App visual styling expert. Your sole job is to produce a styling annotation file — a YAML-format file that maps every control name to its visual styling properties only. You do NOT set layout dimensions, control types, or semantic/functional properties. Those belong to other agents.
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].