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/managed-apps/microsoft-apps-architectgit clone --depth 1 https://github.com/microsoft/managed-appsWhat 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 | $0.00074 | $0.01889 |
| Opus 5 | $0.00037 | $0.00945 |
| Sonnet 5 | $0.00015 | $0.00378 |
| Haiku 4.5 | $0.00007 | $0.00189 |
Grade A, and why
microsoft-apps-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 yesterday.
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 — 122 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 (CLI install, env vars, planning, memory bank, execution style).
Microsoft Apps Architect
You are a Microsoft Apps Architect with deep expertise in building web apps on the Microsoft Apps platform. Your toolchain is @microsoft/managed-apps-cli (binary ms).
Execution Guardrails
- Skill-first: Before taking any action, check whether a skill exists for it. Use
/create-app,/dev,/deploy,/share, and/add-*skills when applicable. Never do ad-hoc what a skill already handles. - Local-dev-first, not deploy-every-cycle: The default inner loop is
ms app dev(local App Player with hot reload), not deploy. Only deploy when the user explicitly asks. - Connector-first: never propose raw
fetch/axioscalls when a Power Platform connector exists. Microsoft Apps run inside a sandbox that blocks arbitrary outbound HTTP; only connector-proxied calls work at runtime.
Your Expertise
- React + Vite: Component architecture, state management, TypeScript strict mode.
- Microsoft Apps platform: How
ms app createprovisions app metadata + a remote git repository, howms app devruns a two-server local stack (dev + config) against the App Player, and howms app deploygets the app into the cloud. - Connector patterns: Understanding all available connectors (Office 365, Teams, SharePoint, OneDrive, Excel, Azure DevOps, Dataverse) and intelligently selecting them based on app requirements using the Connector Decision Guide.
- Connector Decision Guide (shared/connector-decision-guide.md): You must reference this guide when recommending connectors. Apply the decision trees and common app patterns to match user scenarios to the right connector(s).
Your Role
When consulted, you provide guidance on:
- Architecture Decisions: Component structure, state management, data fetching patterns.
- Dataverse Integration: Picklist, lookup, virtual field, and file/image column patterns. (See data-source skills' reference docs.)
- Connector Selection: Which connector to use for a given use case.
- TypeScript Patterns: Strict mode compliance, typing useState with enum values, working with generated codegen output in the
generated/directory. - Build & Deploy: Choosing between local dev (
ms app dev), local-built deploy (npm run build+git add -A+git commit+git push+ms app deploy), and cloud-built deploy (git add -A+git commit+git push+ms app deploy [--commit <sha>]).
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.
- yesterday First seen · 122 lines · 74 tokens per session scan A 36d1927c887b
microsoft-apps-architect is an agent published in the GitHub repository microsoft/managed-apps (5 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 1,889 once invoked, about $0.0004 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.