Microsoft Managed Apps is a project for building custom web applications with React, TypeScript, and Vite, and it provides Microsoft's official templates and development tooling. Developers use its SDK, CLI, and Vite plugin to create and manage these applications. Its catalogue add-ons help AI coding agents build Microsoft Managed Apps.
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 skills add microsoft/managed-apps --skill devgit clone --depth 1 https://github.com/microsoft/managed-appsWrote 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/managed-apps/dev)<a href="https://agentmods.dev/skills/microsoft/managed-apps/dev"><img src="https://agentmods.dev/badge/skills/microsoft/managed-apps/dev/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/managed-apps/dev"><img src="https://agentmods.dev/badge/skills/microsoft/managed-apps/dev.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 | $0.00031 | $0.01309 |
| Opus 5.5 | $0.00012 | $0.00524 |
| Sonnet 5.5 | $0.00006 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
dev 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 — 96 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.
Local Dev
Starts ms app dev in the project's working directory. The CLI runs two servers — a dev script (Vite or equivalent, default port 8080) and a config server — and prints the App Player URL the user opens in their browser.
This skill does NOT deploy to the cloud. For that, use /deploy.
Workflow
- Memory Bank → 2. Verify Project + Env → 3. Start Dev Server → 4. Hand Off URL
Step 1: Check Memory Bank
Read memory-bank.md from the project root (the project the user has cd'd into, or the path captured from a prior skill invocation) for context — the app slug/GUID and which environment this project targets — so you can confirm you're starting the right app.
ms app dev does not need environmentId or appId passed to it: it runs in the project working directory and reads ms.config.json itself. The memory bank is only for orienting yourself; if it's missing, that's fine — skip straight to Step 2.
Step 2: Verify Project + Env
test -f ms.config.json || { echo "Not in a Microsoft App workspace (no ms.config.json)."; exit 1; }
Probe the CLI binary and confirm auth:
BIN=ms
$BIN auth status
If auth status reports the wrong UPN or is signed out, prompt the user to fix it before continuing (ms auth login). Don't try to repair auth silently — wrong-account dev sessions waste time downstream.
Step 3: Start the Dev Server
Default invocation:
$BIN app dev
Flags worth surfacing (only when the user mentions a need):
| Flag | When to use |
|---|---|
--port <n> (-p) |
Port 8080 is busy. Pick another (e.g., --port 8081). |
--local-app-url <url> (-l) |
The user's Vite/dev script is on a non-default URL (default http://localhost:3000). |
--config-only (-C) |
Only run the config server. Useful when the user runs npm run dev separately. |
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 Changed · -2 lines ccba756992e4
- 2mo ago First seen · 98 lines · 31 tokens per session scan A 5ab92d8ff99f
dev is a skill published in the GitHub repository microsoft/managed-apps (36 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 1,309 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 2026-08-31.
dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| devmicrosoft/managed-apps | Skill | 36 | 3d ago | MIT | A | 31 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |