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 skills/microsoft/managed-apps/playnpx skills add microsoft/managed-apps --skill playgit 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 | $0.00044 | $0.01165 |
| Opus 5 | $0.00022 | $0.00583 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
play 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 — 123 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.
Play
Opens a Microsoft App in the browser by fetching its cloud play URL and launching it. No local dev server required.
| Mode | Command | What opens |
|---|---|---|
live (default) |
ms app play |
The most recently deployed version. A snapshot — does not update until ms app deploy is run again. |
preview (main) |
ms app play --mode preview |
Built from the main branch on demand — always reflects the latest pushed code, even without a deploy. |
preview (commit) |
ms app play --mode preview --commit <sha> |
App as of a specific commit SHA — useful for code review or regression testing. |
Live vs. preview: Live requires a prior
ms app deploy. Preview builds from source on demand — it works without any deployment and always reflects unpublished code.
Workflow
- Memory Bank → 2. Verify Project + Env → 3. Resolve Mode → 4. Run → 5. Surface URL
Step 1: Check Memory Bank
Read memory-bank.md per shared-instructions.md for the app's environment/app identifiers, if recorded.
Step 2: Verify Project + Env
test -f ms.config.json || { echo "Not in a Microsoft App workspace."; exit 1; }
BIN=ms
$BIN auth status # must report the expected UPN
--app and --environment-id can be passed explicitly to run from outside a project directory — ms.config.json is only needed for the defaults.
Step 3: Resolve Mode
If not already clear from the user's request, ask:
"Do you want to open the live deployed version, a preview of the latest code on main, or a preview of a specific commit?"
Map intent to mode:
| User says | Mode |
|---|---|
| "live", "deployed", no qualifier | live (default — no flag needed) |
| "preview", "latest", "unpublished", "before deploy" | --mode preview |
| "preview at commit X" / specific SHA provided | --mode preview --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 · 123 lines · 44 tokens per session scan A 18a458e40550
play is a skill published in the GitHub repository microsoft/managed-apps (5 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 1,165 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…