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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/managed-appsnpx agentmods add skills/microsoft/managed-apps/stateWrote 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/state)<a href="https://agentmods.dev/skills/microsoft/managed-apps/state"><img src="https://agentmods.dev/badge/skills/microsoft/managed-apps/state/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/state"><img src="https://agentmods.dev/badge/skills/microsoft/managed-apps/state.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 | $0.00071 | $0.04196 |
| Opus 5.5 | $0.00028 | $0.01678 |
| Sonnet 5.5 | $0.00014 | $0.00839 |
| Haiku 4.5 | $0.00007 | $0.00420 |
Grade A, and why
state 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 — 381 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.
Managed Apps State with CLI schema + generated client
Every Microsoft Managed App can use built-in app state when the state feature is enabled for the
current CLI/environment: a NoSQL store the app calls directly (no middle-tier function, connector,
or SDK; the host attaches auth). Records are grouped into collections by an item type name; the
server assigns each record an itemId.
For schema-backed state, do not edit schema JSON by hand. Use ms project state ... to change
the schema, run ms project state generate-code, then call the generated TypeScript services from
app code.
Mandatory feature gate
Before using any guidance in this skill, it is recommended that the user is signed in to the CLI. Run
ms auth status, and if it reports no signed-in account, ask the user to run ms auth login.
ms feature status never prompts for sign-in, and features that are on by default for the user's
organization only apply once they are signed in, so a signed-out check can report state as
disabled even when it is available to them.
Then run:
ms feature status --name state --json
Continue only when the output has "success": true and feature.enabled is true. Read the JSON
rather than the human-readable output, which lists several settings that can each say "enabled". If
the command fails (non-zero exit or "success": false), the feature is not found, or
feature.enabled is false, stop and do not run any ms project state ... command.
When state is not enabled, recommend an alternative data-source path based on the user's need:
- Durable relational/business data: use
/add-dataverse. - SharePoint lists or document-backed collaboration data: use
/add-sharepoint. - Workbook-backed tabular data: use
/add-excel. - Mail, calendar, user profile, Teams, Azure DevOps, OneDrive, Copilot Studio, or Work IQ scenarios:
use the matching
/add-*skill. - Anything else: use
/add-data-sourceto discover and bind the appropriate connector.
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 b2e1d08544ab
- 29d ago First seen · 383 lines · 71 tokens per session scan A ac8e1c46dab8
state is a skill published in the GitHub repository microsoft/managed-apps (36 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 4,196 once invoked, about $0.0003 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 2026-10-10.
state compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| statemicrosoft/managed-apps | Skill | 36 | 3d ago | MIT | A | 71 | Claude Code |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | today | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | 3d ago | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | today | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 924 | today | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | 2d ago | Apache-2.0 | A | 63 | Claude Code, Codex |