Borrowing it
Nothing to install: this file belongs to geekfujiwara/CodeAppsDevelopmentStandard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geekfujiwara/CodeAppsDevelopmentStandard/main/.github/skills/managed-runtime/SKILL.mdgit clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandardWrote 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/geekfujiwara/codeappsdevelopmentstandard/managed-runtime)<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/managed-runtime"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/managed-runtime/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/geekfujiwara/codeappsdevelopmentstandard/managed-runtime"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/managed-runtime.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 | $0.00108 | $0.03065 |
| Opus 5.5 | $0.00043 | $0.01226 |
| Sonnet 5.5 | $0.00022 | $0.00613 |
| Haiku 4.5 | $0.00011 | $0.00307 |
Grade A, and why
managed-runtime 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 17d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Managed Runtime アプリ開発スキル
Microsoft Copilot Managed Runtime のアプリを、CLI（@microsoft/managed-apps-cli、コマンド ms）と
SDK（@microsoft/managed-apps）で最初から作る。手順は Microsoft Learn の
CLI クイックスタート
に沿う。
[!CAUTION] Public Preview。 API・テンプレート・ツールは GA までに変わる可能性がある。 本番利用はユーザーの明示承認がある場合に限り、SDK / CLI / Vite plugin の版を固定する。
Code Apps との境界
| 要件 | 選ぶもの |
|---|---|
| GA 必須、Azure B2B ゲスト、Dataverse ソリューション / Power Platform Pipelines 中心、使う人のほとんどが Power Apps Premium を持つ | code-apps |
| Microsoft 365 の社内業務アプリ、Git のコミット単位で preview / live / rollback、M365 管理センターで一元管理 | 本スキル |
| Power Apps Premium を持たない人が中心で利用が不定期。Copilot Credits の従量課金で払いたい | 本スキル |
@microsoft/power-apps を @microsoft/managed-apps に置き換えるだけの移行はしない。
判断材料は 比較リファレンス。
スクリプト
| スクリプト | 用途 |
|---|---|
| scripts/check_prereqs.py | Node / Git / Git Credential Manager / Git identity / ms CLI / サインインの確認（Step 1） |
| scripts/create_app.py | リポジトリ方式を明示して ms app create。URL・作成先・GitHub リポジトリを事前検証（Step 4） |
| scripts/validate_project.py | push / deploy 前ゲート。Code Apps 混在、SDK の版、.env 追跡、外部通信、共有接続の allowedActions、未 push を検出（Step 7・8） |
パラメータは references/.env.example を参照し、実値は .env に置く。
ワークフロー
Step 0: Preview 利用とライセンスを確認する
AskUserQuestion で次を確認し、承認がなければ code-apps を提案して止まる。
- Public Preview であること。
- 使う人ごとの支払い方法。Power Apps Premium を持つ人はクレジットを消費しない。持たない人は Managed Application Copilot Credits で払う（起動ごとと API 呼び出しごと。API 呼び出しは 1 回 0.1 クレジット）。 ローカル実行する開発者にも同じ要件がかかる。
- クレジットで払う人がいる場合は、管理者が M365 管理センター → Copilot → Cost management で従量課金を有効にし、 使う人を実行用の支出ポリシーに入れる。作るときの課金設定とは別。見積もり方は 比較リファレンスのライセンス節。
- アプリは組織内向け。組織内共有リンクはゲストに使えない。
- 既定 CSP は外部通信を遮断する。外部 API はコネクタ経由で呼ぶ。
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/.env.example 1.6 KB
- references/cli-reference.md 3.1 KB
- references/github-actions.md 3.3 KB
- references/repository-modes.md 3.7 KB
- references/sdk-usage.md 5.3 KB
- references/troubleshooting.md 5.9 KB
- scripts/check_prereqs.py 7.2 KB runs code
- scripts/create_app.py 12 KB runs code
- scripts/validate_project.py 13 KB runs code
- templates/github-actions-deploy/.github/workflows/deploy-managed-app.yml 1.6 KB
- templates/github-actions-deploy/scaffold.json 771 B
- tests/test_create_app.py 2.8 KB runs code
- tests/test_validate_project.py 6.6 KB runs code
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.
- 17d ago Changed · +1 lines 44c058de9202
- 1mo ago First seen · 215 lines · 108 tokens per session scan A d782e42656b6
managed-runtime is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 3,065 once invoked, about $0.0004 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 2026-10-01.
managed-runtime compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| managed-runtimegeekfujiwara/CodeAppsDevelopmentStandard | Skill | 78 | yesterday | MIT | A | 108 | Claude Code, Codex |
| temps-add-handlergotempsh/temps | Skill | 903 | yesterday | Apache-2.0 | A | 90 | Claude Code, Codex |
| temps-add-plugingotempsh/temps | Skill | 903 | yesterday | Apache-2.0 | A | 88 | Claude Code, Codex |
| deployoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 46 | Claude Code |
| ranuichaxus/ran | Skill | 269 | today | MIT | A | 35 | Claude Code |
| api-testingpetrkindlmann/qa-skills | Skill | 250 | 15d ago | MIT | A | 129 | Claude Code, Codex |
| add-api-endpointwilldady/platypus | Skill | 131 | yesterday | MIT | A | 35 | Claude Code, Codex |