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/azure-infra/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/azure-infra)<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/azure-infra"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/azure-infra/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/azure-infra"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/azure-infra.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 | $0.00157 | $0.03151 |
| Opus 5.5 | $0.00063 | $0.01260 |
| Sonnet 5.5 | $0.00031 | $0.00630 |
| Haiku 4.5 | $0.00016 | $0.00315 |
Grade A, and why
azure-infra 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 8d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure 基盤（azure-infra）スキル
Azure 開発を、テナントのセキュリティガバナンスに準拠したまま進めるためのスキル。 要件から適切なリファレンスアーキテクチャを選定し、構築・デプロイ・検証・クリーンアップまでを一貫して行う。
原則: 組織ポリシー（Azure Policy / Conditional Access）と戦わず、準拠する構成を採る。
担当範囲: 基盤（VNet / Private Endpoint / Managed Identity / RBAC / デプロイ経路）を扱う。 Azure の個別サービスを使うアプリ側の実装（MCP Server、データ基盤、音声認識など）は各専門スキルが持ち、基盤部分だけをこのスキルに委譲する。
publicNetworkAccess=Disabledでも Private Link は常に到達可能——これを土台にする。
Step 0: 事前確認（会話の最初に 1 回だけ）
本スキルの利用が確定したら、standard の共通契約に加え、 1 回の AskUserQuestion で次をまとめて確認する。
| # | 質問 | 合格条件 |
|---|---|---|
| 1 | 対象 subscription、resource group、region、予算はどれか | 実装先と課金上限、作成 / 削除の承認範囲が確定している |
| 2 | リソース作成と RBAC 割り当ての担当者は誰か | リソース作成は対象 scope の Contributor 相当、role assignment は Role Based Access Control Administrator / User Access Administrator / Owner の担当者を記録している |
| 3 | 適用される Azure Policy と Conditional Access は何か | public network、shared key、allowed regions / SKUs、private endpoint、MFA の制約を確認している |
| 4 | ネットワーク変更の担当者は誰か | VNet、subnet、Private DNS、private endpoint に必要な権限と既存ネットワーク所有者の承認がある |
| 5 | デプロイ経路とシークレット管理は何か | Managed Identity / workload identity、Key Vault、CI runner のネットワーク到達性を確定している |
| 6 | 検証とクリーンアップを誰が行うか | security test、cost確認、削除期限、保持対象を記録している |
広い Owner を既定にせず、リソース作成と role assignment を分離する。
Policy、MFA、Private DNS のいずれかが不明なら Step 4 の構築へ進まない。
リファレンスアーキテクチャ一覧（メニュー）
| リファレンス | 用途 | ドキュメント |
|---|---|---|
| セキュアな Web × ストレージ | 公衆アクセス禁止ストレージのコンテンツを Web で安全配信 | references/secure-website.md |
| Web / SPA の Entra ID ログイン | 同一タブ redirect、API access token、認証後の実機検証 | references/browser-auth.md |
| Microsoft Foundry エージェント | Web 組み込みエージェント / 知識グラウンディング(Work IQ・Foundry IQ・Fabric IQ) / AI Gateway ガバナンス | references/foundry-agent.md |
| MCP Server（Azure Functions） | 社内データを Copilot Studio エージェントへ公開する自前 MCP Server | mcp-server スキル |
| 短期トークン発行（トークン ブローカー） | ブラウザから Azure サービスへ直結する（WebSocket 等）ための短期トークンを、Managed Identity で発行してカスタム コネクタ経由で渡す | references/token-broker.md |
What ships with it
21 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 1.8 KB
- references/browser-auth.md 7.4 KB
- references/foundry-agent.md 12 KB
- references/preflight-checklist.md 2.1 KB
- references/secure-website.md 12 KB
- references/token-broker.md 9.2 KB
- references/troubleshooting.md 9.2 KB
- scripts/check_browser_auth.mjs 3.4 KB runs code
- scripts/deploy_functionapp.yml 1.6 KB
- scripts/ensure_az_mfa.ps1 3.4 KB runs code
- scripts/setup_private_endpoint.ps1 6.0 KB runs code
- scripts/test_browser_auth.mjs 4.3 KB runs code
- templates/entra-browser-auth/.env.example 189 B
- templates/entra-browser-auth/.gitignore 56 B
- templates/entra-browser-auth/package.json 368 B
- templates/entra-browser-auth/public/auth-callback.html 263 B
- templates/entra-browser-auth/README.md 3.8 KB
- templates/entra-browser-auth/scaffold.json 306 B
- templates/entra-browser-auth/src/auth.ts 3.9 KB runs code
- templates/entra-browser-auth/tests/auth.test.mjs 7.8 KB runs code
- templates/entra-browser-auth/tsconfig.json 231 B
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.
- 8d ago Changed · +8 lines · +27 tokens per session 83e5478e670a
- 1mo ago First seen · 126 lines · 130 tokens per session scan A ab0fb1e77ff3
azure-infra is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 3,151 once invoked, about $0.0006 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 2026-10-03.
azure-infra compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| azure-infrageekfujiwara/CodeAppsDevelopmentStandard | Skill | 78 | yesterday | MIT | A | 157 | Claude Code, Codex |
| architecture-diagrammateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| aws-architecture-diagramautomateyournetwork/netclaw | Skill | 715 | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| architecture-paradigm-microservicesathola/claude-night-market | Skill | 348 | yesterday | MIT | A | 33 | Claude Code |
| architecture-paradigm-serverlessathola/claude-night-market | Skill | 348 | yesterday | MIT | A | 37 | Claude Code |
| data-data-lakehousej4flmao/agent-skills | Skill | 38 | 3d ago | MIT | A | 113 | Claude Code, Codex |
| data-lake-architecturej4flmao/agent-skills | Skill | 38 | 3d ago | MIT | A | 170 | Claude Code, Codex |