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/standard/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/standard)<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/standard"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/standard/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/standard"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/standard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 3 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 39 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 49 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 70 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 75 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00131 | $0.06098 |
| Opus 5.5 | $0.00052 | $0.02439 |
| Sonnet 5.5 | $0.00026 | $0.01220 |
| Haiku 4.5 | $0.00013 | $0.00610 |
Grade A, and why
standard 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 10d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Platform 包括開発標準スキル
全スキル共通の開発基盤。このスキルが扱うのは 認証 / .env / ソリューション運用 の 3 テーマのみ。 個別コンポーネントの設計・構築ルールは各専門スキルが持つ（→ スキルカタログ README）。
クイックスタートは認証後の一度の確認から開発デプロイ・検証まで継続する
リポジトリ URL と「クイックスタート」を依頼されたら quickstart.md を優先する。
.github/agents / .github/skills / .gitignore を安全に配置しただけでは停止せず、
利用可能な環境情報取得 → 共通認証・.env・認証キャッシュの再利用検証まで実行する。
認証準備後は AskUserQuestion で要望確認し、必ず回答待ちで一旦停止する。
資料があれば対象資料からの継続・対象変更・準備までを選べる形にし、
資料なしならフォルダー名から具体的なアプリ案を複数提示して選んでもらう。
回答前に資料変換・仕様作成・設計提案へ進まず、継続回答後は Step 0〜3 の契約に従い、
ルートの業務資料を spec/input/ へ整理 → spec-builder → architecture・既存テンプレート提案 →
認証キャッシュで既存環境・必要時の Azure を調査 → フル構成の開発デプロイ・実動作検証まで進む。
以降は自分で分かることを調べ、既知事項や通常の実装判断で AskUserQuestion を繰り返さない。
要望確認の選択肢には、資料・テンプレートに基づく開発デプロイ・テストまでの範囲を明記する。
白紙の業務ヒアリングではなく、事実・仮説を分けた業務改善と AI 活用の推奨を先に示す。
業務フローと構成の Mermaid 図をチャットと Markdown の両方へ出す。図は質問ポップアップ内に入れない。
例外的に本人の判断が不可欠な事項だけ質問し、承認済みの開発範囲では提案の都度停止しない。
各専門スキルのプレデプロイ・品質テスト・デプロイ後の検証を行い、実際の構成・各 URL・文書を報告する。
必須構成が全て検証済みの場合だけ「全て完了」とし、未検証・承認待ちは明示する。
環境スキャンは接続先等のメタデータ取得であり、DLP / ACP・Code Apps 許可の事前診断とは分ける。
共通認証・承認・既存ファイル保護は省略せず、サインインや回答待ちの後は同じタスクを再開する。
サブリファレンス（必要に応じて参照）
| リファレンス | 内容 |
|---|---|
| 一気通貫クイックスタート | Step 0〜3: 標準更新・認証後に要望確認で一旦停止し、回答後は仕様・テンプレート・環境調査からフル構成の開発デプロイ・実動作検証まで自律実行する。配置は scripts/initialize_workspace.py |
| クイックスタートの異常系 | 配置の競合・権限不足・資料なしの場合の継続方法と恒久対策 |
| Power Platform 開発標準 | 設計原則・Phase 別手順・チェックリストをまとめた全体ガイド |
| インタラクティブ環境セットアップ | PAC CLI + Dataverse API で .env を対話的に構成する手順（プロジェクト開始時に最初に参照） |
| 認証リファレンス | auth_helper.py の詳細実装・認証パターン（Dataverse / Flow / ARM・Azure SQL・Graph・自前 API のスコープ一覧を含む） |
| .env サンプル | 全フェーズ共通の .env テンプレート（各テーマで .env にコピーして値を設定） |
| コネクタ ID カタログ | コネクタの通称（SharePoint / Outlook / SQL 等）→ shared_xxx の対応表。scripts/connector_catalog.py で解決する |
| 環境チェック・障害復旧 | 明示的なチェック依頼時、または開発・デプロイ障害時だけ使用する。通常開発の事前ゲートにしない |
| Dataverse MCP 登録 | VS Code / Copilot から Dataverse を直接操作する MCP サーバー登録手順（upsert_skill 等） |
| ブラウザ自動化方針 | ブラウザ起動前に AskUserQuestion で Edge プロファイルを確認し、回答前は操作しない。ポータル操作は VS Code 統合 Playwright ブラウザ（playwright-browser_navigate / playwright-browser_click / playwright-browser_type / playwright-browser_handle_dialog 等）を使う。Playwright MCP サーバー・Playwright 単体ブラウザのインストール・起動は禁止 |
What ships with it
36 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 4.8 KB
- references/auth-patterns.md 27 KB
- references/browser-automation.md 7.6 KB
- references/connector-catalog.json 6.9 KB
- references/dataverse-mcp-setup.md 8.1 KB
- references/demo-pdf-generation.md 5.7 KB
- references/design-language.md 5.2 KB
- references/gitignore-template 955 B
- references/html-email-template.md 6.2 KB
- references/icon-creation.md 15 KB
- references/interactive-setup.md 13 KB
- references/map-embed-pattern.md 14 KB
- references/power-platform-development-standard.md 112 KB
- references/quickstart.md 16 KB
- references/template-components.md 9.4 KB
- references/troubleshooting.md 6.3 KB
- scripts/add_to_solution.py 5.8 KB runs code
- scripts/auth_helper.py 35 KB runs code
- scripts/auth_preferences.py 4.3 KB runs code
- scripts/azure_helper.py 4.3 KB runs code
- scripts/bootstrap.mjs 12 KB runs code
- scripts/check_connections.py 1.3 KB runs code
- scripts/check_mcp_client.py 3.2 KB runs code
- scripts/connector_catalog.py 6.0 KB runs code
- scripts/find_app.py 1.0 KB runs code
- scripts/generate_icon_png.py 4.0 KB runs code
- scripts/initialize_workspace.py 4.8 KB runs code
- scripts/requirements.txt 60 B
- scripts/setup_environment.py 11 KB runs code
- scripts/test_retry.py 1020 B runs code
- scripts/verify_auth_cache.py 2.6 KB runs code
- tests/test_auth_cache.py 7.2 KB runs code
- tests/test_auth_preferences.py 7.7 KB runs code
- tests/test_initialize_workspace.py 5.1 KB runs code
- tests/test_quickstart_contract.py 7.2 KB runs code
- tests/test_setup_environment.py 4.1 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.
- 10d ago Changed · +12 lines · +13 tokens per session 31b913c54fcf
- 14d ago Changed · +18 lines 11755b79e0bd
- 17d ago Changed · +26 lines · +46 tokens per session 31b44bd67e3a
- 20d ago Changed · +3 lines bcb3c15e95be
- 1mo ago Changed · +27 lines b9c5da92be1d
- 1mo ago Changed · +2 lines 45e633c6554a
- 2mo ago Changed · +6 lines 0f07ac3cd9b8
- 2mo ago Changed · +3 lines 9c3d882b5832
- 2mo ago Changed · +1 lines 842dd8ef8a3e
- 2mo ago First seen · 153 lines · 72 tokens per session scan A cbfdb61dc437
standard is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 6,098 once invoked, about $0.0005 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 2026-08-30.
standard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| standardgeekfujiwara/CodeAppsDevelopmentStandard | Skill | 78 | yesterday | MIT | A | 131 | Claude Code, Codex |
| sparc-methodologyruvnet/RuView | Skill | 103k | yesterday | MIT | A | 29 | Claude Code |
| architecture-diagrammateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| product-image-processorAlpacaLabsLLC/skills-for-architects | Skill | 402 | 3d ago | MIT | A | 45 | Claude Code |
| site-historyAlpacaLabsLLC/skills-for-architects | Skill | 402 | 3d ago | MIT | A | 53 | Claude Code |
| modular-skillsathola/claude-night-market | Skill | 348 | yesterday | MIT | A | 24 | Claude Code |
| plugin-reviewathola/claude-night-market | Skill | 348 | yesterday | MIT | A | 23 | Claude Code |