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/geekfujiwara/codeappsdevelopmentstandard/code-appsnpx skills add geekfujiwara/CodeAppsDevelopmentStandard --skill code-appsgit clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandardWhat 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 | $0.00066 | $0.12034 |
| Opus 5 | $0.00033 | $0.06017 |
| Sonnet 5 | $0.00013 | $0.02407 |
| Haiku 4.5 | $0.00007 | $0.01203 |
Grade A, and why
code-apps 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 2d 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 — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Apps 開発スキル
Power Apps Code Apps(コードファースト)を TypeScript + React + Tailwind CSS で開発する。 UI 設計・CSP 構成・メール送信パターンまで Code Apps 開発の全領域をカバーする統合スキル。
[!NOTE] 本スキルは React + Vite の Web Code Apps 用。Expo/React Native、camera/barcode/location 等の 端末ネイティブ機能、Power Apps Developer app、Wrap が要件なら
mobile-appsへ切り替える。Native は Private Preview で本番利用できない。
[!NOTE] Microsoft Learn の現行概要では、Code Apps は React / Vue などの SPA を Power Apps 上でホストする仕組み とされている。 この開発標準はその中でも React ベース実装に標準化したガイドであり、他フレームワーク一般論ではなく、このリポジトリのテンプレートと運用実績に基づく推奨事項をまとめている。
1. 概要
Code Apps 開発は 設計 → 初回デプロイ → データソース接続 → 改善デプロイ の順に進む。
[!NOTE] サブエージェント並行実行パターン:
architectureスキルで Code Apps が確定し、dataverseスキルで スキーマが承認されたタイミングで、このスキルがサブエージェントとして起動される。 Dataverse 構築(--skip-localizeフェーズ)と Code Apps 開発(scaffold → deploy → add-data-source)は 並行して進める。Dataverse 構築が先に終わったら--localize-onlyでローカライズ&デモデータ投入。
標準ワークフロー全体像
[設計] ① デザインテンプレートを選ばせる(6種・プレビュー付き)
② 画面設計(design-pattern)→ ユーザー承認
│
[§2 初回デプロイ]
③ テンプレート scaffold + npm install(Dataverse 構築 Phase 2 と並行して即着手/VS Code では Code Apps サブエージェントとして起動)
④ ソリューション + 接続参照を用意(setup_connection_reference.py)★init より前
⑤ npx power-apps init(power.config.json 生成)
⑥ vite.config.ts 必須設定の確認 / .env 設定
⑦ npm run deploy -- --solution-id {GUID}(build + power-apps push)★初回 push でソリューション所属が確定
│
[§3 データソース接続]
⑧ npx power-apps add-data-source --api-id shared_commondataserviceforapps -cr ... -s ...(1 回だけ)
⑨ MicrosoftDataverseService + *WithOrganization ラッパーを実装
│
[§4 改善デプロイ]
⑩ src/ 実装 → npm run deploy(power-apps push を反復)
⑪ 最終 push 後に power-apps share(利用者は play、共同開発者だけ edit)
この後の章構成
| 章 | 内容 |
|---|---|
| §1 概要(本章) | 標準ワークフロー全体像・大前提・設計フェーズ(デザインテンプレート選択) |
| §2 初回デプロイ | 環境前提・scaffold・ソリューション/接続参照の準備・init・初回 build & push |
| §3 データソース接続 | add-data-source(接続参照バインド)・MicrosoftDataverseService・Lookup 名前解決 |
| §4 改善デプロイ | 開発時の必須ルール・再デプロイ・プレデプロイレビュー |
| §5 リファレンス | 全リファレンス索引・技術スタック・.env |
What ships with it
60 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 1.9 KB
- references/advanced-patterns.md 9.6 KB
- references/ai-evaluation-master-pattern.md 16 KB
- references/build-reference.md 24 KB
- references/calendar-pattern.md 7.6 KB
- references/checklist-scoring-pattern.md 9.0 KB
- references/cli-reference.md 18 KB
- references/component-catalog.md 22 KB
- references/connector-reference.md 12 KB
- references/copilot-chat-pattern.md 22 KB
- references/copilot-studio-connector.md 9.8 KB
- references/cross-tab-pattern.md 7.2 KB
- references/crud-ui-pattern.md 29 KB
- references/csp.md 8.7 KB
- references/csv-export-pattern.md 4.0 KB
- references/data-source-patterns.md 17 KB
- references/deep-link.md 8.5 KB
- references/design-approval.yml 3.2 KB
- references/design-pattern.md 21 KB
- references/design-templates.md 17 KB
- references/flow-integration.md 8.5 KB
- references/japan-map-pattern.md 15 KB
- references/japanese-sanitize.md 8.5 KB
- references/lookup-resolution.md 5.6 KB
- references/mail-pdf.md 10 KB
- references/maps/map-circle.svg 16 KB
- references/maps/map-full.svg 30 KB
- references/maps/map-mobile.svg 30 KB
- references/maps/map-polygon.svg 11 KB
- references/maps/README.md 1.4 KB
- references/master-detail-pane-pattern.md 11 KB
- references/mock-data-pattern.md 5.7 KB
- references/mypage-pattern.md 7.9 KB
- references/new-theme-checklist.md 4.1 KB
- references/owner-guard-pattern.md 14 KB
- references/pareto-chart-pattern.md 6.0 KB
- references/patch-nameutils.cjs 513 B runs code
- references/pre-deploy-review.md 19 KB
- references/previews/amber-orange.html 5.5 KB
- references/previews/emerald-teal.html 5.5 KB
- references/previews/indigo-violet.html 5.5 KB
- references/previews/ocean-blue.html 6.0 KB
- references/previews/rose-pink.html 5.5 KB
- references/previews/slate-mono.html 5.5 KB
- references/sample-authoring-guide.md 12 KB
- references/scheduling-pattern.md 8.7 KB
- references/service-flow-pattern.md 3.8 KB
- references/solution-alm.md 11 KB
- references/stage-path-pattern.md 5.9 KB
- references/telemetry-pattern.md 7.2 KB
- references/template-cache.md 6.9 KB
- references/template-snapshot/.gitignore 226 B
- references/template-snapshot/package-lock.json 306 KB
- references/template-snapshot/package.json 1.2 KB
- references/timeline-stepper-pattern.md 6.8 KB
- references/troubleshooting.md 83 KB
- references/user-identity.md 6.0 KB
- references/wizard-form-pattern.md 5.4 KB
- samples/geek-approval/.env.example 1.3 KB
- samples/geek-approval/components.json 446 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.
- 2d ago First seen · 589 lines · 66 tokens per session scan A df85c2e954ef
code-apps is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (59 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 12,034 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
compiler-orchestrator
Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.
feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
frontend-unit-testing
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.
gradio-themes
Build and customise Gradio themes. Use when creating, editing, or publishing Python-based Gradio themes that control colours, typography, spacing, shadows, and dark mode.
hf-gradio
Use Gradio applications via API. Use when the user asks for to generate a prediction from a Gradio app on Hugging Face spaces or public URL. For example, "Generate an image using black-forest-labs/FLUX.2-dev".
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.