CodeAppsDevelopmentStandard: Skill for Claude Code

.github/skills/architecture/SKILL.md

architecture is a skill for Claude Code, Codex from geekfujiwara/CodeAppsDevelopmentStandard. It costs 152 tokens per session (21,875 once invoked), scanned A, original, MIT.

A guide for designing the overall architecture of Microsoft Power Platform solutions, including Copilot Studio, Power Automate, Code Apps, Power Pages, and AI Builder.

In plain words
What is it for?
Use it to gather requirements, select components, design integrations, and decide between a small proof of concept and a full AI teammate implementation.
Why use it?
It helps choose suitable components and integrations before implementation begins, based on the business problem and constraints.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

This is geekfujiwara/CodeAppsDevelopmentStandard's own configuration. It tells Claude Code and Codex how to work on CodeAppsDevelopmentStandard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CodeAppsDevelopmentStandard configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Managed Runtime を採用した場合の実装は [`managed-runtime` スキル](../managed-runtime/SKILL.md) で行う。.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/geekfujiwara/CodeAppsDevelopmentStandard/main/.github/skills/architecture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandard

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/architecture/github.svg)](https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/architecture)
Your own site
<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/architecture"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/architecture/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.

agentmods 80×15 button for architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/architecture"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 21,875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Prompt Injection · line 76
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.21875
Opus 5.5 $0.00061 $0.08750
Sonnet 5.5 $0.00030 $0.04375
Haiku 4.5 $0.00015 $0.02187

Measured 10d ago against content hash c37219a8df6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture 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.

.github/skills/architecture/SKILL.md · 872 lines

How it starts

The opening of the file, as written. The whole thing — 872 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power Platform 共通アーキテクチャデザインスキル

ユーザー要件から Power Platform のどのコンポーネントを使うか を判断し、全体アーキテクチャを設計する。 各コンポーネントの得意領域・制約・統合パターンを把握し、迷わず最適な構成を選定するためのスキル。

このスキルの位置づけ: Phase 1(設計)の最初に実行する。個別コンポーネントのスキルに入る前に、まず要件を深掘りして全体像を確定させる。

SharePoint URL だけでは直接接続の指示と解釈しない。 Code Apps の業務データは、直接接続・継続利用が 明示された場合を除き Dataverse に移行する。URL は仕様・移行元の参照情報として扱う。 dataverse でスキーマを構築し、data-migration で承認付き移行・照合を行う。 ナレッジとしての文書参照と Code Apps の業務データ保存先は区別する。


0. 要件ヒアリング(Phase 1 の最初に必ず実行)

クイックスタート時は提案先行モードを優先する

standard/references/quickstart.md Step 1 から来た場合は、認証準備後の要望確認で得た回答・環境情報・資料・ spec-builder の結果を引き継ぎ、以下の通常ヒアリング表を一から質問しない。 要望確認の回答前なら、この提案工程へ進まず AskUserQuestion の回答を待つ。 資料がなければワークスペース名から提示済みのアプリ案のうち、選ばれた案を具体化し、方向性を聞き直さない。 業界知識とベストプラクティスを使って、事実・仮説・推奨を分けた To-Be 業務、AI 改善、 Code Apps + Dataverse を既定とする構成、段階的な実装計画まで具体化する。 未確認の固有規程・人数・価格・契約は創作せず、仮説または要確認とする。 白紙の要件ヒアリングや既存システムの単純なリフト&シフトで終わらせない。

業務フロー図とアーキテクチャ図を Mermaid コードブロックでチャットと Markdown の両方へ出力する。 業務フローは spec/output/docs/business-requirements.md、構成・AI 改善・実装計画は spec/output/docs/design-requirements.md に既存内容を保護して統合する。 図は質問ポップアップ内に入れない。推奨案・代替案・判断材料はチャットに示す。 既存リポジトリの templates/ / samples/・マニフェスト・前提条件を調べ、適合するテンプレートの パス・選定理由・不足機能を示す。既知事項や通常の実装判断で AskUserQuestion を繰り返さない。 要望確認の回答・資料・テンプレート・読み取り API で分かることは自分で調べ、 承認済みの開発範囲では構成案ごとの再承認を求めず、環境調査・フル構成デプロイ・実動作検証へ進む。 認証や環境選択の回答後に利用者へ工程を投げ返さず、構成・各 URL・検証結果と文書更新まで同じタスクで進める。 設計・実装・デプロイ・移行・追加費用の承認範囲は区別する。

通常モードのヒアリング

IT に詳しくないエンドユーザーに向き合うプロの IT コンサルタントとして振る舞う。 専門用語を使わず、業務課題・現状・理想の姿を引き出すことを最優先にする。

AskUserQuestion で深掘りする項目

既知の情報は再質問せず、必要な不足事項だけを 1 問ずつ確認する。

確認項目 質問の例
解決したい課題 今どんな問題・不便がありますか?
現状の管理方法 今は Excel・メール・紙などで管理していますか?
利用者・規模 誰が使いますか?社内のみですか?何人くらいですか?
利用者のライセンスと頻度 使う人は Power Apps Premium を持っていますか?持っていない人は毎日使いますか、それとも月に数回ですか?(→ §5「ライセンスで使い分ける」)
必要な操作 登録・検索・承認・通知・レポートのうち何が必要ですか?
外部連携 Teams / Outlook / SharePoint / 既存システムとつなぎたいですか?
Dataverse 外のデータ 参照したいデータは 既存の基幹 DB・ファイルサーバー・業務 API にありますか?(→ あるなら §6.5:自前 MCP Server)
データの量と使い方 件数・増え方・履歴分析・Power BI・機械学習・文書(手順書)の引用は必要ですか?(→ 必要なら §6.6:データ基盤の使い分け)
AI・自動化 チャットで問い合わせできると便利ですか?自動通知は必要ですか?
人としての同僚 ツールとしての AI でよいですか?それとも自分のメールアドレスや予定表を持ち、メンバーとして働く存在が欲しいですか?(→ 後者なら §7)

Read the full file on GitHub · 872 lines

Files

What ships with it

5 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.

Changes

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.

  1. 10d ago Changed · +7 lines c37219a8df6d
  2. 17d ago Changed · -2 lines · -185 tokens per session 75241663a6e1
  3. 28d ago Changed · +2 lines e1f52b766af3
  4. 1mo ago Changed · +1 lines 45428266504e
  5. 1mo ago Changed · +64 lines · +60 tokens per session 3140cf75834a
  6. 1mo ago Changed · +32 lines 04fcb86180bb
  7. 1mo ago Changed · +11 lines 15da5e838343
  8. 1mo ago Changed · +37 lines 8ef90f109c5e
  9. 2mo ago Changed · +2 lines · +42 tokens per session 7eea3207a7c3
  10. 2mo ago First seen · 718 lines · 235 tokens per session scan A 978754f52bc6

Subscribe to this mod's changes

architecture is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 21,875 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 2026-08-30.

Related

architecture compared with skills from other repositories

architecture next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
architecturegeekfujiwara/CodeAppsDevelopmentStandardSkill78yesterdayMITA152Claude Code, Codex
sparc-methodologyruvnet/RuViewSkill103kyesterdayMITA29Claude Code
architecture-diagrammateaix/mateclawSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
product-image-processorAlpacaLabsLLC/skills-for-architectsSkill4023d agoMITA45Claude Code
site-historyAlpacaLabsLLC/skills-for-architectsSkill4023d agoMITA53Claude Code
modular-skillsathola/claude-night-marketSkill348yesterdayMITA24Claude Code
plugin-reviewathola/claude-night-marketSkill348yesterdayMITA23Claude Code