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/agent365npx skills add geekfujiwara/CodeAppsDevelopmentStandard --skill agent365git 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 | $0.00234 | $0.10547 |
| Opus 5 | $0.00117 | $0.05274 |
| Sonnet 5 | $0.00047 | $0.02109 |
| Haiku 4.5 | $0.00023 | $0.01055 |
Grade A, and why
agent365 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 — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI チームメイト開発スキル
Microsoft Agent SDK アプリを App Service で自己ホストし、Agent 365 のエージェント ID ブループリントと Teams アプリパッケージを通じて、Teams / Microsoft 365 Copilot の **同僚エージェント（agentUser）**として実際に会話できる状態にする。
Foundry ホスト方式は使わない。 Foundry の
activityprotocolを Agent 365 の agentUser エンドポイントに指定すると Agent 365 のトークンが 401 で拒否され、Teams で話しかけても応答が 返ってこない（無反応）。受理 audience を変える手段が無く、回避策も無い。 参考情報としてのみ references/foundry-hosted-bot.md に隔離する。 実装で作るのは常に自前 App Service の/api/messages。
本 SKILL.md には正常系フローだけを置く。手順の中身・分岐・異常系はすべて references/、
再現可能な操作は scripts/ にある。
| 原則 | 内容 |
|---|---|
| 正常系は自己ホスト | agentUser チャットが動くのは Agents SDK アプリを App Service で自己ホストする構成のみ |
| Foundry は参考 | Foundry エージェントは正常系に含めない。頭脳として使うなら中間サービスで読替が要る |
| SDK / REST のみ | Azure CLI・a365 CLI・Agents SDK で完結。ポータルのブラウザ自動操作は行わない |
| テンプレート駆動 | コミットするのは ${VAR} 入りテンプレートだけ。実値は .env / シークレットストアのみ |
| 外部データはデータ | 取り込んだ文章はフェンスで囲って渡し、実害のある操作はコードで ID を検証する |
| インスタンス単位 | 同意・写真・Dataverse 登録はインスタンスごと。作り直すたびにやり直す |
| ALM は委譲 | pre-commit・CI/CD・レビューゲート・リリース記録は alm スキルが担当する |
前提ツール: Python 3.10+、Azure CLI（
az）、Agent 365 CLI（a365）、.NET 8 SDK、Git。 認証はstandard/scripts/auth_helper.pyのキャッシュを共有し、agent365 用に個別ログインしない。
| 参照 | 用途 |
|---|---|
| digital-colleague-design.md | 何を作るかを決める（役割カタログ R1〜R6 / 機能ブロック B1〜B16 / 提案条件 / 制約 / 段階導入）。Step 0 で読む |
| self-hosted-agent.md | 自己ホストの完全手順（Azure Bot / App Service / appsettings.json / ログの読み方） |
| feature-blocks.md | 機能ブロックの実装レシピ（B2/B6/B9〜B16 のコピー・アプリ設定・DI 登録）。Step 8 で読む |
| agent-brain.md | 中身の作り込み（Azure OpenAI / 会話履歴 / プロンプト外部化 / Dataverse MCP / Work IQ / 再デプロイ） |
| prompt-injection.md | 外部データを読むなら必須。フェンス / 許可リスト / 検知 / 同意の強制の 4 層。Step 8 で読む |
| usage-accounting.md | 誰が・何に・いくら使ったかの計測（B15）。Azure ポータルでは出せない内訳。Step 8 で読む |
| incoming-files.md | 送られたファイルを受け取る（B16）。取得経路と supportsFiles。Step 8 で読む |
| assistant-agent-pattern.md | 秘書・同僚としての標準品質（承認後の実行 / 権限準拠検索 / 人格 / プレゼンス） |
| sample-implementation-cases.md | 評価・運用のサンプル実装事例（KPI ドリルダウン / 複数ターン評価 / 非同期ジョブ / Power Automate / Dataverse ミラー） |
| architecture.md | 2 種類のブループリントの違い / manifest スキーマ / 公開経路 / 表示名・アイコンの変更 |
| troubleshooting.md | 異常系（401 / AADSTS82001 / AADSTS65001 / カタログ公開の 409・403 など） |
| .env.example | 環境変数の一覧と取得元 |
alm |
秘匿化ゲート・CI/CD・リリース記録 |
| 参考のみ | foundry-hosted-bot.md（Foundry ホスト方式）/ poc-quickstart.md（共有エージェントの簡易ルート）/ team-pattern.md（複数体構成）/ a365-cli.md |
What ships with it
57 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 11 KB
- references/a365-cli.md 5.2 KB
- references/agent-brain.md 40 KB
- references/architecture.md 8.2 KB
- references/assistant-agent-pattern.md 12 KB
- references/code-sandbox.md 12 KB
- references/digital-colleague-design.md 29 KB
- references/document-sharing.md 6.2 KB
- references/feature-blocks.md 28 KB
- references/foundry-hosted-bot.md 4.9 KB
- references/incoming-files.md 8.9 KB
- references/outbound-formatting.md 9.0 KB
- references/poc-quickstart.md 5.7 KB
- references/progress-updates.md 5.7 KB
- references/prompt-injection.md 14 KB
- references/sample-implementation-cases.md 9.3 KB
- references/scheduled-delivery.md 13 KB
- references/self-hosted-agent.md 11 KB
- references/team-pattern.md 11 KB
- references/templates/agent.template.yaml 1.5 KB
- references/templates/AgentHealth.template.cs 3.0 KB
- references/templates/AgenticIdentity.template.cs 3.3 KB
- references/templates/agenticUser.template.json 302 B
- references/templates/AgentProgress.template.cs 11 KB
- references/templates/assistant-system-prompt.template.md 7.0 KB
- references/templates/CodeSandbox.template.cs 9.3 KB
- references/templates/DocumentLedger.template.cs 11 KB
- references/templates/DocumentShareTools.template.cs 23 KB
- references/templates/IncomingFiles.template.cs 18 KB
- references/templates/MailboxWorker.template.cs 15 KB
- references/templates/MailTools.template.cs 14 KB
- references/templates/manifest.template.json 1.8 KB
- references/templates/MessageHtml.template.cs 13 KB
- references/templates/PresenceWorker.template.cs 2.9 KB
- references/templates/SandboxTools.template.cs 22 KB
- references/templates/ScheduleStore.template.cs 12 KB
- references/templates/ScheduleTools.template.cs 8.0 KB
- references/templates/ScheduleWorker.template.cs 8.3 KB
- references/templates/TeamsChatTools.template.cs 17 KB
- references/templates/UsageStore.template.cs 7.0 KB
- references/templates/UsageTools.template.cs 13 KB
- references/templates/WebSearchTools.template.cs 8.7 KB
- references/troubleshooting.md 73 KB
- references/usage-accounting.md 11 KB
- references/web-grounding.md 10 KB
- scripts/build_teams_package.py 11 KB runs code
- scripts/configure_agent_presence.py 6.7 KB runs code
- scripts/create_blueprint.py 4.5 KB runs code
- scripts/create_instance.py 6.1 KB runs code
- scripts/deploy.py 3.9 KB runs code
- scripts/discover_foundry_context.py 8.4 KB runs code
- scripts/grant_agent_graph_scopes.py 8.9 KB runs code
- scripts/grant_agent_instance_consent.py 6.7 KB runs code
- scripts/provision_code_sandbox.py 11 KB runs code
- scripts/provision_selfhost.py 10 KB runs code
- scripts/publish_teams_app.py 7.7 KB runs code
- scripts/set_agent_user_photo.py 6.3 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.
- 2d ago First seen · 504 lines · 234 tokens per session scan A 9fc281653598
agent365 is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (59 stars, last pushed 4d ago), licensed MIT. It adds 234 tokens to every session and 10,547 once invoked, about $0.0012 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…