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/copilot-studio/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/copilot-studio)<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/copilot-studio"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/copilot-studio/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/copilot-studio"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/copilot-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 123 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 307 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 318 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 | $0.00071 | $0.06269 |
| Opus 5.5 | $0.00028 | $0.02508 |
| Sonnet 5.5 | $0.00014 | $0.01254 |
| Haiku 4.5 | $0.00007 | $0.00627 |
Grade A, and why
copilot-studio 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 17d 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Studio エージェント構築スキル
Copilot Studio エージェントを 生成オーケストレーション（Generative Orchestration）モード一択 で構築する。 外部トリガー・ニュース配信エージェント等の応用パターンまでカバーする統合スキル。
環境診断は明示依頼時・障害時だけ。通常は構築を開始し、環境・DLP の事前確認を挟まない。 ポリシー関連の拒否が発生したら admin の権限確認付き復旧 に従う。 現在の委任権限で可能な診断・承認済み最小修復・限定リトライを行い、権限不足なら管理者へ依頼する。
サブリファレンス（必要に応じて参照）
| リファレンス | 内容 |
|---|---|
| admin スキル（環境・DLP チェック） | 明示依頼時・障害時だけの権限確認付き診断・修復 |
| 構築リファレンス | 構築手順の詳細・Instructions テンプレート・スクリプトコード |
| 外部公開 WebChat SDK（標準） | 外部公開の標準パターン。BotFramework WebChat SDK で UI フルカスタマイズ・プログラム的メッセージ送信 |
| 外部公開デザインテンプレート（標準 UI） | 標準 UI デザイン：左パネル（カテゴリ別カード＋プロンプトチップス）＋ 右 WebChat パネル（グラデーション枠・AI タイピング Tips） |
| ライトモード・テンプレート集 | ライトモード 5 レイアウト（workspace / minimal / hero-cards / dashboard / sidebar）＋ 全テンプレート標準の**「新しい会話（初期化）」ボタン**（React 再マウント対策 freshWebchatEl()） |
| 外部公開 手動認証（SSO） | Entra ID サインイン必須＋ユーザー権限で Dataverse アクセス（RLS/OBO）。2 アプリ登録・FIC（シークレットレス）・OAuth カードの silent トークン交換 |
| 外部公開 iframe（レガシー・非推奨） | iframe で埋め込む簡易版。UI カスタマイズ不可のため標準では使わない。動作確認・PoC 用のみ |
| 外部トリガー | メール受信・Teams メッセージ・スケジュール等のトリガー追加 |
| Standard MCP tool | UI観測済みprivate APIによる承認付きMCP追加とread-back |
| Standard model selection | GPT component YAMLのモデル値をETag・SHA-256・承認plan付きで変更 |
| トリガーパターン | トリガーの設定パターン集 |
| トラブルシューティング | トリガー関連を中心とした異常系・トラブルシューティング |
| ニュース配信エージェント | RSS + Web検索 + Work IQ MCP によるニュース収集・配信エージェント構築 |
| ニュース配信デプロイガイド | ニュース配信エージェントのデプロイ手順 |
| ニュース配信メールテンプレート | ニュース配信メールの HTML テンプレート |
| トランスクリプト分析 | 会話トランスクリプトの分析パターン（ボット識別・ユーザー識別） |
What ships with it
46 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 4.3 KB
- references/build-reference.md 26 KB
- references/external-web-embed.md 11 KB
- references/market-research-deployment-guide.md 13 KB
- references/market-research-email-template.md 12 KB
- references/market-research-report.md 33 KB
- references/model-selection.md 2.5 KB
- references/standard-mcp-tools.md 3.5 KB
- references/transcript-analytics.md 5.6 KB
- references/trigger-patterns.md 27 KB
- references/trigger.md 42 KB
- references/troubleshooting.md 27 KB
- references/webchat-sdk-design-template.md 20 KB
- references/webchat-sdk-embed.md 28 KB
- references/webchat-sdk-light-templates.md 10.0 KB
- references/webchat-sdk-manual-auth.md 9.4 KB
- scripts/add_fic.py 3.1 KB runs code
- scripts/analyze_bot.py 4.1 KB runs code
- scripts/check_email_trigger_status.py 4.7 KB runs code
- scripts/check_publish.py 432 B runs code
- scripts/deploy_agent.py 30 KB runs code
- scripts/deploy_email_trigger.py 13 KB runs code
- scripts/deploy_news_agent.py 27 KB runs code
- scripts/deploy_news_flow.py 9.3 KB runs code
- scripts/deploy_website.py 8.5 KB runs code
- scripts/fix_email_msgid.py 13 KB runs code
- scripts/fix_email_reply.py 15 KB runs code
- scripts/fix_email_trigger_v2.py 10 KB runs code
- scripts/fix_email_trigger.py 12 KB runs code
- scripts/generate_news_icon.py 5.6 KB runs code
- scripts/provision_agent.py 9.8 KB runs code
- scripts/set_agent_channels.py 7.1 KB runs code
- scripts/set_agent_security.py 3.8 KB runs code
- scripts/set_model.py 12 KB runs code
- scripts/setup_email_trigger.py 8.2 KB runs code
- scripts/setup_webchat_auth.py 13 KB runs code
- scripts/standard_model_yaml.py 3.2 KB runs code
- scripts/standard_tool_browser_runner.mjs 15 KB runs code
- scripts/standard_tool_plan.py 8.1 KB runs code
- scripts/trigger_contract.py 2.1 KB runs code
- tests/test_provision_agent.py 2.6 KB runs code
- tests/test_set_model.py 4.5 KB runs code
- tests/test_standard_model_yaml.py 2.2 KB runs code
- tests/test_standard_tool_browser_runner.mjs 4.9 KB runs code
- tests/test_standard_tool_plan.py 4.2 KB runs code
- tests/test_trigger_contract.py 4.0 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.
- 17d ago Changed · -1 lines 63e33d75d4a8
- 27d ago Changed · +26 lines 3ddaedd0958f
- 1mo ago Changed · +8 lines · +10 tokens per session da91e303c541
- 1mo ago Changed · +17 lines 948559077654
- 1mo ago Changed f10243839f9c
- 2mo ago Changed · +6 lines e9df68c5514e
- 2mo ago First seen · 330 lines · 61 tokens per session scan A e28b1002a0d0
copilot-studio is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 6,269 once invoked, about $0.0003 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.
copilot-studio compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| copilot-studiogeekfujiwara/CodeAppsDevelopmentStandard | Skill | 78 | yesterday | MIT | A | 71 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |