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/cowork/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/cowork)<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/cowork"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/cowork/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/cowork"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/cowork.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 215 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 218 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 222 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 253 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 406 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 | $0.00116 | $0.16700 |
| Opus 5.5 | $0.00046 | $0.06680 |
| Sonnet 5.5 | $0.00023 | $0.03340 |
| Haiku 4.5 | $0.00012 | $0.01670 |
Grade A, and why
cowork 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 22d 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 — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cowork プラグイン開発（Dataverse MCP セット）
目的特化型の Copilot Cowork プラグイン（M365 アプリパッケージ .zip）を作る。
ビジネススキル（SKILL.md）と Dataverse MCP コネクタをセットにし、Entra ID の OAuth 2.0 認可コードフロー認証で
Cowork から Dataverse を直接操作できるようにする。
データ先は Dataverse だけではない:
agentConnectorsは remote MCP server を指すため、 mcp-server スキル で構築した 自前 MCP Server（Azure Functions） も 同じようにコネクタにできる。基幹 DB・ファイルサーバー・業務 API など Dataverse に無いデータを Cowork から扱う場合は 自前 MCP Server をコネクタにする を併せて読む （差分は Step 3 の権限・Step 4 の可否・Step 5 の Scope・Step 6 の URL の 4 点だけ）。
前提: 利用テナントが Frontier プレビュー に参加していること。 会社環境で Cowork の利用が許可されている場合のみこのスキルを使用してください。利用可否が不明な場合は管理者に確認してください。 異常系・トラブルシュートは references/troubleshooting.md を参照。
サブリファレンス
| リファレンス | 内容 |
|---|---|
| 自前 MCP Server をコネクタにする | Dataverse 外のデータ（基幹 DB / ファイルサーバー / 業務 API）を Cowork から扱う場合の差分手順 |
| 営業支援 CRM プラグイン テンプレート | 予定表・メール・チャットからの活動登録 / 目標達成プラン / マネージャーの障害レビュー。Code Apps の templates/sales-crm と同じ Dataverse を共有し、scaffold で生成する |
| 株主総会 想定問答アシスタント テンプレート | IR 抜粋を根拠に想定問答とリハーサル台本を下書きで登録・想定問答の点検。Code Apps の templates/agm-qa-assist と同じ Dataverse。変数は --questions で AskUserQuestion |
| 店長アシスト テンプレート | 店長の判断基準で品目ごとの発注案（夕方便・朝便・仕込み）→ 承認後だけ発注を登録・本部通達の整理・週次店舗レポート。結果は Render UI のグラフ（単位ごと）・表・HTML レポート（共通ルールの差し込みと report_builder.py）。Code Apps の templates/store-ordering と同じ Dataverse。変数は --questions で AskUserQuestion |
| 必要な権限の案内 | 作る・同意する・登録する・公開する・使う人ごとの最小の権限と、利用者の Dataverse ロールの作り方（scaffold 直後に担当者と確認） |
| 異常系・トラブルシュート | 実際に踏んだ失敗と恒久対策 |
| 結果の見せ方（Render UI のグラフ・表・HTML レポート） | 提案するスキル・数字を扱うスキルの出力の標準。差し込む共通ルール display-rules.md・ひな形 report-template.html |
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/custom-mcp-connector.md 8.3 KB
- references/display-rules.md 7.1 KB
- references/permissions.md 5.2 KB
- references/portal-api-automation.md 10 KB
- references/report-template.html 7.1 KB
- references/troubleshooting.md 55 KB
- references/visual-output.md 6.7 KB
- scripts/build_agent_package.ps1 13 KB runs code
- scripts/build_cowork_publish_payloads.py 6.9 KB runs code
- scripts/check_connector_ids.py 6.8 KB runs code
- scripts/check_oauth_signins.py 5.7 KB runs code
- scripts/check_visual_output.py 12 KB runs code
- scripts/diagnose_cowork_connector.py 9.1 KB runs code
- scripts/diagnose_dlp_block.py 3.3 KB runs code
- scripts/get_developer_account.py 4.1 KB runs code
- scripts/install_agent_package_personal.py 9.0 KB runs code
- scripts/manage_agent_package_graph.py 7.5 KB runs code
- scripts/manage_oauth_registration_api.py 19 KB runs code
- scripts/register_mcp_client.py 6.3 KB runs code
- scripts/rehearse_plugin.py 20 KB runs code
- scripts/report_builder.py 29 KB runs code
- scripts/setup_entra_oauth_graph.py 14 KB runs code
- scripts/setup_entra_oauth.ps1 4.9 KB runs code
- scripts/test_check_connector_ids.py 5.6 KB runs code
- scripts/test_check_oauth_signins.py 1.5 KB runs code
- scripts/test_check_visual_output.py 8.3 KB runs code
- scripts/test_manage_agent_package_graph.py 1.5 KB runs code
- scripts/test_manage_oauth_registration_api.py 3.0 KB runs code
- scripts/test_rehearse_plugin.py 2.2 KB runs code
- scripts/test_report_builder.py 7.2 KB runs code
- scripts/test_setup_entra_oauth_graph.py 927 B runs code
- templates/agm-qa-plugin/color.png 3.1 KB
- templates/agm-qa-plugin/manifest.json 2.3 KB
- templates/agm-qa-plugin/outline.png 194 B
- templates/agm-qa-plugin/PERMISSIONS.md 2.4 KB
- templates/agm-qa-plugin/README.md 4.0 KB
- templates/agm-qa-plugin/scaffold.json 4.0 KB
- templates/agm-qa-plugin/scripts/draw_icons.py 3.2 KB runs code
- templates/agm-qa-plugin/skills/agm-qa-authoring/SKILL.md 9.9 KB
- templates/agm-qa-plugin/skills/agm-qa-review/SKILL.md 5.1 KB
- templates/agm-qa-plugin/skills/agm-rehearsal-script/SKILL.md 8.9 KB
- templates/sales-crm-plugin/color.png 1.4 KB
- templates/sales-crm-plugin/dataverse-mcp-tools.json 2.8 KB
- templates/sales-crm-plugin/manifest.json 2.2 KB
- templates/sales-crm-plugin/outline.png 196 B
- templates/sales-crm-plugin/README.md 2.7 KB
- templates/sales-crm-plugin/scaffold.json 2.1 KB
- templates/sales-crm-plugin/skills/manager-blocker-review/SKILL.md 3.8 KB
- templates/sales-crm-plugin/skills/sales-activity-sync/SKILL.md 5.2 KB
- templates/sales-crm-plugin/skills/target-gap-planner/SKILL.md 6.7 KB
- templates/store-assist-plugin/color.png 1.6 KB
- templates/store-assist-plugin/manifest.json 2.3 KB
- templates/store-assist-plugin/outline.png 809 B
- templates/store-assist-plugin/PERMISSIONS.md 1.3 KB
- templates/store-assist-plugin/README.md 4.7 KB
- templates/store-assist-plugin/samples/order-proposal.results.json 10 KB
- templates/store-assist-plugin/scaffold.json 3.6 KB
- templates/store-assist-plugin/scripts/check_skill_queries.py 8.7 KB runs code
- templates/store-assist-plugin/scripts/draw_icons.py 2.9 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.
- 22d ago Changed a553f2cee68e
- 1mo ago Changed · +28 lines 75c0b7e7b089
- 1mo ago Changed · +16 lines 7789ac1c399b
- 1mo ago Changed · +19 lines a4d6eb72db32
- 1mo ago Changed · +8 lines de26304fdc6a
- 1mo ago Changed · +18 lines 45e4fe506c41
- 1mo ago Changed · +60 lines 2c0cc3c0a2df
- 1mo ago Changed · +58 lines ebf696c57a4b
- 2mo ago Changed · +40 lines 5dc38abd3743
- 2mo ago First seen · 447 lines · 116 tokens per session scan A 7bdd366939b7
cowork is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 16,700 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.
cowork compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coworkgeekfujiwara/CodeAppsDevelopmentStandard | Skill | 78 | 2d ago | MIT | A | 116 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |