agentmods.dev

CodeAppsDevelopmentStandard: Skill for Claude Code

.github/skills/foundry-autopilot/SKILL.md

foundry-autopilot is a skill for Claude Code, Codex from geekfujiwara/CodeAppsDevelopmentStandard. It costs 231 tokens per session (21,562 once invoked), scanned A, original, MIT.

A deployment guide for publishing a Microsoft Foundry hosted agent as an Agent 365 Autopilot, so it can appear as a digital colleague in Teams and Microsoft 365 Copilot. It also describes an alternative self-hosted App Service route and the setup of evaluation tools.

In plain words
What is it for?
Use it to scaffold and publish an agent, connect it to Microsoft 365 conversations, configure evaluation and monitoring, and choose between hosted and self-hosted deployment.
Why use it?
It helps avoid incompatible deployment paths, authentication failures, and unsafe handling of secrets or external data. It also distinguishes standard Autopilot use from cases needing custom runtime control.

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 runs a file that does not travel with it, so clone the repository first. The line is python scripts/scaffold_ai_teammate.py --decisions decisions.json --env .env --target ..

not rated 78repo +3 changed 10d ago A scan 231 tokens original MIT
View source ↗ geekfujiwara/CodeAppsDevelopmentStandard
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/foundry-autopilot/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 foundry-autopilot

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/foundry-autopilot"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/foundry-autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 231 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 21,562 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.
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 $0.00231 $0.21562
Opus 5.5 $0.00092 $0.08625
Sonnet 5.5 $0.00046 $0.04312
Haiku 4.5 $0.00023 $0.02156

Measured 10d ago against content hash 9b08a6f263f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundry-autopilot 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agent_template_browser_runner.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/foundry-autopilot/SKILL.md · 840 lines

How it starts

The opening of the file, as written. The whole thing — 840 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

Foundry hosted agent を Agent 365 Autopilot として発行し、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。評価Hub、Python EvaluationWorker、Foundry Monitor/Evaluations まで初回 scaffold / publish の標準範囲に含める。 初回の Azure 基盤は新規 Foundry アカウント・プロジェクト・ACR をパブリックエンドポイントで作成する。 公開は匿名アクセスではなく Entra ID / Managed Identity 認証。既存 Azure リソースは流用しない。 格納先のリソースグループだけは新規作成／既存利用を本人に確認し、全 Azure 資産をその1つへ集約する。 構築済みの非公開設定や組織ポリシーは変更しない。

agentUser を持たせる経路は 2 つある。 既定は Foundry Autopilot（hire したインスタンスごとに agent user アカウントが払い出される。Frontier preview が前提） → references/foundry-autopilot.md。 App Service 自己ホストは、独自ランタイム制御が必要な場合の互換経路として残す。

旧来の「Foundry の activityprotocol を Azure Bot に直結する方式」は使わない。 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）。 参考情報としてのみ references/foundry-hosted-bot.md に隔離する。

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。

必須ルーティング・完了契約

  • AI teammate / AIチームメイト / AI チームメイト / Agent Template / Foundry Autopilot の依頼では本スキルを必ず読む。 明示的な自己ホスト要件がなければ hosting: "foundry-autopilot" を decisions JSON に明記し、 references/foundry-autopilot.md の手順と scripts/publish_foundry_autopilot.py --check → --execute を使う。 汎用 scripts/deploy.py や SDK の agents.create_version だけで Agent template を発行したことにしない。
  • 明示的な Agent Template / Autopilot 要求でプレビュー参加・ライセンス・権限・対応リージョンなどの 前提が不足／未確認なら停止する。 不足と必要な担当者を報告し、通常 Agent・共有 bot・自己ホストへ 自動で切り替えない。自己ホスト要件はサポートする別経路であり、経路変更には利用者の明示的な合意が必要。
  • Autopilot は 同じ agent version の digital_worker_type=m365 と、その応答の blueprint.client_id に結び付く agenticUserTemplate.AgentIdentityBlueprintId を用い、 publishAsAutopilot=true・useAgenticUserTemplate=true・agenticUserTemplate を揃えて発行する。
  • HTTP 200、通常の Registry 行、teamsAppId / titleId の取得だけでは完了しない。 M365 管理センター Requests の対象行の Type = Agent template を手動確認し、承認後に Teams の Agents for your team から採用（hire）でき、agent user が払い出されることを確認してから完了とする。 カタログ登録までの依頼でも Type を確認し、採用未確認なら「登録済み・採用未確認」と報告する。 UI を確認できない場合は承認待ち／採用待ちとして止め、推測の read-back API で代用しない。
  • --container-only は既存の検証済み Agent template のコード更新だけ。 初回発行、Type 未確認、通常 Agent の修復には使わず、完全な発行と UI 検証を行う。 確認済みの場合も --confirm-existing-template を明示する。生成 deploy.ps1 は既定で完全発行し、 コードのみ更新する場合だけ -ContainerOnly -ConfirmExistingTemplate を指定する。 build_teams_package.py も Agent template を必須とし、blueprint 不足時の共有 Agent への降格は行わない。

Read the full file on GitHub · 840 lines

Files

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.

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 · +10 lines 9b08a6f263f6
  2. 11d ago Changed · +1 lines ed55e9b2d321
  3. 20d ago Changed · +55 lines · +15 tokens per session 79243fe108d2
  4. 28d ago First seen · 774 lines · 216 tokens per session scan A 5e5c4005f83f

Subscribe to this mod's changes

foundry-autopilot is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 231 tokens to every session and 21,562 once invoked, about $0.0009 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 2026-10-09.

Building agentsCloudDevOps and cloudautomation
Related

foundry-autopilot compared with skills from other repositories

foundry-autopilot next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
foundry-autopilotgeekfujiwara/CodeAppsDevelopmentStandardSkill78yesterdayMITA231Claude Code, Codex
gke-compute-classesgoogle/skillsSkill22kyesterdayApache-2.0A83Claude Code, Codex
gke-reliabilitygoogle/skillsSkill22kyesterdayApache-2.0A85Claude Code, Codex
gke-workload-securitygoogle/skillsSkill22kyesterdayApache-2.0A171Claude Code, Codex
cloud-architectJeffallan/claude-skillsSkill12k7d agoMITA71Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code