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/almnpx skills add geekfujiwara/CodeAppsDevelopmentStandard --skill almgit 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 | $0.00154 | $0.03804 |
| Opus 5 | $0.00077 | $0.01902 |
| Sonnet 5 | $0.00031 | $0.00761 |
| Haiku 4.5 | $0.00015 | $0.00380 |
Grade A, and why
alm 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ALM（秘匿化・汎用化・CI/CD）共通スキル
コードファースト資産を安全に Git へ載せ、機械判定だけでデプロイまで到達させるための共通基盤。
プロダクト非依存であり、agent365（Foundry エージェント）、code-apps（Code Apps）など
どのスキルからも同じ仕組みで利用できる。デプロイの実処理だけを各プロダクトスキルへ委譲する。
| 原則 | 内容 |
|---|---|
| テンプレートのみコミット | 追跡するのは ${VAR} 入りテンプレートだけ。実値は .env とシークレットストアにのみ存在する |
| 二重の防御 | ローカルは pre-commit（sanitize.py → check_secrets.py）、CI は決定論ゲート（review_sanitization.py） |
| 機械判定 | レビューはルールベース。人手の承認（HITL）を前提にせず、判定を再現可能にする |
| ホスティング非依存 | Git ホスティングとシークレットストアは GIT_PROVIDER / SECRET_BACKEND で差し替える |
| 最小権限 | ワークフローは permissions: を明示。contents: write はリリースジョブだけに許可する |
| 記録はリリースに残す | デプロイ結果とレビュー結果は GitHub Releases（バージョンごと）に残す。Issue には残さない |
| 設定の外出し | パス・許可リスト等は alm.config.json。スクリプト本体はどのリポジトリでも無改変で使う |
前提ツール: Python 3.10+、Git、Azure CLI（
az）。 シークレットストアに応じて GitHub CLI（gh）またはaz extension add --name azure-devopsを追加する。
各プロダクトスキルとの責務分担
| 担当 | 内容 | 参照先 |
|---|---|---|
alm（本スキル） |
秘匿化・汎用化・pre-commit・レビューゲート・承認・リリース記録 | 本ファイル |
agent365 |
Foundry エージェント定義、ブループリント、Teams パッケージ、公開 | agent365 |
code-apps |
Code Apps の実装、npm run deploy などのデプロイ手順 |
code-apps |
standard |
ソリューション運用・環境戦略などの上位ルール | standard |
プロダクトスキル側は「何をデプロイするか」だけを定義し、 「どう秘匿化し、どう検証し、どう承認して記録するか」は本スキルに従う。
スキル同梱スクリプト
テーマリポジトリの scripts/ へそのままコピーして使う（alm_config.py を必ず一緒に置く）。
| スクリプト | 用途 | 実行場所 |
|---|---|---|
| scripts/alm_config.py | alm.config.json の読み込み（他スクリプトが import） |
- |
| scripts/sanitize.py | 実値入りファイルを ${VAR} 化し、シークレットストアへ同期 |
pre-commit |
| scripts/check_secrets.py | ステージ済み差分への実値混入を検査 | pre-commit |
| scripts/render.py | テンプレートの ${VAR} を環境変数で解決 |
ローカル / CI |
| scripts/review_sanitization.py | 秘匿化・汎用化の決定論レビューゲート | CI（必須チェック） |
| scripts/gate_rules.py | 品質 / 汎用性 / セキュリティ / 可読性 / リリース判定のルールエンジン | CI（各ゲート） |
| scripts/review_report.py | 各ゲートの判定を 1 枚のレビュー結果表に統合 | CI（レポート） |
What ships with it
13 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.
- alm.config.example.json 756 B
- references/.env.example 1.7 KB
- references/ci-providers.md 9.6 KB
- references/repo-scaffold.md 5.0 KB
- references/review-gates.md 16 KB
- references/troubleshooting.md 4.2 KB
- scripts/alm_config.py 4.2 KB runs code
- scripts/check_secrets.py 3.2 KB runs code
- scripts/gate_rules.py 17 KB runs code
- scripts/render.py 3.1 KB runs code
- scripts/review_report.py 3.9 KB runs code
- scripts/review_sanitization.py 4.0 KB runs code
- scripts/sanitize.py 9.9 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.
- 2d ago First seen · 216 lines · 154 tokens per session scan A a06590ca567c
alm is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (59 stars, last pushed 5d ago), licensed MIT. It adds 154 tokens to every session and 3,804 once invoked, about $0.0008 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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.