Borrowing it
Nothing to install: this file belongs to yoshimi-I/ai-engineer-teams. 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/yoshimi-I/ai-engineer-teams/main/.kiro/skills/delivery-pipeline/SKILL.mdgit clone --depth 1 https://github.com/yoshimi-I/ai-engineer-teamsWrote 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/yoshimi-i/ai-engineer-teams/delivery-pipeline)<a href="https://agentmods.dev/skills/yoshimi-i/ai-engineer-teams/delivery-pipeline"><img src="https://agentmods.dev/badge/skills/yoshimi-i/ai-engineer-teams/delivery-pipeline/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/yoshimi-i/ai-engineer-teams/delivery-pipeline"><img src="https://agentmods.dev/badge/skills/yoshimi-i/ai-engineer-teams/delivery-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.01683 |
| Opus 5 | $0.00000 | $0.00842 |
| Sonnet 5 | $0.00000 | $0.00337 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
delivery-pipeline 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 12d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Pipeline — コードからユーザーが使える状態まで
いつ使うか
- INCEPTION でissueを生成する時
- implement エージェントが「完了」を判断する時
- review エージェントがマージ可否を判断する時
原則
「PRがマージされた」≠「完了」。ユーザーがアクセスできて初めて完了。
完了の定義 (Definition of Done)
機能が「完了」と見なされるには、以下の全てを満たす必要がある:
- ✅ コードが実装されている
- ✅ テストが書かれ、通っている
- ✅ CIが通っている（lint, typecheck, test, build）
- ✅ レビューが承認されている
- ✅ mainにマージされている
- ✅ デプロイパイプラインが存在し、マージ後に自動デプロイされる
- ✅ デプロイ先の環境でアクセス可能である
開発フロー全体像
INCEPTION
↓
Phase 0: 基盤構築（2トラック並行）
├── トラックA: アプリ基盤
│ ├── scaffold (frontend / backend / shared)
│ ├── justfile with dev recipe
│ ├── CI パイプライン (lint + typecheck + test + build)
│ └── .env.example + config loader
├── トラックB: インフラ・デプロイ基盤（即着手）
│ ├── GitHub OIDC for AWS
│ ├── VPC + networking (Terraform)
│ ├── Database (RDS/Aurora)
│ ├── Compute (ECS/Lambda)
│ ├── ALB + DNS
│ ├── Dockerfile (scaffold完了後)
│ ├── Docker build + ECR push (CI)
│ └── Staging deploy workflow
└── 合流: トラックA の Dockerfile + トラックB のインフラ → CD 完成
↓
Phase 1: Walking Skeleton
├── /health エンドポイント → staging デプロイ → E2E
└── ここで「コード→デプロイ」の全経路が開通
↓
Phase 2: 機能実装（デプロイ経路は既に開通済み）
├── ドメインモデル / スキーマ
├── API エンドポイント
├── フロントエンド UI
└── 統合テスト / E2E
↓
Phase 3: デリバリー
├── production IaC + deploy
└── ユーザーアクセス確認
なぜインフラを最初から並行するか
Terraform は初回 apply で高確率でエラーが出る:
- IAM ポリシー不足
- リソースクォータ制限
- リージョン固有の制約
- ネットワーク設定ミス
機能実装が終わってからインフラに着手すると、ここで詰まって全体が止まる。 最初から並行して走らせ、エラーを早期に潰すのが正しい戦略。
Phase 0 で生成すべきissue（INCEPTIONで必須）
トラックA: CI（Continuous Integration）
| issue | 内容 | 依存 |
|---|---|---|
ci: add linter and formatter |
oxlint/biome/eslint + CI ワークフロー | scaffold 後 |
ci: add typecheck and test |
tsc --noEmit + vitest/jest + CI ジョブ | linter 後 |
ci: add build verification |
pnpm build が通ることを CI で検証 | typecheck 後 |
トラックB: インフラ（IaC）— scaffold を待たず即着手
| issue | 内容 | 依存 |
|---|---|---|
infra: configure GitHub OIDC |
GitHub Actions → AWS の認証設定 | なし（最初に作る） |
infra: provision VPC + networking |
VPC/Subnet/SG | なし |
infra: provision database |
RDS/Aurora + セキュリティグループ | VPC 後 |
infra: provision compute |
ECS/Lambda + タスク定義 | VPC 後 |
infra: provision ALB + DNS |
ALB/CloudFront/Route53 | compute 後 |
infra: configure secrets |
Secrets Manager / SSM Parameter Store | なし |
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.
- 12d ago First seen · 144 lines · 0 tokens per session scan A 586376c33a57
delivery-pipeline is a skill published in the GitHub repository yoshimi-I/ai-engineer-teams (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,683 tokens. 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 2026-08-31.
Other skills, from other repositories
openobserve-telemetry
Instruments AWS serverless projects (API Gateway, Lambda, DynamoDB) to send full OpenTelemetry data — traces, metrics, and logs — to the shared OpenObserve instance on this account. Covers ADOT Lambda layer setup, OTLP endpoint (derived live from CloudFormation) and auth (single SSM SecureString parameter), API…
cognito-passkey-auth
Amazon Cognito — Custom UI with Passkeys, Social Login & Face ID. Reference skill (loaded via skill:// from the ios agent).
amazon-location-service
Amazon Location Service. Reference skill (loaded via skill:// from the ios agent).
amazon-polly-generative
Amazon Polly Generative Voices. Reference skill (loaded via skill:// from the ios agent).
amazon-bedrock
Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore. Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, troubleshooting Bedrock…
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.