By aws-samples
Automate AIDLC operations on AWS: execute self-improving loops via continuous trace evaluation and PR proposals, run 4-stage canary deployments on Kubernetes with SLO gates and human approvals, handle incident response from alarms, enforce cost budgets with model recommendations, and log audits for compliance.
모든 사용자 발화·agent 행동·phase 전환·gate 판정을 ISO 8601 타임스탬프와 함께 감사 로그에 기록한다. 사용자 입력은 축약·요약 없이 verbatim blockquote로 보존하며, SOC2·ISMS-P 감사 요구사항에 매핑되는 보존 정책(30·90·365일)을 프로젝트별로 선택한다. 모든 AIDLC skill이 호출 가능한 공통 감사 계층을 제공한다.
Agent 또는 skill의 프로덕션 배포를 canary 1% → 10% → 50% → 100% 4단계로 자동 진행한다. 각 단계는 continuous-eval 통과와 SLO 준수를 gate로 하며 circuit breaker가 SLO 위반을 감지하면 즉시 이전 단계로 자동 롤백한다. 100% 승격은 사람 승인이 필수다.
Ragas 기반 품질·안전 평가를 매 배포 직후와 매 1시간 cron으로 실행하여 faithfulness, answer relevance, context precision, toxicity, PII leakage 지표를 측정한다. Golden dataset 관리와 regression gate(baseline 대비 5%p 하락 시 차단)를 수행하며 autopilot-deploy의 canary gate에 사용된다.
AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다. 월간 예산 ceiling을 초과할 것으로 예상되는 배포는 veto하여 autopilot-deploy의 pre-flight gate로 작동한다.
CloudWatch/Prometheus 알람을 수신하여 severity 분류, runbook 조회, hypothesis 생성, 진단 MCP 쿼리, 사람 승인 기반 remediation 수행까지 자동화한다. SEV1은 즉시 on-call 호출, SEV2/3은 agent가 drafted response를 준비한 뒤 사람 승인 후 실행한다.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AIDLC × AgenticOps — a plugin marketplace that automates the full AI-Driven Development Lifecycle with agent-based operations on AWS.
한국어 README · Documentation · Plugins · Steering
oh-my-aidlcops (OMA) is the sibling project of
oh-my-claudecode (OMC).
Where OMC orchestrates generic Claude Code workflows, OMA specializes in the
AIDLC loop: Inception → Construction → Operations.
The thesis: AIDLC is complete only when operations are agent-automated. OMA fuses the AWS-official AIDLC workflows with an AgenticOps layer (self-improving feedback loops, autonomous deploys, continuous evaluation, incident response, cost governance) so the lifecycle closes itself without human execution at every step.
| Plugin | What it does | Example skills |
|---|---|---|
agentic-platform | Build & run the Agentic AI Platform on EKS | agentic-eks-bootstrap, vllm-serving-setup, inference-gateway-routing, langfuse-observability, gpu-resource-management, ai-gateway-guardrails |
agenticops | Operate it with agents | self-improving-loop, autopilot-deploy, incident-response, continuous-eval, cost-governance, audit-trail |
aidlc-inception | AIDLC Phase 1 extensions | structured-intake, requirements-analysis, user-stories, workflow-planning |
aidlc-construction | AIDLC Phase 2 extensions | component-design, code-generation, test-strategy, risk-discovery, quality-gates |
modernization | Legacy workload modernization to AWS (6R strategy) | workload-assessment, modernization-strategy, to-be-architecture, containerization, cutover-planning |
OMA inherits the Tier-0 pattern from OMC — high-leverage workflows you invoke once and let run, with human approval only at checkpoints.
| Command | Purpose |
|---|---|
/oma:autopilot | Full AIDLC loop autopilot (Inception → Construction → Operations) |
/oma:aidlc-loop | Single-feature AIDLC one-pass |
/oma:agenticops | Operations mode (continuous-eval + incident-response + cost-governance) |
/oma:self-improving | Feedback loop — Langfuse traces to skill/prompt improvement PR |
/oma:platform-bootstrap | 5-checkpoint Agentic AI Platform build on EKS |
/oma:modernize | Legacy workload modernization (6R decision → cutover) |
/oma:review | AIDLC artifact review (ADR, spec, design, PR) |
/oma:cancel | Terminate active Tier-0 mode |
install.sh downloads the pinned release tarball, extracts to ~/.oma, and
symlinks ~/.local/bin/oma. oma setup then writes a project profile,
seeds the ontology, installs the plugins, and runs oma doctor to confirm
the environment.
curl -fsSL https://raw.githubusercontent.com/aws-samples/sample-oh-my-aidlcops/v0.2.0-preview.1/install.sh | bash
cd my-project
oma setup
oma doctor
See the Easy Button docs
for what oma setup writes, how the 12 doctor probes work, and how the
ontology + harness DSL get enforced at runtime.
Tech Preview notice —
v0.2.0-preview.1stabilizesprofile.yamlv1 and the 6 ontology schemas. Everything else (CLI UX, DSL fields, doctor report shape) may evolve before GA. See Support Policy.
claude
Inside the Claude Code session:
/plugin marketplace add https://github.com/aws-samples/sample-oh-my-aidlcops
/plugin install agentic-platform@oh-my-aidlcops
/plugin install agenticops@oh-my-aidlcops
/plugin install aidlc-inception@oh-my-aidlcops
/plugin install aidlc-construction@oh-my-aidlcops
/plugin install modernization@oh-my-aidlcops
/plugin list
/plugin installaccepts a single plugin id per invocation. Pasting the six lines above lets Claude Code run them sequentially. For a shell one-liner, useclaude <<'EOF' ... EOFto feed the commands via stdin.
git clone https://github.com/aws-samples/sample-oh-my-aidlcops
bash sample-oh-my-aidlcops/scripts/install/claude.sh
Prompt optimization skills for Amazon Nova 1 and Nova 2. Provides /nova1-prompt and /nova2-prompt — rewrite or migrate a prompt for a specific Nova generation with the correct inference config, formatting rules, and (for Nova 2) multimodal caveats.
Healthcare and Life Sciences domain skills and MCP tools — genomics, drug discovery, clinical trials, biomarker analysis, medical terminology, and more. Use with the AWS Agent Toolkit for full agent build-and-deploy workflows.
AWS Spark Analysis plugin for Claude Code - troubleshoot Spark workloads on AWS Glue, EMR, and EMR Serverless
Two Claude Code skills for EKS Auto Mode: onboarding guide for newcomers and maintenance playbook for repo maintainers
Legacy workload modernization to AWS — 6R strategy (Rehost/Replatform/Refactor/Repurchase/Retire/Retain), workload assessment, to-be architecture (ECS/EKS/Serverless), containerization (multi-stage, multi-arch, non-root), and cutover planning (Blue-Green, Canary, Rolling). Adapted from aws-samples/sample-ai-driven-modernization-with-kiro (MIT-0).
npx claudepluginhub aws-samples/sample-oh-my-aidlcops --plugin agenticopsBuild, deploy, and operate applications on AWS. Skills to author infrastructure-as-code, use core services, and complete common tasks.
Cloud infrastructure agents — cloud, container, SRE specialists
Use this agent when setting up CI/CD pipelines, configuring cloud infrastructure, implementing monitoring systems, or automating deployment processes. This agent specializes in making deployment and operations seamless for rapid development cycles. Examples:\n\n<example>\nContext: Setting up automated deployments\nuser: "We need automatic deployments when we push to main"\nassistant: "I'll set up a complete CI/CD pipeline. Let me use the devops-automator agent to configure automated testing, building, and deployment."\n<commentary>\nAutomated deployments require careful pipeline configuration and proper testing stages.\n</commentary>\n</example>\n\n<example>\nContext: Infrastructure scaling issues\nuser: "Our app crashes when we get traffic spikes"\nassistant: "I'll implement auto-scaling and load balancing. Let me use the devops-automator agent to ensure your infrastructure handles traffic gracefully."\n<commentary>\nScaling requires proper infrastructure setup with monitoring and automatic responses.\n</commentary>\n</example>\n\n<example>\nContext: Monitoring and alerting setup\nuser: "We have no idea when things break in production"\nassistant: "Observability is crucial for rapid iteration. I'll use the devops-automator agent to set up comprehensive monitoring and alerting."\n<commentary>\nProper monitoring enables fast issue detection and resolution in production.\n</commentary>\n</example>
DevOps, cloud, and deployment specialists - Kubernetes, Terraform, AWS, Azure, GCP, and SRE
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
Enhances web_search Skill by researching best practices and deploying infrastructure automatically