본문으로 건너뛰기
aws-samples · AgenticOps
Tech Previewv0.2.0-preview.1 — API may change before GA. See the support policy.

Autonomous operations
for the AWS AIDLC loop.

Extend Claude Code and Kiro with AgenticOps plugins and skills. OMA closes the loop between design, construction, and operations — humans approve at checkpoints, agents execute everything in between.

Plugins
5
Tier-0 workflows
8
AWS MCP servers
11 pinned

$ claude --use-plugin oma

Initializing OMA AgenticOps plugin…

✔ Identity context synced with AWS

✔ MCP servers pinned (eks 0.1.28, cloudwatch 0.0.25, …)

✔ Skills: autopilot-deploy, self-improving-loop, cost-governance

Claude > "How can I help you today?"

$ deploy rag-qa-agent:v2.3.1 to staging

OMA · intercepting · analyzing budget, SLOs, and eval baselines before rollout…

Seamless integration

OMA isn't a separate tool; it's the operational brain inside your favorite AI coding agents.

Claude Code plugin

Ship as a native Claude Code marketplace entry. Slash commands, keyword triggers, and the AWS hosted MCP layer work out of the box.

Kiro skills

install/kiro.sh symlinks every skill into ~/.kiro/skills/ and wires kiro-agents profiles with pinned MCP server versions.

Shared .omao state

Tier-0 mode, project memory, and audit logs live in .omao/. Both harnesses read and write the same directory — switch without losing context.

The AI Development Lifecycle (AIDLC) loop

  1. 1

    Inception

    Structured intake, requirements, user stories, and workflow planning. Every artifact is the contract Construction will honor.

  2. 2

    Construction

    Component design, code generation with human-approved gates, risk discovery across 12 categories, and TDD for agentic systems.

  3. 3

    Operations

    Autopilot deploys, continuous eval, incident response, cost governance, and the self-improving loop that feeds learnings back into Construction.

AgenticOps capabilities

Purpose-built for the autonomous era.

Autopilot deploys

autopilot-deploy runs canary 1% → 10% → 50% → 100% with SLO-gated circuit breakers. Each stage waits for continuous-eval before promotion; regression trips auto-rollback.

  • Argo Rollouts / Flagger
  • Prometheus SLO gates
  • Human approval at 100%

Self-healing

incident-response classifies SEV1–4, pulls the matching runbook, issues diagnostic MCP queries, and drafts a remediation script for approval. SEV1 pages on-call; it never acts.

Cost governance

cost-governance attributes spend per agent, vetoes deploys that would breach the monthly ceiling, and drafts Opus → Sonnet → Haiku downgrade PRs. budget.yaml runs in a simpleeval sandbox — no Python eval, no RCE vector.

CLI first. Always.

Every skill is reachable as a slash command in Claude Code or a direct skill call in Kiro. The full state lives under .omao/ and is portable between harnesses.

> /plugin marketplace add https://github.com/aws-samples/sample-oh-my-aidlcops> /plugin install agentic-platform agenticops modernization> /oma:platform-bootstrap  [1/5] Gather Context  …  ok  [2/5] Pre-flight      …  ok

Five plugins

Install only what you need — or all of them with one marketplace command.

agentic-platformBuild the platform

EKS + vLLM + Inference Gateway + Langfuse. Skills for bootstrap, GPU planning, routing, observability, and guardrails. MCP servers pinned to exact PyPI versions — no @latest.

agenticopsOperate with agents

self-improving-loop, autopilot-deploy, incident-response, continuous-eval, cost-governance, audit-trail. Humans approve, agents execute.

aidlc-inceptionPhase 1 — intent

structured-intake, requirements-analysis, user-stories, workflow-planning. Produces the artifacts Construction consumes as a single source of truth.

aidlc-constructionPhase 2 — build

component-design, code-generation, test-strategy, risk-discovery, quality-gates. LLM calls are mocked in tests; golden evals gate every merge.

modernizationLegacy → AWS

workload-assessment, modernization-strategy (6R), to-be-architecture, containerization, cutover-planning. Uses Kiro-style stage-gated progression.

Secure by default

Ship-ready, not just demo-ready.

  • MCP versions pinned

    Every .mcp.json and agent profile references awslabs MCP servers by exact PyPI version. No @latest supply-chain surprises.

  • Read-only EKS MCP

    The Kiro agent profile does not enable --allow-write or --allow-sensitive-data-access by default; opt in explicitly.

  • Least-privilege IAM

    langfuse-observability uses a bucket-scoped customer-managed policy. AmazonS3FullAccess is called out as a Bad Example.

  • Sandboxed expressions

    cost-governance evaluates budget.yaml rules with simpleeval. Python eval() on user-editable config is a documented RCE vector.

  • Session state stays local

    .omao/state, .omao/plans, .omao/logs, audit-trail output, and project memory are gitignored. Verbatim prompts never leave the machine.

  • Safe JSON hooks

    session-start.sh requires jq or python3 and refuses to emit shell-interpolated JSON, preventing state-file injection into context.

Ready to automate your AWS AIDLC?

Clone the repo, run one install script, and start with a Tier-0 workflow that fits your team.