By aws-samples
Investigate incidents, optimize costs, review architecture, and map topology with the AWS DevOps Agent — fully integrated into Claude Code via MCP, with skills that auto-route incidents to the right workflow.
Open a chat session with the AWS DevOps Agent and ask a question
Ask the AWS DevOps Agent for cost optimization opportunities, scoped to your local IaC
Start a deep root-cause investigation on the AWS DevOps Agent and stream progress
List configured AgentSpaces and summarize each one's accounts and runbooks
Have a fast, conversational analysis with the AWS DevOps Agent. Use for cost optimization, architecture review, topology mapping, knowledge / runbook discovery, security audits, dependency questions, and quick diagnostics — anything that needs a 2-10 second answer rather than a 5-8 minute deep investigation. Trigger words include cost, optimize, review, architecture, topology, what runbooks, show me, compare, audit, what if.
Run a deep root-cause investigation on the AWS DevOps Agent. Use when the user describes an incident, alarm, outage, or unexplained behavior — keywords like "5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "investigate", "root cause", "debug", "alarm fired", "service down". Polls and streams progress, then surfaces recommendations.
Coordinate the AWS DevOps Agent across multiple AgentSpaces from one Claude Code session — route questions to the right space (prod vs staging vs knowledge), query several spaces in parallel and synthesize, or compare findings across accounts. Use whenever the user has more than one AgentSpace configured, mentions multiple AWS accounts, or asks something like "check both prod and staging", "compare across accounts", or "ask the knowledge space".
First-time setup of the AWS DevOps Agent for Claude Code — install the binary, configure AWS profiles for one or more AgentSpaces, discover space IDs, write the local routing guide, and verify the MCP server starts. Use when the user says "set up devops agent", "configure agent spaces", "I have multiple AWS accounts", or you detect that credentials / spaces are missing.
External network access
Connects to servers outside your machine
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.
You are enhanced with the AWS DevOps Agent, an AI-powered operational intelligence system for AWS environments. You access it through the AWS MCP Server using aws___call_aws for standard API operations and aws___run_script for streaming APIs (like SendMessage).
Your superpower: You can combine your local workspace knowledge (files, git, skills, terminal) with the DevOps Agent's cloud knowledge (CloudWatch, X-Ray, IAM, topology) by packing local context into API call parameters. This makes you far more effective than either system alone.
The aws-devops-agent plugin gives Claude Code:
aws___call_aws, aws___run_script, and more) for accessing the AWS DevOps Agent API — investigations, chat, recommendations, AgentSpaces, journal records.investigate — incident root cause (deep, 5–8 min, streamed progress)chat — cost / architecture / topology / knowledge (instant)multi-space — coordinate across multiple AgentSpaces in one sessionsetup — first-time configuration of profiles, spaces, and routing/aws-devops-agent:chat, /aws-devops-agent:investigate, /aws-devops-agent:spaces, /aws-devops-agent:cost.plugins/aws-devops-agent/examples/multi-space-walkthrough.md.Prerequisite: uv must be on PATH (the AWS MCP Server is fetched via uvx).
# Install uv if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh
# Verify the MCP proxy works (fetches on first run)
uvx mcp-proxy-for-aws@latest --help
Then in Claude Code:
/plugin marketplace add aws-samples/sample-aws-devops-agent-claude-plugin
/plugin install aws-devops-agent@aws-devops-tools
/reload-plugins
# In your shell, before launching Claude Code:
export AWS_PROFILE=<your-aws-profile>
aws sso login # or: aws configure
Then in Claude Code:
aws___call_aws(cli_command="aws devops-agent list-agent-spaces --region us-east-1") — should return your spaces.investigate skill.chat./aws-devops-agent:spaces — list your AgentSpaces explicitly.If you have more than one AgentSpace (e.g. prod, staging, knowledge), say "set up the devops agent for multiple accounts" and the setup skill walks you through per-space AWS profiles, shell wrappers, and a routing guide. The worked walkthrough at plugins/aws-devops-agent/examples/multi-space-walkthrough.md shows the end-to-end pattern: prod investigation + staging comparison + knowledge-space runbook lookup, all from one Claude Code session.
.
├── .claude-plugin/
│ └── marketplace.json # this catalog
├── plugins/
│ └── aws-devops-agent/ # the plugin
│ ├── .claude-plugin/plugin.json
│ ├── .mcp.json # AWS MCP Server config (uvx mcp-proxy-for-aws)
│ ├── skills/ # auto-invoked workflows
│ │ ├── investigate/
│ │ ├── chat/
│ │ ├── multi-space/
│ │ └── setup/
│ ├── commands/ # user-invoked slash commands
│ └── examples/ # worked walkthroughs
└── README.md # this file
Test the plugin without publishing:
git clone <this-repo> claude-aws-devops-agent
claude --plugin-dir ./claude-aws-devops-agent/plugins/aws-devops-agent
Or load the whole marketplace:
/plugin marketplace add ./claude-aws-devops-agent
/plugin install aws-devops-agent@aws-devops-tools
After editing skills or commands, run /reload-plugins to pick up changes.
Validate before pushing:
claude plugin validate ./claude-aws-devops-agent
PRs welcome. Skills should keep their description frontmatter sharp — that's what the model uses to decide whether to auto-invoke. If you add a skill, also add a one-row entry to plugins/aws-devops-agent/README.md.
MIT-0. See LICENSE.
npx claudepluginhub aws-samples/sample-aws-devops-agent-claude-plugin --plugin aws-devops-agentPrompt 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
AIDLC Operations phase automation — self-improving loops, autonomous deploys, continuous evaluation, incident response, and cost governance on AWS. Humans approve at checkpoints; agents execute diagnosis, proposal, and remediation between gates.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.