agent-plugins
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
Agent Plugins for AWS is a library of official AWS plugins for AI coding assistants that package domain expertise, MCP servers, and automation hooks to help developers architect, deploy, and operate on AWS. The collection includes plugins for serverless development, deployment automation, database guidance, full-stack app building with Amplify, location services, AI/ML with SageMaker, and codebase documentation. Each plugin combines structured workflows (agent skills), live data connections (MCP servers), and validation hooks to guide AI assistants through complex AWS tasks without bloating prompts. Supports Claude Code, Codex, and Cursor with experimental Kiro compatibility.
Key Features
Use Cases
- 01Deploy web applications to AWS with automated architecture recommendations and cost estimates
- 02Build full-stack apps using AWS Amplify Gen 2 with guided auth, data, storage, and function workflows
- 03Design and deploy serverless applications with Lambda, API Gateway, EventBridge, and Step Functions
- 04Migrate GCP infrastructure or legacy codebases (COBOL, .NET) to AWS with resource mapping and IaC generation
- 05Add maps, geocoding, routing, and places search to applications using Amazon Location Service
- 06Analyze inherited codebases to generate technical documentation with exact code citations
Related Plugins
View moreandrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
agent-plugins — FAQ
What are Agent Plugins for AWS?+
Agent Plugins for AWS are official AWS building blocks for AI coding assistants (Claude Code, Codex, Cursor) that bundle structured workflows, MCP server connections, and automation hooks to guide agents through AWS architecture, deployment, and operations tasks.
How do I install Agent Plugins for AWS in Claude Code?+
Add the marketplace with `/plugin marketplace add awslabs/agent-plugins`, then install individual plugins like `/plugin install deploy-on-aws@agent-plugins-for-aws`. Requires Claude Code version 2.1.29 or later.
Which AI coding assistants support these plugins?+
Claude Code, Codex, and Cursor are officially supported. Experimental Kiro support is available via a third-party conversion tool that transforms plugins into Kiro format.
Do I need AWS credentials to use these plugins?+
Yes, you need AWS CLI configured with appropriate credentials. Some MCP servers (like aurora-dsql direct database operations) are disabled by default and require explicit enablement.
Are Agent Plugins for AWS free to use?+
The plugins themselves are open-source (Apache 2.0 license) and free. However, AWS resources created through plugin-guided deployments incur standard AWS service charges based on usage.
What is the difference between these plugins and Agent Toolkit for AWS?+
Agent Toolkit for AWS is the official successor with IAM condition keys, CloudWatch/CloudTrail visibility, and validated skills for production use. This repo continues to work and accept contributions, with proven projects migrating to the Toolkit over time.
How do I install agent-plugins?+
Open the source repository on GitHub and follow its README. agent-plugins is a plugin — MCP Agents Market links you directly to the official repo.
Is agent-plugins free?+
agent-plugins is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.