[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75753":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":16,"starSnapshotCount":16,"syncStatus":33,"lastSyncTime":34,"discoverSource":35},75753,"agent-plugins","awslabs\u002Fagent-plugins","awslabs","Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.",null,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins","Shell",780,114,7,13,0,4,15,93,12,10.18,false,"main",[25,26,27,28,5,29],"agent-skills","agents","coding-agent-skills","coding-agents","aws","2026-06-12 02:03:35","# Agent Plugins for AWS\n\n_Read this in other languages: [日本語](README.jp.md)_\n\n> [!IMPORTANT]\n> Generative AI can make mistakes. You should consider reviewing all output and costs generated by your chosen AI model and agentic coding assistant. See [AWS Responsible AI Policy](https:\u002F\u002Faws.amazon.com\u002Fai\u002Fresponsible-ai\u002Fpolicy\u002F).\n\n## What's new\n\n> [!TIP]\n> The [Agent Toolkit for AWS](https:\u002F\u002Faws.amazon.com\u002Fabout-aws\u002Fwhats-new\u002F2026\u002F05\u002Fagent-toolkit\u002F) is now live! The Agent Toolkit for AWS is the successor to the MCP servers, plugins, and skills available on AWS Labs, and was informed by feedback from customers like you. If you're building production software using coding agents or building agents for your own customers, we recommend Agent Toolkit for AWS. It includes IAM condition keys to distinguish agent actions from human ones, CloudWatch and CloudTrail visibility, and skills that have been evaluated for accuracy and effectiveness. This repo continues to work and accept contributions. Over time, the most useful projects here will move into Agent Toolkit for AWS.\n\n---\n\n## Agent Plugins for AWS\n\nAgent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS. Agent plugins are currently supported by Claude Code, Codex, and Cursor.\n\nAI coding agents are increasingly used in software development, helping developers write, review, and deploy code more efficiently. Agent skills and the broader agent plugin packaging model are emerging as best practices for steering coding agents toward reliable outcomes without bloating model context. Instead of repeatedly pasting long AWS guidance into prompts, developers can now encode that guidance as reusable, versioned capabilities that agents invoke when relevant. This improves determinism, reduces context overhead, and makes agent behavior easier to standardize across teams. Agent plugins act as containers that package different types of expertise artifacts together. A single agent plugin can include:\n\n- Agent skills – Structured workflows and best-practice playbooks that guide AI through complex tasks like deployment, code review, or architecture planning. Agent skills encode domain expertise as step-by-step processes.\n- MCP servers – Connections to external services, data sources, and APIs. MCP servers give your assistant access to live documentation, pricing data, and other resources at runtime. Learn more about [MCP servers for AWS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp).\n- Hooks – Automation and guardrails that run on developer actions. Hooks can validate changes, enforce standards, or trigger workflows automatically.\n- References – Documentation, configuration defaults, and knowledge that the agent skill can consult. References make agent skills smarter without bloating the prompt.\n\nAs new types of expertise artifacts emerge in this space, they can be packaged into agent plugins, making the evolution transparent to developers.\n\n## Best practices\n\nTo maximize the benefits of plugin-assisted development while maintaining security and code quality, follow these essential guidelines:\n\n- Always review generated code before deployment (for example, against your constraints for security, cost, resilience)\n- Use plugins as accelerators, not replacements for developer judgment and expertise.\n- Keep plugins updated to benefit from the latest AWS best practices.\n- Follow the principle of least privilege when configuring AWS credentials.\n- Run security scanning tools on generated infrastructure code.\n\n## Plugins\n\n| Plugin                          | Description                                                                                                                                                                                             | Status                                |\n| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------- |\n| **amazon-location-service**     | Add maps, geocoding, routing, places search, and geospatial features to applications with Amazon Location Service                                                                                       | Available                             |\n| **aws-amplify**                 | Build full-stack apps with AWS Amplify Gen 2 using guided workflows for auth, data, storage, and functions                                                                                              | Available                             |\n| **aws-serverless**              | Build serverless applications with Lambda, API Gateway, EventBridge, Step Functions, and durable functions                                                                                              | Available                             |\n| **aws-transform**               | Migrate, modernize, and upgrade codebases to AWS — .NET to .NET 8\u002F10, mainframe COBOL to Java, VMware to EC2, SQL Server to Aurora, and language\u002FSDK upgrades                                           | Available                             |\n| **codebase-documentor-for-aws** | Analyze AWS-deployed services and codebases to generate structured technical documentation with source-of-truth citations                                                                               | Available                             |\n| **databases-on-aws**            | Database guidance for the AWS database portfolio — schema design, queries, migrations, and multi-tenant patterns                                                                                        | Some Services Available (Aurora DSQL) |\n| **deploy-on-aws**               | Deploy applications to AWS with architecture recommendations, cost estimates, and IaC deployment                                                                                                        | Available                             |\n| **sagemaker-ai**                | Build, train, and deploy AI models with deep AWS AI\u002FML expertise brought directly into your coding assistants, covering the surface area of [Amazon SageMaker AI](https:\u002F\u002Faws.amazon.com\u002Fsagemaker\u002Fai\u002F) | Available                             |\n\n## Installation\n\n### Claude Code\n\n#### Add the marketplace\n\n```bash\n\u002Fplugin marketplace add awslabs\u002Fagent-plugins\n```\n\n#### Install a plugin\n\n```bash\n\u002Fplugin install amazon-location-service@agent-plugins-for-aws\n```\n\nor\n\n```bash\n\u002Fplugin install aws-amplify@agent-plugins-for-aws\n```\n\nor\n\n```bash\n\u002Fplugin install aws-serverless@agent-plugins-for-aws\n```\n\nor\n\n```bash\n\u002Fplugin install codebase-documentor-for-aws@agent-plugins-for-aws\n```\n\nor\n\n```bash\n\u002Fplugin install databases-on-aws@agent-plugins-for-aws\n```\n\nor\n\n```bash\n\u002Fplugin install deploy-on-aws@agent-plugins-for-aws\n```\n\nor\n\n```bash\n\u002Fplugin install sagemaker-ai@agent-plugins-for-aws\n```\n\n### Codex\n\nCodex supports repo-local marketplaces and plugin manifests through\n`.agents\u002Fplugins\u002Fmarketplace.json` and per-plugin manifests under\n`plugins\u002F*\u002F.codex-plugin\u002Fplugin.json`; this repo includes both, following the\nofficial Codex plugin packaging guidance in\n[Build plugins](https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fplugins\u002Fbuild).\n\nTo try these plugins in Codex from this repo:\n\n1. Clone this repository locally.\n2. Open the repo in Codex so Codex can discover\n   `.agents\u002Fplugins\u002Fmarketplace.json`.\n3. Restart Codex.\n4. Open the plugin directory, choose the `Agent Plugins for AWS` marketplace,\n   and install the plugin you want to use.\n\nKnown limitation:\n\n- Claude-specific automatic hooks are not yet wired into the Codex manifests.\n- The `databases-on-aws` prompt hook is included because it does not depend on\n  Claude-specific environment variables.\n\n### Cursor\n\nYou can install the **deploy-on-aws** plugin from the [Cursor Marketplace](https:\u002F\u002Fcursor.com\u002Fmarketplace\u002Faws). For additional information, please refer to the [Cursor plugin documentation](https:\u002F\u002Fcursor.com\u002Fdocs\u002Fplugins). You can also install within the Cursor application:\n\n- Open Cursor Settings\n- Navigate to `Plugins`\n- Search for `AWS`\n- Select the plugin you want to install and click `Add to Cursor`\n- Select the scope for the installed plugin\n- The plugin should appear under `Plugins -> Installed`\n\n### Kiro (experimental)\n\nYou can convert Claude Code plugins into Kiro format using the third-party [`@every-env\u002Fcompound-plugin`](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@every-env\u002Fcompound-plugin) CLI. This converts skills (SKILL.md workflow instructions and reference documents) and MCP server configs into Kiro's `.kiro\u002F` format.\n\nRequires [Bun](https:\u002F\u002Fbun.sh) (latest version recommended).\n\n> [!NOTE]\n> Hook conversion is a work in progress — hooks are currently dropped entirely during conversion because the Claude Code and Kiro hook models are not 1:1. Skills and MCP servers are fully supported.\n\n#### Project scope\n\nWrites to `.kiro\u002F` in the current working directory:\n\n```bash\nCOMPOUND_PLUGIN_GITHUB_SOURCE=https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins \\\n  bunx @every-env\u002Fcompound-plugin install deploy-on-aws --to kiro\n```\n\n#### Global scope\n\nWrites to `~\u002F.kiro\u002F` so skills are available across all projects:\n\n```bash\nCOMPOUND_PLUGIN_GITHUB_SOURCE=https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins \\\n  bunx @every-env\u002Fcompound-plugin install deploy-on-aws --to kiro --output ~\u002F.kiro\n```\n\nReplace `deploy-on-aws` with any plugin name from the table above (e.g., `aws-serverless`, `amazon-location-service`, `migration-to-aws`, `aws-amplify`).\n\n> [!TIP]\n> If a skill isn't activated automatically, you can explicitly invoke it by saying \"Use the deploy skill to ...\" in your prompt. Kiro's intent matching may not always auto-trigger skills.\n>\n> If `bunx` fails with a \"Cannot find package\" error, clear the bun cache and retry:\n>\n> ```bash\n> rm -rf ~\u002F.bun\u002Finstall\u002Fcache\u002F@every-env\n> ```\n\nFor issues with the conversion tool, please report them at [EveryInc\u002Fcompound-engineering-plugin](https:\u002F\u002Fgithub.com\u002FEveryInc\u002Fcompound-engineering-plugin\u002Fissues).\n\n## amazon-location-service\n\nGuides developers through adding maps, places search, geocoding, routing, and other geospatial features with Amazon Location Service, including authentication setup, SDK integration, and best practices.\n\n### Agent Skill Triggers\n\n| Agent Skill                 | Triggers                                                                                                                               |\n| --------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |\n| **amazon-location-service** | \"add a map\", \"geocode an address\", \"calculate a route\", \"location-aware app\", \"Amazon Location Service\", \"geospatial\", \"places search\" |\n\n### MCP Servers\n\n| Server      | Purpose                                |\n| ----------- | -------------------------------------- |\n| **aws-mcp** | AWS documentation and service guidance |\n\n## aws-amplify\n\nBuild full-stack apps with AWS Amplify Gen 2 using TypeScript code-first development, guided by official AWS Agent Standard Operating Procedures (SOPs).\n\n### Workflow\n\n1. **Backend** - Create Amplify Gen 2 resources (auth, data, storage, functions)\n2. **Sandbox** - Deploy to sandbox for testing\n3. **Frontend & Test** - Connect frontend to backend, verify locally\n4. **Production** - Deploy to production\n\n### Agent Skill Triggers\n\n| Agent Skill          | Triggers                                                                                                     |\n| -------------------- | ------------------------------------------------------------------------------------------------------------ |\n| **amplify-workflow** | \"build Amplify app\", \"create Amplify project\", \"add auth to Amplify\", \"deploy Amplify\", \"full-stack Amplify\" |\n\n### MCP Servers\n\n| Server      | Purpose                                |\n| ----------- | -------------------------------------- |\n| **aws-mcp** | AWS documentation and service guidance |\n\n## aws-serverless\n\nDesign, build, deploy, test, and debug serverless applications with AWS Lambda, API Gateway, EventBridge, Step Functions, and durable functions. Includes SAM and CDK deployment workflows, a SAM template validation hook, and the AWS Lambda durable functions skill for building resilient, long-running, multi-step applications.\n\n### Agent Skill Triggers\n\n| Agent Skill                      | Triggers                                                                                                                                                                     |\n| -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **aws-lambda**                   | \"Lambda function\", \"event source\", \"serverless application\", \"API Gateway\", \"EventBridge\", \"Step Functions\", \"serverless API\", \"event-driven architecture\", \"Lambda trigger\" |\n| **aws-serverless-deployment**    | \"use SAM\", \"SAM template\", \"SAM init\", \"SAM deploy\", \"CDK serverless\", \"CDK Lambda construct\", \"NodejsFunction\", \"PythonFunction\", \"serverless CI\u002FCD pipeline\"               |\n| **aws-lambda-durable-functions** | \"lambda durable functions\", \"workflow orchestration\", \"state machines\", \"retry\u002Fcheckpoint patterns\", \"long-running stateful Lambda\", \"saga pattern\", \"human-in-the-loop\"     |\n\n### MCP Servers\n\n| Server                 | Purpose                                                                              |\n| ---------------------- | ------------------------------------------------------------------------------------ |\n| **aws-serverless-mcp** | Serverless development guidance, project scaffolding, IaC generation, and deployment |\n\n### Hooks\n\n| Hook                        | Trigger                                       | Action                                        |\n| --------------------------- | --------------------------------------------- | --------------------------------------------- |\n| **SAM template validation** | After edits to `template.yaml`\u002F`template.yml` | Runs `sam validate` and reports errors inline |\n\n## codebase-documentor-for-aws\n\nAnalyzes codebases to generate structured technical documentation with source-of-truth citations linking every finding back to the exact code that produced it. Uses an outline-driven pipeline to systematically analyze codebases of any size with a persistent task board for resumability.\n\n### Agent Skill Triggers\n\n| Agent Skill          | Triggers                                                                                                                                                                                          |\n| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **document-service** | \"analyze this codebase\", \"generate documentation\", \"document this service\", \"I inherited this code\", \"help me understand this system\", \"draw the architecture\", \"what does this system look like\" |\n\n### MCP Servers\n\n| Server           | Purpose                                                              |\n| ---------------- | -------------------------------------------------------------------- |\n| **awsknowledge** | AWS service descriptions, architecture guidance, documentation links |\n| **awsiac**       | CDK\u002FCloudFormation resource schema validation and IaC best practices |\n\n## databases-on-aws\n\nDatabase guidance for the AWS database portfolio. Design schemas, execute queries, handle migrations, build applications, and choose the right database for your workload. Currently includes Aurora DSQL — a serverless, PostgreSQL-compatible distributed SQL database.\n\n### Agent Skill Triggers\n\n| Agent Skill | Triggers                                                                                                                                      |\n| ----------- | --------------------------------------------------------------------------------------------------------------------------------------------- |\n| **dsql**    | \"Aurora DSQL\", \"DSQL schema\", \"distributed SQL database\", \"serverless PostgreSQL-compatible database\", \"create DSQL table\", \"migrate to DSQL\" |\n\n### MCP Servers\n\n| Server           | Purpose                                                                          |\n| ---------------- | -------------------------------------------------------------------------------- |\n| **awsknowledge** | AWS documentation, architecture guidance, and best practices                     |\n| **aurora-dsql**  | Direct database operations — queries, schema, transactions (disabled by default) |\n\n### Hooks\n\n| Hook                    | Trigger                     | Action                                                   |\n| ----------------------- | --------------------------- | -------------------------------------------------------- |\n| **Schema verification** | After `transact` operations | Prompts verification of schema changes and affected rows |\n\n## deploy-on-aws\n\nEquips agents with the skills to accelerate AWS deployment - recommending AWS architectures and services, estimating costs, generating Infrastructure as Code (CDK or CloudFormation), and guiding you through deployment.\n\n### Workflow\n\n1. **Analyze** - Scan codebase for framework, database, dependencies\n2. **Recommend** - Select AWS services with concise rationale\n3. **Estimate** - Show cost estimates before proceeding\n4. **Generate** - Write IaC code (CDK\u002FCloudFormation)\n5. **Deploy** - Execute with user confirmation\n\n### Agent Skill Triggers\n\n| Agent Skill | Triggers                                                                                                              |\n| ----------- | --------------------------------------------------------------------------------------------------------------------- |\n| **deploy**  | \"deploy to AWS\", \"host on AWS\", \"run this on AWS\", \"AWS architecture\", \"estimate AWS cost\", \"generate infrastructure\" |\n\n### MCP Servers\n\n| Server           | Purpose                                                      |\n| ---------------- | ------------------------------------------------------------ |\n| **awsknowledge** | AWS documentation, architecture guidance, and best practices |\n| **awspricing**   | Real-time AWS service pricing for cost estimates             |\n| **aws-iac-mcp**  | IaC best practices for CDK\u002FCloudFormation                    |\n\n## sagemaker-ai\n\nBuild, train, and deploy AI models with deep AWS AI\u002FML expertise brought directly into your coding assistants, covering the surface area of [Amazon SageMaker AI](https:\u002F\u002Faws.amazon.com\u002Fsagemaker\u002Fai\u002F). [Learn more](.\u002Fplugins\u002Fsagemaker-ai\u002FREADME.md).\n\n## Requirements\n\n- Claude Code >=2.1.29 or [Cursor >= 2.5](https:\u002F\u002Fcursor.com\u002Fchangelog\u002F2-5)\n- AWS CLI configured with appropriate credentials\n\n## Troubleshooting\n\nHaving issues with plugin installation or usage? See our [troubleshooting guide](.\u002Fdocs\u002FTROUBLESHOOTING.md) for common solutions.\n\n## Contributing\n\nBig shout out to our awesome contributors! Thank you for making this project better!\n\nContributions of all kinds are welcome! Check out our [contributor guide](.\u002FCONTRIBUTING.md) for more information.\n\n## Developer guide\n\nIf you want to add a new plugin to the library, check out our [design guidelines](.\u002Fdocs\u002FDESIGN_GUIDELINES.md) and [development guide](.\u002Fdocs\u002FDEVELOPMENT_GUIDE.md).\n\n## Maintainers\n\nRepository reviewers, maintainers, and admins can find PR review workflows, merge rules, and CI\u002FCD documentation in the [maintainers guide](.\u002Fdocs\u002FMAINTAINERS_GUIDE.md).\n\n## Administrators\n\nGitHub environment and AWS account configuration are documented in the [administrators guide](.\u002Fdocs\u002FADMINISTRATORS_GUIDE.md).\n\n## Additional Resources\n\n- [Introducing Agent Plugins for AWS Blog](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdeveloper\u002Fintroducing-agent-plugins-for-aws\u002F)\n- [Extend Cursor with plugins ft. AWS](https:\u002F\u002Fcursor.com\u002Fblog\u002Fmarketplace)\n- [MCP Servers for AWS](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp)\n- [Claude Code plugins documentation](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins)\n- [Cursor plugins documentation](https:\u002F\u002Fcursor.com\u002Fdocs\u002Fplugins)\n\n## License\n\nThis project is licensed under the Apache-2.0 License.\n","awslabs\u002Fagent-plugins 项目为 AWS 上的 AI 编码代理提供了插件，帮助用户进行架构设计、部署和运维。其核心功能包括通过编码指导来提高确定性、减少上下文开销，并使团队间的代理行为标准化；支持 Claude Code、Codex 和 Cursor 等 AI 编码代理工具。技术特点涵盖封装了不同类型的专家知识工件（如代理技能、MCP 服务器连接、自动化钩子及参考资料）的插件容器。此项目特别适合需要在AWS平台上高效开发、维护或优化应用程序的企业和个人开发者使用，尤其是在利用AI辅助软件开发的过程中。",2,"2026-06-11 03:53:15","trending"]