[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-sitetositevpn":3,"mdc--ie12em-key":35,"related-org-aws-sitetositevpn":346,"related-repo-aws-sitetositevpn":517},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"sitetositevpn","configure AWS Site-to-Site VPN","Configures AWS Site-to-Site VPN: creating an IPsec VPN connection between an on-premises network and a VPC, choosing the target gateway (virtual private gateway, transit gateway, or AWS Cloud WAN), choosing static or dynamic (BGP) routing, sizing tunnel bandwidth (Standard 1.25 Gbps or Large 5 Gbps), connecting many sites through a VPN Concentrator, applying the customer gateway device configuration, making a connection highly available, and monitoring tunnels with CloudWatch. Applicable when the user wants to connect a data center or branch office to AWS over an encrypted tunnel, choose how routes are exchanged, scale throughput, consolidate sites, or diagnose a down tunnel. Routes to the right per-task procedure in references. Not for AWS Direct Connect (its own service), Client VPN for individual remote users, the transit gateway side of a VPN attachment (transitgateway skill), or Route 53 DNS work.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Security","security","tag",{"name":17,"slug":18,"type":15},"Networking","networking",{"name":20,"slug":21,"type":15},"Infrastructure","infrastructure",{"name":23,"slug":8,"type":15},"AWS",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-12T08:44:48.645343",null,157,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS","https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Ftree\u002FHEAD\u002Fskills\u002Fspecialized-skills\u002Fnetworking-and-content-delivery-skills\u002Fsitetositevpn","---\nname: sitetositevpn\ndescription: >\n  Configures AWS Site-to-Site VPN: creating an IPsec VPN connection between an on-premises network\n  and a VPC, choosing the target gateway (virtual private gateway, transit gateway, or AWS Cloud\n  WAN), choosing static or dynamic (BGP) routing, sizing tunnel bandwidth (Standard 1.25 Gbps or\n  Large 5 Gbps), connecting many sites through a VPN Concentrator, applying the customer gateway\n  device configuration, making a connection highly available, and monitoring tunnels with\n  CloudWatch. Applicable when the user wants to connect a data center or branch office to AWS over\n  an encrypted tunnel, choose how routes are exchanged, scale throughput, consolidate sites, or\n  diagnose a down tunnel. Routes to the right per-task procedure in references. Not for AWS Direct\n  Connect (its own service), Client VPN for individual remote users, the transit gateway side of a\n  VPN attachment (transitgateway skill), or Route 53 DNS work.\nversion: 1\n---\n\n# AWS Site-to-Site VPN\n\n## Overview\n\nDomain expertise for configuring AWS Site-to-Site VPN, the managed service that builds an encrypted\nIP Security (IPsec) connection between an on-premises network and AWS. Covers the routing decision\n(static versus dynamic (BGP) routing), creating the connection and its dependent resources in the right order,\nsizing tunnel bandwidth, consolidating many sites through a VPN Concentrator, applying the customer\ngateway device configuration, building for high availability, and monitoring and troubleshooting\ntunnels.\n\nThis skill is a router. Each customer task maps to a procedure file under `references\u002F`. Read the\nmatching reference in full before acting, then follow its constraints and steps. The reference\nfiles are self-contained: each carries its own decision tables, constraints, procedure, and\ntroubleshooting.\n\nExecute commands using the AWS MCP server when connected (sandboxed execution, audit logging,\nobservability). Fall back to the AWS CLI otherwise. Site-to-Site VPN is a regional service: pass\n`--region {region}` matching the VPC or transit gateway the connection terminates on.\n\n## Which Site-to-Site VPN task do you need?\n\n| Goal | Reference |\n| --- | --- |\n| Decide between static and dynamic (BGP) routing before creating a connection | [choosing static or dynamic routing](references\u002Fchoosing-static-or-dynamic-routing.md) |\n| Create an encrypted VPN connection from on-premises to a VPC | [creating a site-to-site vpn connection](references\u002Fcreating-a-site-to-site-vpn-connection.md) |\n| Size tunnel bandwidth at Standard (1.25 Gbps) or Large (5 Gbps) | [choosing tunnel bandwidth](references\u002Fchoosing-tunnel-bandwidth-standard-or-large.md) |\n| Connect 25 or more low-bandwidth sites through one shared attachment | [connecting many sites with a vpn concentrator](references\u002Fconnecting-many-sites-with-a-vpn-concentrator.md) |\n| Configure the on-premises customer gateway device | [applying the customer gateway device configuration](references\u002Fapplying-the-customer-gateway-device-configuration.md) |\n| Make the connection survive tunnel maintenance and device failure | [making a connection highly available](references\u002Fmaking-a-connection-highly-available.md) |\n| Detect a down tunnel and find out why | [monitoring and troubleshooting tunnels](references\u002Fmonitoring-and-troubleshooting-tunnels.md) |\n\n## Routing notes\n\n- **Decide routing before you build.** The static-versus-dynamic decision shapes the customer\n  gateway, the failover behavior, and whether the customer can control which routes enter their\n  network. Run the choosing-static-or-dynamic-routing reference before creating the connection so\n  the customer does not have to recreate it to change routing type.\n- **The target gateway gates almost everything.** A virtual private gateway terminates the VPN at\n  one VPC. A transit gateway fronts many VPCs and is the only target that supports Large (5 Gbps)\n  tunnels, equal-cost multi-path (ECMP) bandwidth aggregation, IPv6 customer gateways, and the VPN\n  Concentrator. The gateway choice lives in the creating reference and is referenced again by the\n  bandwidth and concentrator references, because picking a virtual private gateway closes those\n  doors.\n- **Bandwidth sizing vs the Concentrator.** Both scale capacity, in opposite directions. Large\n  tunnels give one connection more throughput (up to 5 Gbps per tunnel); the Concentrator gives\n  many low-bandwidth sites a shared 5 Gbps attachment so each site does not need its own\n  full-bandwidth connection. Match the reference to whether the customer has one high-throughput\n  site or many small ones.\n- **AWS side vs device side.** Creating the connection and downloading the configuration happen on\n  the AWS side; applying that configuration happens on the customer's on-premises device, which AWS\n  never touches. The applying-the-customer-gateway-device-configuration reference is device-side\n  education, not an AWS-side step.\n- **Monitoring is its own task.** Detecting and diagnosing a down tunnel (CloudWatch metrics,\n  alarms, and VPN logs) is the monitoring reference, separate from building the connection.\n\n## Additional Resources\n\n- [AWS Site-to-Site VPN User Guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fvpn\u002Flatest\u002Fs2svpn\u002FVPC_VPN.html)\n- [AWS Site-to-Site VPN product page](https:\u002F\u002Faws.amazon.com\u002Fvpn\u002Fsite-to-site-vpn\u002F)\n- [AWS VPN pricing](https:\u002F\u002Faws.amazon.com\u002Fvpn\u002Fpricing\u002F)\n",{"data":36,"body":38},{"name":4,"description":6,"version":37},1,{"type":39,"children":40},"root",[41,50,57,63,77,90,96,244,250,306,312],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"aws-site-to-site-vpn",[47],{"type":48,"value":49},"text","AWS Site-to-Site VPN",{"type":42,"tag":51,"props":52,"children":54},"h2",{"id":53},"overview",[55],{"type":48,"value":56},"Overview",{"type":42,"tag":58,"props":59,"children":60},"p",{},[61],{"type":48,"value":62},"Domain expertise for configuring AWS Site-to-Site VPN, the managed service that builds an encrypted\nIP Security (IPsec) connection between an on-premises network and AWS. Covers the routing decision\n(static versus dynamic (BGP) routing), creating the connection and its dependent resources in the right order,\nsizing tunnel bandwidth, consolidating many sites through a VPN Concentrator, applying the customer\ngateway device configuration, building for high availability, and monitoring and troubleshooting\ntunnels.",{"type":42,"tag":58,"props":64,"children":65},{},[66,68,75],{"type":48,"value":67},"This skill is a router. Each customer task maps to a procedure file under ",{"type":42,"tag":69,"props":70,"children":72},"code",{"className":71},[],[73],{"type":48,"value":74},"references\u002F",{"type":48,"value":76},". Read the\nmatching reference in full before acting, then follow its constraints and steps. The reference\nfiles are self-contained: each carries its own decision tables, constraints, procedure, and\ntroubleshooting.",{"type":42,"tag":58,"props":78,"children":79},{},[80,82,88],{"type":48,"value":81},"Execute commands using the AWS MCP server when connected (sandboxed execution, audit logging,\nobservability). Fall back to the AWS CLI otherwise. Site-to-Site VPN is a regional service: pass\n",{"type":42,"tag":69,"props":83,"children":85},{"className":84},[],[86],{"type":48,"value":87},"--region {region}",{"type":48,"value":89}," matching the VPC or transit gateway the connection terminates on.",{"type":42,"tag":51,"props":91,"children":93},{"id":92},"which-site-to-site-vpn-task-do-you-need",[94],{"type":48,"value":95},"Which Site-to-Site VPN task do you need?",{"type":42,"tag":97,"props":98,"children":99},"table",{},[100,119],{"type":42,"tag":101,"props":102,"children":103},"thead",{},[104],{"type":42,"tag":105,"props":106,"children":107},"tr",{},[108,114],{"type":42,"tag":109,"props":110,"children":111},"th",{},[112],{"type":48,"value":113},"Goal",{"type":42,"tag":109,"props":115,"children":116},{},[117],{"type":48,"value":118},"Reference",{"type":42,"tag":120,"props":121,"children":122},"tbody",{},[123,142,159,176,193,210,227],{"type":42,"tag":105,"props":124,"children":125},{},[126,132],{"type":42,"tag":127,"props":128,"children":129},"td",{},[130],{"type":48,"value":131},"Decide between static and dynamic (BGP) routing before creating a connection",{"type":42,"tag":127,"props":133,"children":134},{},[135],{"type":42,"tag":136,"props":137,"children":139},"a",{"href":138},"references\u002Fchoosing-static-or-dynamic-routing.md",[140],{"type":48,"value":141},"choosing static or dynamic routing",{"type":42,"tag":105,"props":143,"children":144},{},[145,150],{"type":42,"tag":127,"props":146,"children":147},{},[148],{"type":48,"value":149},"Create an encrypted VPN connection from on-premises to a VPC",{"type":42,"tag":127,"props":151,"children":152},{},[153],{"type":42,"tag":136,"props":154,"children":156},{"href":155},"references\u002Fcreating-a-site-to-site-vpn-connection.md",[157],{"type":48,"value":158},"creating a site-to-site vpn connection",{"type":42,"tag":105,"props":160,"children":161},{},[162,167],{"type":42,"tag":127,"props":163,"children":164},{},[165],{"type":48,"value":166},"Size tunnel bandwidth at Standard (1.25 Gbps) or Large (5 Gbps)",{"type":42,"tag":127,"props":168,"children":169},{},[170],{"type":42,"tag":136,"props":171,"children":173},{"href":172},"references\u002Fchoosing-tunnel-bandwidth-standard-or-large.md",[174],{"type":48,"value":175},"choosing tunnel bandwidth",{"type":42,"tag":105,"props":177,"children":178},{},[179,184],{"type":42,"tag":127,"props":180,"children":181},{},[182],{"type":48,"value":183},"Connect 25 or more low-bandwidth sites through one shared attachment",{"type":42,"tag":127,"props":185,"children":186},{},[187],{"type":42,"tag":136,"props":188,"children":190},{"href":189},"references\u002Fconnecting-many-sites-with-a-vpn-concentrator.md",[191],{"type":48,"value":192},"connecting many sites with a vpn concentrator",{"type":42,"tag":105,"props":194,"children":195},{},[196,201],{"type":42,"tag":127,"props":197,"children":198},{},[199],{"type":48,"value":200},"Configure the on-premises customer gateway device",{"type":42,"tag":127,"props":202,"children":203},{},[204],{"type":42,"tag":136,"props":205,"children":207},{"href":206},"references\u002Fapplying-the-customer-gateway-device-configuration.md",[208],{"type":48,"value":209},"applying the customer gateway device configuration",{"type":42,"tag":105,"props":211,"children":212},{},[213,218],{"type":42,"tag":127,"props":214,"children":215},{},[216],{"type":48,"value":217},"Make the connection survive tunnel maintenance and device failure",{"type":42,"tag":127,"props":219,"children":220},{},[221],{"type":42,"tag":136,"props":222,"children":224},{"href":223},"references\u002Fmaking-a-connection-highly-available.md",[225],{"type":48,"value":226},"making a connection highly available",{"type":42,"tag":105,"props":228,"children":229},{},[230,235],{"type":42,"tag":127,"props":231,"children":232},{},[233],{"type":48,"value":234},"Detect a down tunnel and find out why",{"type":42,"tag":127,"props":236,"children":237},{},[238],{"type":42,"tag":136,"props":239,"children":241},{"href":240},"references\u002Fmonitoring-and-troubleshooting-tunnels.md",[242],{"type":48,"value":243},"monitoring and troubleshooting tunnels",{"type":42,"tag":51,"props":245,"children":247},{"id":246},"routing-notes",[248],{"type":48,"value":249},"Routing notes",{"type":42,"tag":251,"props":252,"children":253},"ul",{},[254,266,276,286,296],{"type":42,"tag":255,"props":256,"children":257},"li",{},[258,264],{"type":42,"tag":259,"props":260,"children":261},"strong",{},[262],{"type":48,"value":263},"Decide routing before you build.",{"type":48,"value":265}," The static-versus-dynamic decision shapes the customer\ngateway, the failover behavior, and whether the customer can control which routes enter their\nnetwork. Run the choosing-static-or-dynamic-routing reference before creating the connection so\nthe customer does not have to recreate it to change routing type.",{"type":42,"tag":255,"props":267,"children":268},{},[269,274],{"type":42,"tag":259,"props":270,"children":271},{},[272],{"type":48,"value":273},"The target gateway gates almost everything.",{"type":48,"value":275}," A virtual private gateway terminates the VPN at\none VPC. A transit gateway fronts many VPCs and is the only target that supports Large (5 Gbps)\ntunnels, equal-cost multi-path (ECMP) bandwidth aggregation, IPv6 customer gateways, and the VPN\nConcentrator. The gateway choice lives in the creating reference and is referenced again by the\nbandwidth and concentrator references, because picking a virtual private gateway closes those\ndoors.",{"type":42,"tag":255,"props":277,"children":278},{},[279,284],{"type":42,"tag":259,"props":280,"children":281},{},[282],{"type":48,"value":283},"Bandwidth sizing vs the Concentrator.",{"type":48,"value":285}," Both scale capacity, in opposite directions. Large\ntunnels give one connection more throughput (up to 5 Gbps per tunnel); the Concentrator gives\nmany low-bandwidth sites a shared 5 Gbps attachment so each site does not need its own\nfull-bandwidth connection. Match the reference to whether the customer has one high-throughput\nsite or many small ones.",{"type":42,"tag":255,"props":287,"children":288},{},[289,294],{"type":42,"tag":259,"props":290,"children":291},{},[292],{"type":48,"value":293},"AWS side vs device side.",{"type":48,"value":295}," Creating the connection and downloading the configuration happen on\nthe AWS side; applying that configuration happens on the customer's on-premises device, which AWS\nnever touches. The applying-the-customer-gateway-device-configuration reference is device-side\neducation, not an AWS-side step.",{"type":42,"tag":255,"props":297,"children":298},{},[299,304],{"type":42,"tag":259,"props":300,"children":301},{},[302],{"type":48,"value":303},"Monitoring is its own task.",{"type":48,"value":305}," Detecting and diagnosing a down tunnel (CloudWatch metrics,\nalarms, and VPN logs) is the monitoring reference, separate from building the connection.",{"type":42,"tag":51,"props":307,"children":309},{"id":308},"additional-resources",[310],{"type":48,"value":311},"Additional Resources",{"type":42,"tag":251,"props":313,"children":314},{},[315,326,336],{"type":42,"tag":255,"props":316,"children":317},{},[318],{"type":42,"tag":136,"props":319,"children":323},{"href":320,"rel":321},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fvpn\u002Flatest\u002Fs2svpn\u002FVPC_VPN.html",[322],"nofollow",[324],{"type":48,"value":325},"AWS Site-to-Site VPN User Guide",{"type":42,"tag":255,"props":327,"children":328},{},[329],{"type":42,"tag":136,"props":330,"children":333},{"href":331,"rel":332},"https:\u002F\u002Faws.amazon.com\u002Fvpn\u002Fsite-to-site-vpn\u002F",[322],[334],{"type":48,"value":335},"AWS Site-to-Site VPN product page",{"type":42,"tag":255,"props":337,"children":338},{},[339],{"type":42,"tag":136,"props":340,"children":343},{"href":341,"rel":342},"https:\u002F\u002Faws.amazon.com\u002Fvpn\u002Fpricing\u002F",[322],[344],{"type":48,"value":345},"AWS VPN pricing",{"items":347,"total":516},[348,365,380,395,410,420,433,449,466,479,491,506],{"slug":349,"name":349,"fn":350,"description":351,"org":352,"tags":353,"stars":24,"repoUrl":25,"updatedAt":364},"agents-build","add capabilities to existing agent projects","Use when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal. Triggers on: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"auth to call agent\", \"streaming responses\", \"VPC\", \"VPC connectivity\", \"VPC error\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"after import\", \"migration issue\", \"framework for migration\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"resource-based policy on memory\", \"pay for x402 content\", \"402 Payment Required\", \"microtransactions\", \"paid API or tool\". Not for connecting to external APIs via Gateway — use agents-connect. Not for scaffolding a new project — use agents-get-started. Not for CLI\u002Fdev server errors — use agents-debug. Strands vs LangGraph in a migration context routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[354,357,360,361],{"name":355,"slug":356,"type":15},"Agents","agents",{"name":358,"slug":359,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":362,"slug":363,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":366,"name":366,"fn":367,"description":368,"org":369,"tags":370,"stars":24,"repoUrl":25,"updatedAt":379},"agents-connect","connect agents to external services","Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: \"connect to API\", \"add gateway\", \"connect to MCP server\", \"Lambda tools\", \"OpenAPI\", \"gateway target\", \"Cedar policy\", \"restrict tools\", \"policy engine\", \"gateway auth error\", \"store API key\", \"outbound credential\", \"env var API key\", \"API key None after deploy\", \"credential not available after deploy\", \"should this be a gateway target\", \"give my agent tools\", \"add tools to agent\". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[371,372,375,378],{"name":355,"slug":356,"type":15},{"name":373,"slug":374,"type":15},"API Development","api-development",{"name":376,"slug":377,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":381,"name":381,"fn":382,"description":383,"org":384,"tags":385,"stars":24,"repoUrl":25,"updatedAt":394},"agents-debug","debug agent and environment issues","Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: \"agent not working\", \"wrong answer\", \"agent error\", \"tool call failing\", \"debug agent\", \"check logs\", \"read traces\", \"broken\", \"500 error\", \"424 error\", \"model access denied\", \"command not found\", \"stuck in DELETING\", \"maxVms exceeded\", \"cold start diagnosis\", \"cold start slow\", \"agentcore create error\", \"create failed\", \"exit code 7\", \"connection refused local dev\". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[386,387,388,391],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":389,"slug":390,"type":15},"Debugging","debugging",{"name":392,"slug":393,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":396,"name":396,"fn":397,"description":398,"org":399,"tags":400,"stars":24,"repoUrl":25,"updatedAt":409},"agents-deploy","deploy AI agents to AWS","Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK\u002FIAM\u002Fquota error diagnosis, version management, rollback, and canary deployments. Triggers on: \"deploy my agent\", \"agentcore deploy\", \"deploy failed\", \"CDK error\", \"rollback\", \"canary deploy\", \"pin version\", \"redeploy\", \"deploy stuck\". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[401,402,403,406],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":404,"slug":405,"type":15},"CI\u002FCD","ci-cd",{"name":407,"slug":408,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":411,"name":411,"fn":412,"description":413,"org":414,"tags":415,"stars":24,"repoUrl":25,"updatedAt":419},"agents-get-started","scaffold and deploy new agent projects","Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: \"build an agent\", \"create an agent\", \"get started\", \"new project\", \"agentcore create\", \"which framework\", \"Strands vs LangGraph\", \"hello world agent\", \"first agent\", \"create MCP server\", \"host MCP server\", \"agentcore dev\", \"dev server\", \"what port\", \"local development\". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[416,417,418],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":407,"slug":408,"type":15},"2026-07-12T08:42:51.963247",{"slug":421,"name":421,"fn":422,"description":423,"org":424,"tags":425,"stars":24,"repoUrl":25,"updatedAt":432},"agents-harden","harden agents for production","Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: \"production checklist\", \"harden agent\", \"production ready\", \"secure agent\", \"inbound auth\", \"going live\", \"cold start optimization\", \"session lifecycle\", \"StopRuntimeSession\", \"quota\", \"throttling\", \"maxVms\", \"rate limit\", \"security audit of outbound API calls\", \"gateway target audit for production\", \"restrict who can call\", \"lock down endpoint\", \"only our app can call\". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[426,427,428,431],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":429,"slug":430,"type":15},"Best Practices","best-practices",{"name":13,"slug":14,"type":15},"2026-07-16T06:00:42.174705",{"slug":434,"name":434,"fn":435,"description":436,"org":437,"tags":438,"stars":24,"repoUrl":25,"updatedAt":448},"agents-optimize","optimize agent quality and performance","Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI\u002FCD quality gates, observability, or cost optimization. Triggers on: \"evaluate my agent\", \"add evaluator\", \"measure quality\", \"quality gate\", \"run evals\", \"agent too slow\", \"why is it slow\", \"reduce latency\", \"set up observability\", \"CloudWatch dashboard\", \"how much does my agent cost\", \"cost optimization\", \"logs not showing up\", \"logs missing\", \"spans not found\", \"eval failing\", \"eval error\", \"dev traces\", \"local traces\", \"agentcore dev traces\", \"traces to CloudWatch\". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[439,440,441,444,445],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":442,"slug":443,"type":15},"Evals","evals",{"name":392,"slug":393,"type":15},{"name":446,"slug":447,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":450,"name":450,"fn":451,"description":452,"org":453,"tags":454,"stars":24,"repoUrl":25,"updatedAt":465},"amazon-aurora-mysql","manage Amazon Aurora MySQL clusters","Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql instead. Contains safety guardrails and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[455,456,459,462],{"name":23,"slug":8,"type":15},{"name":457,"slug":458,"type":15},"Database","database",{"name":460,"slug":461,"type":15},"MySQL","mysql",{"name":463,"slug":464,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":467,"name":467,"fn":468,"description":469,"org":470,"tags":471,"stars":24,"repoUrl":25,"updatedAt":478},"amazon-aurora-postgresql","configure Amazon Aurora PostgreSQL clusters","Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless, express configuration, pgvector, Babelfish). Trigger for Aurora PostgreSQL cluster operations, express-configuration quick-start, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or PostgreSQL upgrade planning. For Aurora MySQL, use amazon-aurora-mysql instead. Contains safety guardrails, express-first routing, and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[472,473,474,477],{"name":23,"slug":8,"type":15},{"name":457,"slug":458,"type":15},{"name":475,"slug":476,"type":15},"PostgreSQL","postgresql",{"name":463,"slug":464,"type":15},"2026-07-16T06:00:34.789624",{"slug":480,"name":480,"fn":481,"description":482,"org":483,"tags":484,"stars":24,"repoUrl":25,"updatedAt":490},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore. Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, 402 Payment Required, pay for content, paid endpoint, agent payments). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[485,486,487],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":488,"slug":489,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":492,"name":492,"fn":493,"description":494,"org":495,"tags":496,"stars":24,"repoUrl":25,"updatedAt":505},"amazon-documentdb","manage Amazon DocumentDB clusters","Manages Amazon DocumentDB end-to-end — serverless-on-8.0 cluster setup, TLS\u002FVPC\u002Fdriver config, flexible-schema and vector-search data modeling, MongoDB compatibility assessment, DMS-based migration, slow-query diagnosis, major version upgrades (4.0→5.0→8.0), Well-Architected reviews (41-check wa_review.py), cost estimation, and security hardening. Retrieve for every DocumentDB question and when the user asks to set up or migrate MongoDB to AWS — DocumentDB is AWS's MongoDB-compatible managed database. Triggers: JSON document store, document database, MongoDB on AWS, Nested fields, Lambda cannot connect, TLS handshake, VPC port 27017, IAM auth, Secrets Manager, encryption at rest, $graphLookup, flexible schema, COLLSCAN, compound index, DMS migration, CDC cutover, $vectorSearch, RAG, Global Clusters, DR replication, cost sizing, audit, health check, production-readiness.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[497,498,499,502],{"name":23,"slug":8,"type":15},{"name":457,"slug":458,"type":15},{"name":500,"slug":501,"type":15},"MongoDB","mongodb",{"name":503,"slug":504,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":507,"name":507,"fn":508,"description":509,"org":510,"tags":511,"stars":24,"repoUrl":25,"updatedAt":515},"amazon-dynamodb","design and debug DynamoDB data layers","Designs, reviews, and debugs DynamoDB data layers from design axioms — enumerates access patterns, chooses partition\u002Fsort keys and GSIs, decides single-table vs. multi-table, configures Streams, Global Tables, TTL, and zero-ETL integrations to OpenSearch\u002FRedshift\u002FSageMaker Lakehouse, and produces a defensible data-layer design with a monthly cost estimate and optional live validation. Applies whenever a user is designing, reviewing, or refactoring anything backed by DynamoDB — schemas, access patterns, GSIs, single- vs. multi-table choices, Streams consumers, transactional outboxes, Global Tables, zero-ETL pipelines — even when they don't say \"axioms\" or \"design review.\" Also applies when debugging hot partitions, throttling, unbounded Scans, LWW conflicts, or surprise bills on DynamoDB workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[512,513,514],{"name":23,"slug":8,"type":15},{"name":457,"slug":458,"type":15},{"name":503,"slug":504,"type":15},"2026-07-16T06:00:37.690386",115,{"items":518,"total":568},[519,526,533,540,547,553,560],{"slug":349,"name":349,"fn":350,"description":351,"org":520,"tags":521,"stars":24,"repoUrl":25,"updatedAt":364},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[522,523,524,525],{"name":355,"slug":356,"type":15},{"name":358,"slug":359,"type":15},{"name":23,"slug":8,"type":15},{"name":362,"slug":363,"type":15},{"slug":366,"name":366,"fn":367,"description":368,"org":527,"tags":528,"stars":24,"repoUrl":25,"updatedAt":379},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[529,530,531,532],{"name":355,"slug":356,"type":15},{"name":373,"slug":374,"type":15},{"name":376,"slug":377,"type":15},{"name":23,"slug":8,"type":15},{"slug":381,"name":381,"fn":382,"description":383,"org":534,"tags":535,"stars":24,"repoUrl":25,"updatedAt":394},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[536,537,538,539],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":389,"slug":390,"type":15},{"name":392,"slug":393,"type":15},{"slug":396,"name":396,"fn":397,"description":398,"org":541,"tags":542,"stars":24,"repoUrl":25,"updatedAt":409},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[543,544,545,546],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":404,"slug":405,"type":15},{"name":407,"slug":408,"type":15},{"slug":411,"name":411,"fn":412,"description":413,"org":548,"tags":549,"stars":24,"repoUrl":25,"updatedAt":419},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[550,551,552],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":407,"slug":408,"type":15},{"slug":421,"name":421,"fn":422,"description":423,"org":554,"tags":555,"stars":24,"repoUrl":25,"updatedAt":432},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[556,557,558,559],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":429,"slug":430,"type":15},{"name":13,"slug":14,"type":15},{"slug":434,"name":434,"fn":435,"description":436,"org":561,"tags":562,"stars":24,"repoUrl":25,"updatedAt":448},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[563,564,565,566,567],{"name":355,"slug":356,"type":15},{"name":23,"slug":8,"type":15},{"name":442,"slug":443,"type":15},{"name":392,"slug":393,"type":15},{"name":446,"slug":447,"type":15},114]