[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-transitgateway":3,"mdc-rgh10e-key":32,"related-repo-aws-transitgateway":436,"related-org-aws-transitgateway":542},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":21,"repoUrl":22,"updatedAt":23,"license":24,"forks":25,"topics":26,"repo":27,"sourceUrl":30,"mdContent":31},"transitgateway","configure AWS Transit Gateway","Configures AWS Transit Gateway: creating a hub and attaching VPCs, segmenting traffic with route tables, centralizing egress and inspection through a hub (appliances or a Gateway Load Balancer endpoint), forcing east-west traffic between VPCs through AWS Network Firewall, connecting on-premises networks over the transit-gateway side of a Site-to-Site VPN or Direct Connect attachment (including ECMP to aggregate bandwidth across multiple VPN tunnels), peering transit gateways across Regions, migrating from a VPC peering mesh, and routing IP multicast. Applicable when connecting many VPCs through one router, isolating environments, forcing VPC-to-VPC traffic through a central Network Firewall, reaching on-premises over the hub, linking Regions, or moving off a peering mesh. Not applicable for single-VPC routing, VPC peering between two VPCs (vpcpeering skill), Direct Connect gateway or virtual interface setup (directconnect skill), or Route 53 DNS work.",{"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],{"name":13,"slug":14,"type":15},"Networking","networking","tag",{"name":17,"slug":18,"type":15},"Infrastructure","infrastructure",{"name":20,"slug":8,"type":15},"AWS",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-22T06:00:34.044401",null,157,[],{"repoUrl":22,"stars":21,"forks":25,"topics":28,"description":29},[],"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\u002Ftransitgateway","---\nname: transitgateway\ndescription: >-\n  Configures AWS Transit Gateway: creating a hub and attaching VPCs, segmenting traffic with route\n  tables, centralizing egress and inspection through a hub (appliances or a Gateway Load Balancer\n  endpoint), forcing east-west traffic between VPCs through AWS Network Firewall, connecting\n  on-premises networks over the transit-gateway side of a Site-to-Site VPN or Direct Connect\n  attachment (including ECMP to aggregate bandwidth across multiple VPN tunnels), peering transit\n  gateways across Regions, migrating from a VPC peering mesh, and routing IP multicast. Applicable\n  when connecting many VPCs through one router, isolating environments, forcing VPC-to-VPC traffic\n  through a central Network Firewall, reaching on-premises over the hub, linking Regions, or moving\n  off a peering mesh. Not applicable for single-VPC routing, VPC peering between two VPCs (vpcpeering\n  skill), Direct Connect gateway or virtual interface setup (directconnect skill), or Route 53 DNS\n  work.\nversion: 1\n---\n\n# AWS Transit Gateway\n\n## Overview\n\nDomain expertise for configuring AWS Transit Gateway, the Regional network hub that connects many\nVPCs and on-premises networks through a single router instead of a mesh of point-to-point\nconnections. Covers building the hub and attaching VPCs, segmenting traffic with route tables,\ncentralizing egress and inspection, east-west inspection with AWS Network Firewall, hybrid\nconnectivity over Site-to-Site VPN and Direct Connect, inter-Region peering, migrating off a VPC\npeering mesh, and IP multicast.\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. All CLI operations require least-privilege,\nephemeral credentials (an assumed IAM role through AWS STS or AWS IAM Identity Center \u002F SSO), never\nlong-lived IAM user access keys. A transit gateway is a Regional resource: run each `aws ec2`\ntransit gateway command in the Region that holds the hub.\n\n## Which Transit Gateway task do you need?\n\n| Goal | Reference |\n| --- | --- |\n| Create a Regional hub and connect VPCs to it | [creating a transit gateway and attaching VPCs](references\u002Fcreating-a-transit-gateway-and-attaching-vpcs.md) |\n| Isolate some VPCs while letting others share services | [segmenting traffic with route tables](references\u002Fsegmenting-traffic-with-route-tables.md) |\n| Send all spoke traffic out through one inspected egress VPC | [centralizing egress and inspection](references\u002Fcentralizing-egress-and-inspection.md) |\n| Inspect traffic between VPCs with AWS Network Firewall | [inspecting east-west traffic with Network Firewall](references\u002Finspecting-east-west-traffic-with-network-firewall.md) |\n| Reach on-premises networks over Site-to-Site VPN or Direct Connect | [connecting on-premises networks](references\u002Fconnecting-on-premises-networks.md) |\n| Link transit gateways in two Regions over the AWS network | [peering transit gateways across Regions](references\u002Fpeering-transit-gateways-across-regions.md) |\n| Move off a VPC peering mesh without dropping traffic | [migrating from VPC peering](references\u002Fmigrating-from-vpc-peering.md) |\n| Distribute IP multicast across attached VPCs | [routing multicast traffic](references\u002Frouting-multicast-traffic.md) |\n\n## Routing notes\n\n- **Decide segmentation before you build.** \"Default route table association\" and \"Default route\n  table propagation\" are on by default, which wires every attachment into one open mesh. If the\n  customer plans isolated environments, the creating reference disables the defaults up front and\n  hands off to the segmenting reference. Retrofitting isolation onto an open hub is a re-architect.\n- **North-south egress vs east-west inspection.** Centralizing egress sends spoke traffic out to\n  the internet through a central VPC. East-west inspection keeps traffic between spokes internal\n  and forces it through a firewall on the way. They look similar but use different route table\n  recipes. Match the reference to the direction of traffic the customer actually has.\n- **Appliance vs Gateway Load Balancer for inspection.** Raw third-party appliances and a Gateway\n  Load Balancer (GWLB) endpoint are two paths to the same goal. GWLB is the recommended approach\n  for new designs. Both live in the centralizing-egress reference; appliance mode and the GWLB endpoint\n  route table entries differ and the reference covers each.\n- **Appliance mode is required for stateful cross-Availability-Zone inspection, with a tradeoff.** Appliance mode\n  keeps each flow on one Availability Zone's appliance so request and response do not split. It\n  also disables cross-Availability-Zone failover for that attachment, so the inspection design must\n  pair it with health-check-based failover. Both the egress and east-west references carry this.\n- **Transit gateway side vs Direct Connect side.** The connecting-on-premises reference covers the\n  transit gateway side: Site-to-Site VPN attachment options, route propagation, and equal-cost multi-path\n  (ECMP). The Direct Connect gateway and virtual interface setup belongs to the separate\n  `directconnect` skill. Do not restate the Direct Connect side here.\n\n## Security considerations\n\nA transit gateway is the central routing point for many VPCs and on-premises networks, so a\nmisconfiguration here has blast radius across every attached network. Apply these controls\nregardless of the specific task; each per-task reference carries the detail.\n\n- You MUST enable Transit Gateway Flow Logs for traffic visibility, audit, and incident response\n  across the hub, and MUST enable encryption at rest on the destination (a KMS key on the CloudWatch\n  log group, or SSE-KMS on the S3 bucket).\n- You MUST, when a KMS key encrypts a flow log destination (CloudWatch log group or S3 bucket) or a\n  CloudTrail destination, scope the KMS key policy with condition keys (`aws:SourceArn`,\n  `aws:SourceAccount`, and `kms:ViaService`) so only the specific log group, bucket, or trail in the\n  expected account and service can use the key, preventing cross-account or cross-service misuse.\n- You SHOULD apply least-privilege IAM for transit gateway administration, avoiding service\n  wildcards and FullAccess policies, restricting who can create attachments, modify route tables,\n  and change associations or propagations.\n- You SHOULD ensure Site-to-Site VPN tunnels use strong encryption (for example AES-256-GCM with IKEv2) and enable tunnel\n  logging to CloudWatch Logs with encryption enabled (a KMS key) to protect sensitive connection\n  state and IKE negotiation detail from unauthorized access (see the connecting on-premises networks\n  reference).\n- You MUST treat a misconfigured transit gateway route table as a security risk, since wrong\n  associations or propagations can expose workloads across environments meant to stay isolated (see\n  the segmenting traffic reference).\n- You MUST enable AWS CloudTrail to detect unauthorized changes to transit gateway route tables,\n  associations, and propagations, MUST enable encryption at rest on the CloudTrail destination (a KMS\n  key), and use AWS Config rules to detect drift from the intended design.\n\n## Additional Resources\n\n- [AWS Transit Gateway Guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fvpc\u002Flatest\u002Ftgw\u002Fwhat-is-transit-gateway.html)\n- [AWS Transit Gateway product page](https:\u002F\u002Faws.amazon.com\u002Ftransit-gateway\u002F)\n- [AWS Transit Gateway pricing](https:\u002F\u002Faws.amazon.com\u002Ftransit-gateway\u002Fpricing\u002F)\n",{"data":33,"body":35},{"name":4,"description":6,"version":34},1,{"type":36,"children":37},"root",[38,47,54,60,74,87,93,258,264,328,334,339,396,402],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"aws-transit-gateway",[44],{"type":45,"value":46},"text","AWS Transit Gateway",{"type":39,"tag":48,"props":49,"children":51},"h2",{"id":50},"overview",[52],{"type":45,"value":53},"Overview",{"type":39,"tag":55,"props":56,"children":57},"p",{},[58],{"type":45,"value":59},"Domain expertise for configuring AWS Transit Gateway, the Regional network hub that connects many\nVPCs and on-premises networks through a single router instead of a mesh of point-to-point\nconnections. Covers building the hub and attaching VPCs, segmenting traffic with route tables,\ncentralizing egress and inspection, east-west inspection with AWS Network Firewall, hybrid\nconnectivity over Site-to-Site VPN and Direct Connect, inter-Region peering, migrating off a VPC\npeering mesh, and IP multicast.",{"type":39,"tag":55,"props":61,"children":62},{},[63,65,72],{"type":45,"value":64},"This skill is a router. Each customer task maps to a procedure file under ",{"type":39,"tag":66,"props":67,"children":69},"code",{"className":68},[],[70],{"type":45,"value":71},"references\u002F",{"type":45,"value":73},". 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":39,"tag":55,"props":75,"children":76},{},[77,79,85],{"type":45,"value":78},"Execute commands using the AWS MCP server when connected (sandboxed execution, audit logging,\nobservability). Fall back to the AWS CLI otherwise. All CLI operations require least-privilege,\nephemeral credentials (an assumed IAM role through AWS STS or AWS IAM Identity Center \u002F SSO), never\nlong-lived IAM user access keys. A transit gateway is a Regional resource: run each ",{"type":39,"tag":66,"props":80,"children":82},{"className":81},[],[83],{"type":45,"value":84},"aws ec2",{"type":45,"value":86},"\ntransit gateway command in the Region that holds the hub.",{"type":39,"tag":48,"props":88,"children":90},{"id":89},"which-transit-gateway-task-do-you-need",[91],{"type":45,"value":92},"Which Transit Gateway task do you need?",{"type":39,"tag":94,"props":95,"children":96},"table",{},[97,116],{"type":39,"tag":98,"props":99,"children":100},"thead",{},[101],{"type":39,"tag":102,"props":103,"children":104},"tr",{},[105,111],{"type":39,"tag":106,"props":107,"children":108},"th",{},[109],{"type":45,"value":110},"Goal",{"type":39,"tag":106,"props":112,"children":113},{},[114],{"type":45,"value":115},"Reference",{"type":39,"tag":117,"props":118,"children":119},"tbody",{},[120,139,156,173,190,207,224,241],{"type":39,"tag":102,"props":121,"children":122},{},[123,129],{"type":39,"tag":124,"props":125,"children":126},"td",{},[127],{"type":45,"value":128},"Create a Regional hub and connect VPCs to it",{"type":39,"tag":124,"props":130,"children":131},{},[132],{"type":39,"tag":133,"props":134,"children":136},"a",{"href":135},"references\u002Fcreating-a-transit-gateway-and-attaching-vpcs.md",[137],{"type":45,"value":138},"creating a transit gateway and attaching VPCs",{"type":39,"tag":102,"props":140,"children":141},{},[142,147],{"type":39,"tag":124,"props":143,"children":144},{},[145],{"type":45,"value":146},"Isolate some VPCs while letting others share services",{"type":39,"tag":124,"props":148,"children":149},{},[150],{"type":39,"tag":133,"props":151,"children":153},{"href":152},"references\u002Fsegmenting-traffic-with-route-tables.md",[154],{"type":45,"value":155},"segmenting traffic with route tables",{"type":39,"tag":102,"props":157,"children":158},{},[159,164],{"type":39,"tag":124,"props":160,"children":161},{},[162],{"type":45,"value":163},"Send all spoke traffic out through one inspected egress VPC",{"type":39,"tag":124,"props":165,"children":166},{},[167],{"type":39,"tag":133,"props":168,"children":170},{"href":169},"references\u002Fcentralizing-egress-and-inspection.md",[171],{"type":45,"value":172},"centralizing egress and inspection",{"type":39,"tag":102,"props":174,"children":175},{},[176,181],{"type":39,"tag":124,"props":177,"children":178},{},[179],{"type":45,"value":180},"Inspect traffic between VPCs with AWS Network Firewall",{"type":39,"tag":124,"props":182,"children":183},{},[184],{"type":39,"tag":133,"props":185,"children":187},{"href":186},"references\u002Finspecting-east-west-traffic-with-network-firewall.md",[188],{"type":45,"value":189},"inspecting east-west traffic with Network Firewall",{"type":39,"tag":102,"props":191,"children":192},{},[193,198],{"type":39,"tag":124,"props":194,"children":195},{},[196],{"type":45,"value":197},"Reach on-premises networks over Site-to-Site VPN or Direct Connect",{"type":39,"tag":124,"props":199,"children":200},{},[201],{"type":39,"tag":133,"props":202,"children":204},{"href":203},"references\u002Fconnecting-on-premises-networks.md",[205],{"type":45,"value":206},"connecting on-premises networks",{"type":39,"tag":102,"props":208,"children":209},{},[210,215],{"type":39,"tag":124,"props":211,"children":212},{},[213],{"type":45,"value":214},"Link transit gateways in two Regions over the AWS network",{"type":39,"tag":124,"props":216,"children":217},{},[218],{"type":39,"tag":133,"props":219,"children":221},{"href":220},"references\u002Fpeering-transit-gateways-across-regions.md",[222],{"type":45,"value":223},"peering transit gateways across Regions",{"type":39,"tag":102,"props":225,"children":226},{},[227,232],{"type":39,"tag":124,"props":228,"children":229},{},[230],{"type":45,"value":231},"Move off a VPC peering mesh without dropping traffic",{"type":39,"tag":124,"props":233,"children":234},{},[235],{"type":39,"tag":133,"props":236,"children":238},{"href":237},"references\u002Fmigrating-from-vpc-peering.md",[239],{"type":45,"value":240},"migrating from VPC peering",{"type":39,"tag":102,"props":242,"children":243},{},[244,249],{"type":39,"tag":124,"props":245,"children":246},{},[247],{"type":45,"value":248},"Distribute IP multicast across attached VPCs",{"type":39,"tag":124,"props":250,"children":251},{},[252],{"type":39,"tag":133,"props":253,"children":255},{"href":254},"references\u002Frouting-multicast-traffic.md",[256],{"type":45,"value":257},"routing multicast traffic",{"type":39,"tag":48,"props":259,"children":261},{"id":260},"routing-notes",[262],{"type":45,"value":263},"Routing notes",{"type":39,"tag":265,"props":266,"children":267},"ul",{},[268,280,290,300,310],{"type":39,"tag":269,"props":270,"children":271},"li",{},[272,278],{"type":39,"tag":273,"props":274,"children":275},"strong",{},[276],{"type":45,"value":277},"Decide segmentation before you build.",{"type":45,"value":279}," \"Default route table association\" and \"Default route\ntable propagation\" are on by default, which wires every attachment into one open mesh. If the\ncustomer plans isolated environments, the creating reference disables the defaults up front and\nhands off to the segmenting reference. Retrofitting isolation onto an open hub is a re-architect.",{"type":39,"tag":269,"props":281,"children":282},{},[283,288],{"type":39,"tag":273,"props":284,"children":285},{},[286],{"type":45,"value":287},"North-south egress vs east-west inspection.",{"type":45,"value":289}," Centralizing egress sends spoke traffic out to\nthe internet through a central VPC. East-west inspection keeps traffic between spokes internal\nand forces it through a firewall on the way. They look similar but use different route table\nrecipes. Match the reference to the direction of traffic the customer actually has.",{"type":39,"tag":269,"props":291,"children":292},{},[293,298],{"type":39,"tag":273,"props":294,"children":295},{},[296],{"type":45,"value":297},"Appliance vs Gateway Load Balancer for inspection.",{"type":45,"value":299}," Raw third-party appliances and a Gateway\nLoad Balancer (GWLB) endpoint are two paths to the same goal. GWLB is the recommended approach\nfor new designs. Both live in the centralizing-egress reference; appliance mode and the GWLB endpoint\nroute table entries differ and the reference covers each.",{"type":39,"tag":269,"props":301,"children":302},{},[303,308],{"type":39,"tag":273,"props":304,"children":305},{},[306],{"type":45,"value":307},"Appliance mode is required for stateful cross-Availability-Zone inspection, with a tradeoff.",{"type":45,"value":309}," Appliance mode\nkeeps each flow on one Availability Zone's appliance so request and response do not split. It\nalso disables cross-Availability-Zone failover for that attachment, so the inspection design must\npair it with health-check-based failover. Both the egress and east-west references carry this.",{"type":39,"tag":269,"props":311,"children":312},{},[313,318,320,326],{"type":39,"tag":273,"props":314,"children":315},{},[316],{"type":45,"value":317},"Transit gateway side vs Direct Connect side.",{"type":45,"value":319}," The connecting-on-premises reference covers the\ntransit gateway side: Site-to-Site VPN attachment options, route propagation, and equal-cost multi-path\n(ECMP). The Direct Connect gateway and virtual interface setup belongs to the separate\n",{"type":39,"tag":66,"props":321,"children":323},{"className":322},[],[324],{"type":45,"value":325},"directconnect",{"type":45,"value":327}," skill. Do not restate the Direct Connect side here.",{"type":39,"tag":48,"props":329,"children":331},{"id":330},"security-considerations",[332],{"type":45,"value":333},"Security considerations",{"type":39,"tag":55,"props":335,"children":336},{},[337],{"type":45,"value":338},"A transit gateway is the central routing point for many VPCs and on-premises networks, so a\nmisconfiguration here has blast radius across every attached network. Apply these controls\nregardless of the specific task; each per-task reference carries the detail.",{"type":39,"tag":265,"props":340,"children":341},{},[342,347,376,381,386,391],{"type":39,"tag":269,"props":343,"children":344},{},[345],{"type":45,"value":346},"You MUST enable Transit Gateway Flow Logs for traffic visibility, audit, and incident response\nacross the hub, and MUST enable encryption at rest on the destination (a KMS key on the CloudWatch\nlog group, or SSE-KMS on the S3 bucket).",{"type":39,"tag":269,"props":348,"children":349},{},[350,352,358,360,366,368,374],{"type":45,"value":351},"You MUST, when a KMS key encrypts a flow log destination (CloudWatch log group or S3 bucket) or a\nCloudTrail destination, scope the KMS key policy with condition keys (",{"type":39,"tag":66,"props":353,"children":355},{"className":354},[],[356],{"type":45,"value":357},"aws:SourceArn",{"type":45,"value":359},",\n",{"type":39,"tag":66,"props":361,"children":363},{"className":362},[],[364],{"type":45,"value":365},"aws:SourceAccount",{"type":45,"value":367},", and ",{"type":39,"tag":66,"props":369,"children":371},{"className":370},[],[372],{"type":45,"value":373},"kms:ViaService",{"type":45,"value":375},") so only the specific log group, bucket, or trail in the\nexpected account and service can use the key, preventing cross-account or cross-service misuse.",{"type":39,"tag":269,"props":377,"children":378},{},[379],{"type":45,"value":380},"You SHOULD apply least-privilege IAM for transit gateway administration, avoiding service\nwildcards and FullAccess policies, restricting who can create attachments, modify route tables,\nand change associations or propagations.",{"type":39,"tag":269,"props":382,"children":383},{},[384],{"type":45,"value":385},"You SHOULD ensure Site-to-Site VPN tunnels use strong encryption (for example AES-256-GCM with IKEv2) and enable tunnel\nlogging to CloudWatch Logs with encryption enabled (a KMS key) to protect sensitive connection\nstate and IKE negotiation detail from unauthorized access (see the connecting on-premises networks\nreference).",{"type":39,"tag":269,"props":387,"children":388},{},[389],{"type":45,"value":390},"You MUST treat a misconfigured transit gateway route table as a security risk, since wrong\nassociations or propagations can expose workloads across environments meant to stay isolated (see\nthe segmenting traffic reference).",{"type":39,"tag":269,"props":392,"children":393},{},[394],{"type":45,"value":395},"You MUST enable AWS CloudTrail to detect unauthorized changes to transit gateway route tables,\nassociations, and propagations, MUST enable encryption at rest on the CloudTrail destination (a KMS\nkey), and use AWS Config rules to detect drift from the intended design.",{"type":39,"tag":48,"props":397,"children":399},{"id":398},"additional-resources",[400],{"type":45,"value":401},"Additional Resources",{"type":39,"tag":265,"props":403,"children":404},{},[405,416,426],{"type":39,"tag":269,"props":406,"children":407},{},[408],{"type":39,"tag":133,"props":409,"children":413},{"href":410,"rel":411},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fvpc\u002Flatest\u002Ftgw\u002Fwhat-is-transit-gateway.html",[412],"nofollow",[414],{"type":45,"value":415},"AWS Transit Gateway Guide",{"type":39,"tag":269,"props":417,"children":418},{},[419],{"type":39,"tag":133,"props":420,"children":423},{"href":421,"rel":422},"https:\u002F\u002Faws.amazon.com\u002Ftransit-gateway\u002F",[412],[424],{"type":45,"value":425},"AWS Transit Gateway product page",{"type":39,"tag":269,"props":427,"children":428},{},[429],{"type":39,"tag":133,"props":430,"children":433},{"href":431,"rel":432},"https:\u002F\u002Faws.amazon.com\u002Ftransit-gateway\u002Fpricing\u002F",[412],[434],{"type":45,"value":435},"AWS Transit Gateway pricing",{"items":437,"total":541},[438,455,470,485,500,510,525],{"slug":439,"name":439,"fn":440,"description":441,"org":442,"tags":443,"stars":21,"repoUrl":22,"updatedAt":454},"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},[444,447,450,451],{"name":445,"slug":446,"type":15},"Agents","agents",{"name":448,"slug":449,"type":15},"Automation","automation",{"name":20,"slug":8,"type":15},{"name":452,"slug":453,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":456,"name":456,"fn":457,"description":458,"org":459,"tags":460,"stars":21,"repoUrl":22,"updatedAt":469},"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},[461,462,465,468],{"name":445,"slug":446,"type":15},{"name":463,"slug":464,"type":15},"API Development","api-development",{"name":466,"slug":467,"type":15},"Authentication","authentication",{"name":20,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":471,"name":471,"fn":472,"description":473,"org":474,"tags":475,"stars":21,"repoUrl":22,"updatedAt":484},"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},[476,477,478,481],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":479,"slug":480,"type":15},"Debugging","debugging",{"name":482,"slug":483,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":486,"name":486,"fn":487,"description":488,"org":489,"tags":490,"stars":21,"repoUrl":22,"updatedAt":499},"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},[491,492,493,496],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":494,"slug":495,"type":15},"CI\u002FCD","ci-cd",{"name":497,"slug":498,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":501,"name":501,"fn":502,"description":503,"org":504,"tags":505,"stars":21,"repoUrl":22,"updatedAt":509},"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},[506,507,508],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":497,"slug":498,"type":15},"2026-07-12T08:42:51.963247",{"slug":511,"name":511,"fn":512,"description":513,"org":514,"tags":515,"stars":21,"repoUrl":22,"updatedAt":524},"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},[516,517,518,521],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":519,"slug":520,"type":15},"Best Practices","best-practices",{"name":522,"slug":523,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":526,"name":526,"fn":527,"description":528,"org":529,"tags":530,"stars":21,"repoUrl":22,"updatedAt":540},"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},[531,532,533,536,537],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":534,"slug":535,"type":15},"Evals","evals",{"name":482,"slug":483,"type":15},{"name":538,"slug":539,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",114,{"items":543,"total":660},[544,551,558,565,572,578,585,593,610,623,635,650],{"slug":439,"name":439,"fn":440,"description":441,"org":545,"tags":546,"stars":21,"repoUrl":22,"updatedAt":454},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[547,548,549,550],{"name":445,"slug":446,"type":15},{"name":448,"slug":449,"type":15},{"name":20,"slug":8,"type":15},{"name":452,"slug":453,"type":15},{"slug":456,"name":456,"fn":457,"description":458,"org":552,"tags":553,"stars":21,"repoUrl":22,"updatedAt":469},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[554,555,556,557],{"name":445,"slug":446,"type":15},{"name":463,"slug":464,"type":15},{"name":466,"slug":467,"type":15},{"name":20,"slug":8,"type":15},{"slug":471,"name":471,"fn":472,"description":473,"org":559,"tags":560,"stars":21,"repoUrl":22,"updatedAt":484},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[561,562,563,564],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":479,"slug":480,"type":15},{"name":482,"slug":483,"type":15},{"slug":486,"name":486,"fn":487,"description":488,"org":566,"tags":567,"stars":21,"repoUrl":22,"updatedAt":499},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[568,569,570,571],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":494,"slug":495,"type":15},{"name":497,"slug":498,"type":15},{"slug":501,"name":501,"fn":502,"description":503,"org":573,"tags":574,"stars":21,"repoUrl":22,"updatedAt":509},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[575,576,577],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":497,"slug":498,"type":15},{"slug":511,"name":511,"fn":512,"description":513,"org":579,"tags":580,"stars":21,"repoUrl":22,"updatedAt":524},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[581,582,583,584],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":519,"slug":520,"type":15},{"name":522,"slug":523,"type":15},{"slug":526,"name":526,"fn":527,"description":528,"org":586,"tags":587,"stars":21,"repoUrl":22,"updatedAt":540},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[588,589,590,591,592],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":534,"slug":535,"type":15},{"name":482,"slug":483,"type":15},{"name":538,"slug":539,"type":15},{"slug":594,"name":594,"fn":595,"description":596,"org":597,"tags":598,"stars":21,"repoUrl":22,"updatedAt":609},"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},[599,600,603,606],{"name":20,"slug":8,"type":15},{"name":601,"slug":602,"type":15},"Database","database",{"name":604,"slug":605,"type":15},"MySQL","mysql",{"name":607,"slug":608,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":611,"name":611,"fn":612,"description":613,"org":614,"tags":615,"stars":21,"repoUrl":22,"updatedAt":622},"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},[616,617,618,621],{"name":20,"slug":8,"type":15},{"name":601,"slug":602,"type":15},{"name":619,"slug":620,"type":15},"PostgreSQL","postgresql",{"name":607,"slug":608,"type":15},"2026-07-16T06:00:34.789624",{"slug":624,"name":624,"fn":625,"description":626,"org":627,"tags":628,"stars":21,"repoUrl":22,"updatedAt":634},"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},[629,630,631],{"name":445,"slug":446,"type":15},{"name":20,"slug":8,"type":15},{"name":632,"slug":633,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":636,"name":636,"fn":637,"description":638,"org":639,"tags":640,"stars":21,"repoUrl":22,"updatedAt":649},"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},[641,642,643,646],{"name":20,"slug":8,"type":15},{"name":601,"slug":602,"type":15},{"name":644,"slug":645,"type":15},"MongoDB","mongodb",{"name":647,"slug":648,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":651,"name":651,"fn":652,"description":653,"org":654,"tags":655,"stars":21,"repoUrl":22,"updatedAt":659},"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},[656,657,658],{"name":20,"slug":8,"type":15},{"name":601,"slug":602,"type":15},{"name":647,"slug":648,"type":15},"2026-07-16T06:00:37.690386",115]