[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-coordinating-multi-space-devops-agent":3,"mdc--tyjs20-key":35,"related-repo-aws-coordinating-multi-space-devops-agent":812,"related-org-aws-coordinating-multi-space-devops-agent":916},{"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},"coordinating-multi-space-devops-agent","coordinate multi-space AWS DevOps agents","Coordinate the AWS DevOps Agent across multiple AgentSpaces from one Claude Code session — route questions to the right space (prod vs staging vs knowledge), query several spaces in parallel and synthesize, or compare findings across accounts. Use whenever the user has more than one AgentSpace configured, mentions multiple AWS accounts, or asks something like \"check both prod and staging\", \"compare across accounts\", or \"ask the knowledge space\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,21],{"name":13,"slug":14,"type":15},"DevOps","devops","tag",{"name":17,"slug":18,"type":15},"Agents","agents",{"name":20,"slug":8,"type":15},"AWS",{"name":22,"slug":23,"type":15},"Multi-Agent","multi-agent",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-12T08:44:16.331085",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\u002Fplugins\u002Faws-agents-for-devsecops\u002Fskills\u002Fcoordinating-multi-space-devops-agent","---\nname: coordinating-multi-space-devops-agent\ndescription: Coordinate the AWS DevOps Agent across multiple AgentSpaces from one Claude Code session — route questions to the right space (prod vs staging vs knowledge), query several spaces in parallel and synthesize, or compare findings across accounts. Use whenever the user has more than one AgentSpace configured, mentions multiple AWS accounts, or asks something like \"check both prod and staging\", \"compare across accounts\", or \"ask the knowledge space\".\n---\n\n# Querying multiple AgentSpaces\n\n## Pre-flight\n\nIf `aws_devops_agent__list_agent_spaces` is **not** in your available tools, the remote MCP server is not connected. Tell the user to ask \"help me set up the AWS DevOps Agent\" so the `setup-devops-agent` skill auto-loads.\n\n## Prerequisite: SigV4 auth required\n\nMulti-space routing requires **SigV4 authentication** — Bearer tokens are scoped to a single AgentSpace and cannot route to other spaces.\n\nMany real teams run **more than one AgentSpace** — typically a production space, a staging space, and a dedicated \"knowledge\" space that holds runbooks shared across accounts. Each space has its own set of associated AWS accounts, runbooks, and history.\n\nThis skill is the routing brain. Use it when the user has multiple spaces configured, or when a question genuinely spans accounts.\n\n## Discovering spaces\n\n```\naws_devops_agent__list_agent_spaces()\n→ {\"agentSpaces\": [{\"agentSpaceId\": \"as-abc123\", \"name\": \"prod\"}, ...]}\n```\n\nIf only one space is returned, this skill doesn't apply — use `chatting-with-aws-devops-agent` or `investigating-incidents-with-aws-devops-agent` directly (no `agent_space_id` needed).\n\nIf more than one is returned, decide whether the user's question is:\n\n| Question shape | Strategy |\n|---------------|----------|\n| Scoped to one environment (\"prod is broken\") | Single space — pick the matching one |\n| Spans environments (\"compare prod vs staging\") | **Parallel** — query each, synthesize |\n| Generic knowledge (\"what runbooks do we have for ECS?\") | Route to the **knowledge** space if one is named that way |\n| Ambiguous (\"our service is slow\") | **Ask the user** which environment, don't guess |\n\n## Per-session routing memory\n\nIf the user has a routing guide stored locally (e.g. `.claude\u002Faws-agents-for-devsecops.md`, `AGENTS.md`, or per-project notes), read it once at the start of the session and use it as the routing table for the rest of the conversation. Format expected:\n\n```markdown\n| Space | AWS Profile | Agent Space ID | Purpose |\n|-------|-------------|----------------|---------|\n| prod  | acme-prod   | as-abc123      | Production incidents, customer-facing services |\n| stage | acme-stage  | as-def456      | Pre-prod validation, integration testing |\n| kb    | acme-shared | as-ghi789      | Shared runbooks, cross-account knowledge |\n```\n\nIf no guide exists, run discovery:\n\n1. `aws_devops_agent__list_agent_spaces()` → get all spaces.\n2. For each space: `aws_devops_agent__chat(message=\"Summarize the AWS accounts, services, and runbooks you have access to.\", agent_space_id=\"\u003CSPACE_ID>\")` → get a one-paragraph summary.\n3. Offer to write the routing guide to the project (e.g. `.claude\u002Faws-agents-for-devsecops.md`, `AGENTS.md`, or per-project notes) so future sessions skip discovery.\n\n## Pattern A — Parallel queries, one synthesized answer\n\nUse when the user wants a comparison: \"compare prod and staging error rates\", \"is this issue happening in both accounts?\", \"audit costs across all our environments\".\n\n```\n# 1. Query each space in parallel with environment-specific context\naws_devops_agent__chat(message=\"\u003Cquestion> | env=prod | \u003Cprod IaC context>\", agent_space_id=\"PROD_ID\")\n→ {\"executionId\": \"...\", \"answer\": \"...\"}\n\naws_devops_agent__chat(message=\"\u003Cquestion> | env=stage | \u003Cstage IaC context>\", agent_space_id=\"STAGE_ID\")\n→ {\"executionId\": \"...\", \"answer\": \"...\"}\n\n# 2. Synthesize locally — present a side-by-side summary, not two separate dumps\n```\n\n**Don't just paste both responses.** Read both, identify what's the same vs. different, and tell the user the *delta* — that's the value.\n\n## Pattern B — Knowledge lookup, then per-space action\n\nUse when one space holds runbooks\u002Fknowledge that informs work in another space.\n\n```\n# 1. Ask the knowledge space first\naws_devops_agent__chat(\n    message=\"What's our standard runbook for ECS 503 errors?\",\n    agent_space_id=\"KB_ID\"\n)\n→ {\"answer\": \"\u003Crunbook text>\"}\n\n# 2. Apply that runbook in the target environment\naws_devops_agent__investigate(\n    title=\"ECS 503 errors on checkout-service. [Runbook from knowledge space] \u003Crunbook text> [Local context] ...\",\n    agent_space_id=\"PROD_ID\",\n    priority=\"HIGH\"\n)\n```\n\nThe DevOps Agent doesn't share state between spaces — you bridge it by quoting the knowledge space's response into the investigation's `title`.\n\n## Pattern C — Targeted single-space query\n\nUse when the user explicitly names a space or environment.\n\n```\n# Pick the matching agentSpaceId from your routing memory, pass it on the call\naws_devops_agent__chat(message=\"\u003Cquestion>\", agent_space_id=\"\u003Cmatched_space_id>\")\n```\n\nIf the routing is ambiguous and the user doesn't say, **ask once** — better than firing into the wrong account.\n\n## Pattern D — Investigations don't share state\n\nInvestigations are per-space. If an issue spans accounts, you may need *two* investigations:\n\n```\naws_devops_agent__investigate(title=\"Latency spike — prod side\", agent_space_id=\"PROD_ID\", priority=\"HIGH\")\naws_devops_agent__investigate(title=\"Latency spike — stage side\", agent_space_id=\"STAGE_ID\", priority=\"HIGH\")\n```\n\nTrack both `taskId`s. Poll both. Surface findings together.\n\nThis is rare — usually one space owns the problem. Don't fan out by default.\n\n## What NOT to do\n\n- **Don't blast every space with every question.** It's slow, expensive, and the user has to read 3× as much output.\n- **Don't fan out without verifying scope.** If a space's `description` or recorded coverage doesn't mention the relevant service, skip it — sending a question into a scope-mismatched space typically hangs rather than returning \"I don't know.\"\n- **Don't fire investigations in parallel by default.** They take 5–8 minutes each. Pick the one space that owns the incident.\n- **Don't silently switch spaces mid-conversation.** If a follow-up needs a different space, tell the user: \"Switching to the knowledge space to look up the runbook.\"\n\n## Timeout guidance\n\nThe `chat` tool buffers the full response server-side before returning. Complex cross-account queries can take 30-90s per space. If a space doesn't respond within 90s, it's likely a scope mismatch — surface a message like \"Space X did not respond within 90s — skipping (likely scope mismatch)\" and move on rather than hanging.\n\n## See also\n\n- `examples\u002Fmulti-space-walkthrough.md` for a fully worked scenario (prod incident with staging comparison and knowledge-space runbook lookup).\n- The `setup-devops-agent` skill for first-time configuration of multiple AgentSpaces, AWS profiles, and shell wrappers.\n",{"data":36,"body":37},{"name":4,"description":6},{"type":38,"children":39},"root",[40,49,56,87,93,105,117,122,128,140,169,174,271,277,298,498,503,550,556,561,570,588,594,599,608,621,627,632,641,653,659,671,680,693,698,704,756,762,775,781,806],{"type":41,"tag":42,"props":43,"children":45},"element","h1",{"id":44},"querying-multiple-agentspaces",[46],{"type":47,"value":48},"text","Querying multiple AgentSpaces",{"type":41,"tag":50,"props":51,"children":53},"h2",{"id":52},"pre-flight",[54],{"type":47,"value":55},"Pre-flight",{"type":41,"tag":57,"props":58,"children":59},"p",{},[60,62,69,71,77,79,85],{"type":47,"value":61},"If ",{"type":41,"tag":63,"props":64,"children":66},"code",{"className":65},[],[67],{"type":47,"value":68},"aws_devops_agent__list_agent_spaces",{"type":47,"value":70}," is ",{"type":41,"tag":72,"props":73,"children":74},"strong",{},[75],{"type":47,"value":76},"not",{"type":47,"value":78}," in your available tools, the remote MCP server is not connected. Tell the user to ask \"help me set up the AWS DevOps Agent\" so the ",{"type":41,"tag":63,"props":80,"children":82},{"className":81},[],[83],{"type":47,"value":84},"setup-devops-agent",{"type":47,"value":86}," skill auto-loads.",{"type":41,"tag":50,"props":88,"children":90},{"id":89},"prerequisite-sigv4-auth-required",[91],{"type":47,"value":92},"Prerequisite: SigV4 auth required",{"type":41,"tag":57,"props":94,"children":95},{},[96,98,103],{"type":47,"value":97},"Multi-space routing requires ",{"type":41,"tag":72,"props":99,"children":100},{},[101],{"type":47,"value":102},"SigV4 authentication",{"type":47,"value":104}," — Bearer tokens are scoped to a single AgentSpace and cannot route to other spaces.",{"type":41,"tag":57,"props":106,"children":107},{},[108,110,115],{"type":47,"value":109},"Many real teams run ",{"type":41,"tag":72,"props":111,"children":112},{},[113],{"type":47,"value":114},"more than one AgentSpace",{"type":47,"value":116}," — typically a production space, a staging space, and a dedicated \"knowledge\" space that holds runbooks shared across accounts. Each space has its own set of associated AWS accounts, runbooks, and history.",{"type":41,"tag":57,"props":118,"children":119},{},[120],{"type":47,"value":121},"This skill is the routing brain. Use it when the user has multiple spaces configured, or when a question genuinely spans accounts.",{"type":41,"tag":50,"props":123,"children":125},{"id":124},"discovering-spaces",[126],{"type":47,"value":127},"Discovering spaces",{"type":41,"tag":129,"props":130,"children":134},"pre",{"className":131,"code":133,"language":47},[132],"language-text","aws_devops_agent__list_agent_spaces()\n→ {\"agentSpaces\": [{\"agentSpaceId\": \"as-abc123\", \"name\": \"prod\"}, ...]}\n",[135],{"type":41,"tag":63,"props":136,"children":138},{"__ignoreMap":137},"",[139],{"type":47,"value":133},{"type":41,"tag":57,"props":141,"children":142},{},[143,145,151,153,159,161,167],{"type":47,"value":144},"If only one space is returned, this skill doesn't apply — use ",{"type":41,"tag":63,"props":146,"children":148},{"className":147},[],[149],{"type":47,"value":150},"chatting-with-aws-devops-agent",{"type":47,"value":152}," or ",{"type":41,"tag":63,"props":154,"children":156},{"className":155},[],[157],{"type":47,"value":158},"investigating-incidents-with-aws-devops-agent",{"type":47,"value":160}," directly (no ",{"type":41,"tag":63,"props":162,"children":164},{"className":163},[],[165],{"type":47,"value":166},"agent_space_id",{"type":47,"value":168}," needed).",{"type":41,"tag":57,"props":170,"children":171},{},[172],{"type":47,"value":173},"If more than one is returned, decide whether the user's question is:",{"type":41,"tag":175,"props":176,"children":177},"table",{},[178,197],{"type":41,"tag":179,"props":180,"children":181},"thead",{},[182],{"type":41,"tag":183,"props":184,"children":185},"tr",{},[186,192],{"type":41,"tag":187,"props":188,"children":189},"th",{},[190],{"type":47,"value":191},"Question shape",{"type":41,"tag":187,"props":193,"children":194},{},[195],{"type":47,"value":196},"Strategy",{"type":41,"tag":198,"props":199,"children":200},"tbody",{},[201,215,233,253],{"type":41,"tag":183,"props":202,"children":203},{},[204,210],{"type":41,"tag":205,"props":206,"children":207},"td",{},[208],{"type":47,"value":209},"Scoped to one environment (\"prod is broken\")",{"type":41,"tag":205,"props":211,"children":212},{},[213],{"type":47,"value":214},"Single space — pick the matching one",{"type":41,"tag":183,"props":216,"children":217},{},[218,223],{"type":41,"tag":205,"props":219,"children":220},{},[221],{"type":47,"value":222},"Spans environments (\"compare prod vs staging\")",{"type":41,"tag":205,"props":224,"children":225},{},[226,231],{"type":41,"tag":72,"props":227,"children":228},{},[229],{"type":47,"value":230},"Parallel",{"type":47,"value":232}," — query each, synthesize",{"type":41,"tag":183,"props":234,"children":235},{},[236,241],{"type":41,"tag":205,"props":237,"children":238},{},[239],{"type":47,"value":240},"Generic knowledge (\"what runbooks do we have for ECS?\")",{"type":41,"tag":205,"props":242,"children":243},{},[244,246,251],{"type":47,"value":245},"Route to the ",{"type":41,"tag":72,"props":247,"children":248},{},[249],{"type":47,"value":250},"knowledge",{"type":47,"value":252}," space if one is named that way",{"type":41,"tag":183,"props":254,"children":255},{},[256,261],{"type":41,"tag":205,"props":257,"children":258},{},[259],{"type":47,"value":260},"Ambiguous (\"our service is slow\")",{"type":41,"tag":205,"props":262,"children":263},{},[264,269],{"type":41,"tag":72,"props":265,"children":266},{},[267],{"type":47,"value":268},"Ask the user",{"type":47,"value":270}," which environment, don't guess",{"type":41,"tag":50,"props":272,"children":274},{"id":273},"per-session-routing-memory",[275],{"type":47,"value":276},"Per-session routing memory",{"type":41,"tag":57,"props":278,"children":279},{},[280,282,288,290,296],{"type":47,"value":281},"If the user has a routing guide stored locally (e.g. ",{"type":41,"tag":63,"props":283,"children":285},{"className":284},[],[286],{"type":47,"value":287},".claude\u002Faws-agents-for-devsecops.md",{"type":47,"value":289},", ",{"type":41,"tag":63,"props":291,"children":293},{"className":292},[],[294],{"type":47,"value":295},"AGENTS.md",{"type":47,"value":297},", or per-project notes), read it once at the start of the session and use it as the routing table for the rest of the conversation. Format expected:",{"type":41,"tag":129,"props":299,"children":303},{"className":300,"code":301,"language":302,"meta":137,"style":137},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","| Space | AWS Profile | Agent Space ID | Purpose |\n|-------|-------------|----------------|---------|\n| prod  | acme-prod   | as-abc123      | Production incidents, customer-facing services |\n| stage | acme-stage  | as-def456      | Pre-prod validation, integration testing |\n| kb    | acme-shared | as-ghi789      | Shared runbooks, cross-account knowledge |\n","markdown",[304],{"type":41,"tag":63,"props":305,"children":306},{"__ignoreMap":137},[307,357,366,410,454],{"type":41,"tag":308,"props":309,"children":312},"span",{"class":310,"line":311},"line",1,[313,319,325,329,334,338,343,347,352],{"type":41,"tag":308,"props":314,"children":316},{"style":315},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[317],{"type":47,"value":318},"|",{"type":41,"tag":308,"props":320,"children":322},{"style":321},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[323],{"type":47,"value":324}," Space ",{"type":41,"tag":308,"props":326,"children":327},{"style":315},[328],{"type":47,"value":318},{"type":41,"tag":308,"props":330,"children":331},{"style":321},[332],{"type":47,"value":333}," AWS Profile ",{"type":41,"tag":308,"props":335,"children":336},{"style":315},[337],{"type":47,"value":318},{"type":41,"tag":308,"props":339,"children":340},{"style":321},[341],{"type":47,"value":342}," Agent Space ID ",{"type":41,"tag":308,"props":344,"children":345},{"style":315},[346],{"type":47,"value":318},{"type":41,"tag":308,"props":348,"children":349},{"style":321},[350],{"type":47,"value":351}," Purpose ",{"type":41,"tag":308,"props":353,"children":354},{"style":315},[355],{"type":47,"value":356},"|\n",{"type":41,"tag":308,"props":358,"children":360},{"class":310,"line":359},2,[361],{"type":41,"tag":308,"props":362,"children":363},{"style":315},[364],{"type":47,"value":365},"|-------|-------------|----------------|---------|\n",{"type":41,"tag":308,"props":367,"children":369},{"class":310,"line":368},3,[370,374,379,383,388,392,397,401,406],{"type":41,"tag":308,"props":371,"children":372},{"style":315},[373],{"type":47,"value":318},{"type":41,"tag":308,"props":375,"children":376},{"style":321},[377],{"type":47,"value":378}," prod  ",{"type":41,"tag":308,"props":380,"children":381},{"style":315},[382],{"type":47,"value":318},{"type":41,"tag":308,"props":384,"children":385},{"style":321},[386],{"type":47,"value":387}," acme-prod   ",{"type":41,"tag":308,"props":389,"children":390},{"style":315},[391],{"type":47,"value":318},{"type":41,"tag":308,"props":393,"children":394},{"style":321},[395],{"type":47,"value":396}," as-abc123      ",{"type":41,"tag":308,"props":398,"children":399},{"style":315},[400],{"type":47,"value":318},{"type":41,"tag":308,"props":402,"children":403},{"style":321},[404],{"type":47,"value":405}," Production incidents, customer-facing services ",{"type":41,"tag":308,"props":407,"children":408},{"style":315},[409],{"type":47,"value":356},{"type":41,"tag":308,"props":411,"children":413},{"class":310,"line":412},4,[414,418,423,427,432,436,441,445,450],{"type":41,"tag":308,"props":415,"children":416},{"style":315},[417],{"type":47,"value":318},{"type":41,"tag":308,"props":419,"children":420},{"style":321},[421],{"type":47,"value":422}," stage ",{"type":41,"tag":308,"props":424,"children":425},{"style":315},[426],{"type":47,"value":318},{"type":41,"tag":308,"props":428,"children":429},{"style":321},[430],{"type":47,"value":431}," acme-stage  ",{"type":41,"tag":308,"props":433,"children":434},{"style":315},[435],{"type":47,"value":318},{"type":41,"tag":308,"props":437,"children":438},{"style":321},[439],{"type":47,"value":440}," as-def456      ",{"type":41,"tag":308,"props":442,"children":443},{"style":315},[444],{"type":47,"value":318},{"type":41,"tag":308,"props":446,"children":447},{"style":321},[448],{"type":47,"value":449}," Pre-prod validation, integration testing ",{"type":41,"tag":308,"props":451,"children":452},{"style":315},[453],{"type":47,"value":356},{"type":41,"tag":308,"props":455,"children":457},{"class":310,"line":456},5,[458,462,467,471,476,480,485,489,494],{"type":41,"tag":308,"props":459,"children":460},{"style":315},[461],{"type":47,"value":318},{"type":41,"tag":308,"props":463,"children":464},{"style":321},[465],{"type":47,"value":466}," kb    ",{"type":41,"tag":308,"props":468,"children":469},{"style":315},[470],{"type":47,"value":318},{"type":41,"tag":308,"props":472,"children":473},{"style":321},[474],{"type":47,"value":475}," acme-shared ",{"type":41,"tag":308,"props":477,"children":478},{"style":315},[479],{"type":47,"value":318},{"type":41,"tag":308,"props":481,"children":482},{"style":321},[483],{"type":47,"value":484}," as-ghi789      ",{"type":41,"tag":308,"props":486,"children":487},{"style":315},[488],{"type":47,"value":318},{"type":41,"tag":308,"props":490,"children":491},{"style":321},[492],{"type":47,"value":493}," Shared runbooks, cross-account knowledge ",{"type":41,"tag":308,"props":495,"children":496},{"style":315},[497],{"type":47,"value":356},{"type":41,"tag":57,"props":499,"children":500},{},[501],{"type":47,"value":502},"If no guide exists, run discovery:",{"type":41,"tag":504,"props":505,"children":506},"ol",{},[507,519,532],{"type":41,"tag":508,"props":509,"children":510},"li",{},[511,517],{"type":41,"tag":63,"props":512,"children":514},{"className":513},[],[515],{"type":47,"value":516},"aws_devops_agent__list_agent_spaces()",{"type":47,"value":518}," → get all spaces.",{"type":41,"tag":508,"props":520,"children":521},{},[522,524,530],{"type":47,"value":523},"For each space: ",{"type":41,"tag":63,"props":525,"children":527},{"className":526},[],[528],{"type":47,"value":529},"aws_devops_agent__chat(message=\"Summarize the AWS accounts, services, and runbooks you have access to.\", agent_space_id=\"\u003CSPACE_ID>\")",{"type":47,"value":531}," → get a one-paragraph summary.",{"type":41,"tag":508,"props":533,"children":534},{},[535,537,542,543,548],{"type":47,"value":536},"Offer to write the routing guide to the project (e.g. ",{"type":41,"tag":63,"props":538,"children":540},{"className":539},[],[541],{"type":47,"value":287},{"type":47,"value":289},{"type":41,"tag":63,"props":544,"children":546},{"className":545},[],[547],{"type":47,"value":295},{"type":47,"value":549},", or per-project notes) so future sessions skip discovery.",{"type":41,"tag":50,"props":551,"children":553},{"id":552},"pattern-a-parallel-queries-one-synthesized-answer",[554],{"type":47,"value":555},"Pattern A — Parallel queries, one synthesized answer",{"type":41,"tag":57,"props":557,"children":558},{},[559],{"type":47,"value":560},"Use when the user wants a comparison: \"compare prod and staging error rates\", \"is this issue happening in both accounts?\", \"audit costs across all our environments\".",{"type":41,"tag":129,"props":562,"children":565},{"className":563,"code":564,"language":47},[132],"# 1. Query each space in parallel with environment-specific context\naws_devops_agent__chat(message=\"\u003Cquestion> | env=prod | \u003Cprod IaC context>\", agent_space_id=\"PROD_ID\")\n→ {\"executionId\": \"...\", \"answer\": \"...\"}\n\naws_devops_agent__chat(message=\"\u003Cquestion> | env=stage | \u003Cstage IaC context>\", agent_space_id=\"STAGE_ID\")\n→ {\"executionId\": \"...\", \"answer\": \"...\"}\n\n# 2. Synthesize locally — present a side-by-side summary, not two separate dumps\n",[566],{"type":41,"tag":63,"props":567,"children":568},{"__ignoreMap":137},[569],{"type":47,"value":564},{"type":41,"tag":57,"props":571,"children":572},{},[573,578,580,586],{"type":41,"tag":72,"props":574,"children":575},{},[576],{"type":47,"value":577},"Don't just paste both responses.",{"type":47,"value":579}," Read both, identify what's the same vs. different, and tell the user the ",{"type":41,"tag":581,"props":582,"children":583},"em",{},[584],{"type":47,"value":585},"delta",{"type":47,"value":587}," — that's the value.",{"type":41,"tag":50,"props":589,"children":591},{"id":590},"pattern-b-knowledge-lookup-then-per-space-action",[592],{"type":47,"value":593},"Pattern B — Knowledge lookup, then per-space action",{"type":41,"tag":57,"props":595,"children":596},{},[597],{"type":47,"value":598},"Use when one space holds runbooks\u002Fknowledge that informs work in another space.",{"type":41,"tag":129,"props":600,"children":603},{"className":601,"code":602,"language":47},[132],"# 1. Ask the knowledge space first\naws_devops_agent__chat(\n    message=\"What's our standard runbook for ECS 503 errors?\",\n    agent_space_id=\"KB_ID\"\n)\n→ {\"answer\": \"\u003Crunbook text>\"}\n\n# 2. Apply that runbook in the target environment\naws_devops_agent__investigate(\n    title=\"ECS 503 errors on checkout-service. [Runbook from knowledge space] \u003Crunbook text> [Local context] ...\",\n    agent_space_id=\"PROD_ID\",\n    priority=\"HIGH\"\n)\n",[604],{"type":41,"tag":63,"props":605,"children":606},{"__ignoreMap":137},[607],{"type":47,"value":602},{"type":41,"tag":57,"props":609,"children":610},{},[611,613,619],{"type":47,"value":612},"The DevOps Agent doesn't share state between spaces — you bridge it by quoting the knowledge space's response into the investigation's ",{"type":41,"tag":63,"props":614,"children":616},{"className":615},[],[617],{"type":47,"value":618},"title",{"type":47,"value":620},".",{"type":41,"tag":50,"props":622,"children":624},{"id":623},"pattern-c-targeted-single-space-query",[625],{"type":47,"value":626},"Pattern C — Targeted single-space query",{"type":41,"tag":57,"props":628,"children":629},{},[630],{"type":47,"value":631},"Use when the user explicitly names a space or environment.",{"type":41,"tag":129,"props":633,"children":636},{"className":634,"code":635,"language":47},[132],"# Pick the matching agentSpaceId from your routing memory, pass it on the call\naws_devops_agent__chat(message=\"\u003Cquestion>\", agent_space_id=\"\u003Cmatched_space_id>\")\n",[637],{"type":41,"tag":63,"props":638,"children":639},{"__ignoreMap":137},[640],{"type":47,"value":635},{"type":41,"tag":57,"props":642,"children":643},{},[644,646,651],{"type":47,"value":645},"If the routing is ambiguous and the user doesn't say, ",{"type":41,"tag":72,"props":647,"children":648},{},[649],{"type":47,"value":650},"ask once",{"type":47,"value":652}," — better than firing into the wrong account.",{"type":41,"tag":50,"props":654,"children":656},{"id":655},"pattern-d-investigations-dont-share-state",[657],{"type":47,"value":658},"Pattern D — Investigations don't share state",{"type":41,"tag":57,"props":660,"children":661},{},[662,664,669],{"type":47,"value":663},"Investigations are per-space. If an issue spans accounts, you may need ",{"type":41,"tag":581,"props":665,"children":666},{},[667],{"type":47,"value":668},"two",{"type":47,"value":670}," investigations:",{"type":41,"tag":129,"props":672,"children":675},{"className":673,"code":674,"language":47},[132],"aws_devops_agent__investigate(title=\"Latency spike — prod side\", agent_space_id=\"PROD_ID\", priority=\"HIGH\")\naws_devops_agent__investigate(title=\"Latency spike — stage side\", agent_space_id=\"STAGE_ID\", priority=\"HIGH\")\n",[676],{"type":41,"tag":63,"props":677,"children":678},{"__ignoreMap":137},[679],{"type":47,"value":674},{"type":41,"tag":57,"props":681,"children":682},{},[683,685,691],{"type":47,"value":684},"Track both ",{"type":41,"tag":63,"props":686,"children":688},{"className":687},[],[689],{"type":47,"value":690},"taskId",{"type":47,"value":692},"s. Poll both. Surface findings together.",{"type":41,"tag":57,"props":694,"children":695},{},[696],{"type":47,"value":697},"This is rare — usually one space owns the problem. Don't fan out by default.",{"type":41,"tag":50,"props":699,"children":701},{"id":700},"what-not-to-do",[702],{"type":47,"value":703},"What NOT to do",{"type":41,"tag":705,"props":706,"children":707},"ul",{},[708,718,736,746],{"type":41,"tag":508,"props":709,"children":710},{},[711,716],{"type":41,"tag":72,"props":712,"children":713},{},[714],{"type":47,"value":715},"Don't blast every space with every question.",{"type":47,"value":717}," It's slow, expensive, and the user has to read 3× as much output.",{"type":41,"tag":508,"props":719,"children":720},{},[721,726,728,734],{"type":41,"tag":72,"props":722,"children":723},{},[724],{"type":47,"value":725},"Don't fan out without verifying scope.",{"type":47,"value":727}," If a space's ",{"type":41,"tag":63,"props":729,"children":731},{"className":730},[],[732],{"type":47,"value":733},"description",{"type":47,"value":735}," or recorded coverage doesn't mention the relevant service, skip it — sending a question into a scope-mismatched space typically hangs rather than returning \"I don't know.\"",{"type":41,"tag":508,"props":737,"children":738},{},[739,744],{"type":41,"tag":72,"props":740,"children":741},{},[742],{"type":47,"value":743},"Don't fire investigations in parallel by default.",{"type":47,"value":745}," They take 5–8 minutes each. Pick the one space that owns the incident.",{"type":41,"tag":508,"props":747,"children":748},{},[749,754],{"type":41,"tag":72,"props":750,"children":751},{},[752],{"type":47,"value":753},"Don't silently switch spaces mid-conversation.",{"type":47,"value":755}," If a follow-up needs a different space, tell the user: \"Switching to the knowledge space to look up the runbook.\"",{"type":41,"tag":50,"props":757,"children":759},{"id":758},"timeout-guidance",[760],{"type":47,"value":761},"Timeout guidance",{"type":41,"tag":57,"props":763,"children":764},{},[765,767,773],{"type":47,"value":766},"The ",{"type":41,"tag":63,"props":768,"children":770},{"className":769},[],[771],{"type":47,"value":772},"chat",{"type":47,"value":774}," tool buffers the full response server-side before returning. Complex cross-account queries can take 30-90s per space. If a space doesn't respond within 90s, it's likely a scope mismatch — surface a message like \"Space X did not respond within 90s — skipping (likely scope mismatch)\" and move on rather than hanging.",{"type":41,"tag":50,"props":776,"children":778},{"id":777},"see-also",[779],{"type":47,"value":780},"See also",{"type":41,"tag":705,"props":782,"children":783},{},[784,795],{"type":41,"tag":508,"props":785,"children":786},{},[787,793],{"type":41,"tag":63,"props":788,"children":790},{"className":789},[],[791],{"type":47,"value":792},"examples\u002Fmulti-space-walkthrough.md",{"type":47,"value":794}," for a fully worked scenario (prod incident with staging comparison and knowledge-space runbook lookup).",{"type":41,"tag":508,"props":796,"children":797},{},[798,799,804],{"type":47,"value":766},{"type":41,"tag":63,"props":800,"children":802},{"className":801},[],[803],{"type":47,"value":84},{"type":47,"value":805}," skill for first-time configuration of multiple AgentSpaces, AWS profiles, and shell wrappers.",{"type":41,"tag":807,"props":808,"children":809},"style",{},[810],{"type":47,"value":811},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":813,"total":915},[814,829,844,859,874,884,899],{"slug":815,"name":815,"fn":816,"description":817,"org":818,"tags":819,"stars":24,"repoUrl":25,"updatedAt":828},"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},[820,821,824,825],{"name":17,"slug":18,"type":15},{"name":822,"slug":823,"type":15},"Automation","automation",{"name":20,"slug":8,"type":15},{"name":826,"slug":827,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":830,"name":830,"fn":831,"description":832,"org":833,"tags":834,"stars":24,"repoUrl":25,"updatedAt":843},"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},[835,836,839,842],{"name":17,"slug":18,"type":15},{"name":837,"slug":838,"type":15},"API Development","api-development",{"name":840,"slug":841,"type":15},"Authentication","authentication",{"name":20,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":845,"name":845,"fn":846,"description":847,"org":848,"tags":849,"stars":24,"repoUrl":25,"updatedAt":858},"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},[850,851,852,855],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":853,"slug":854,"type":15},"Debugging","debugging",{"name":856,"slug":857,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":860,"name":860,"fn":861,"description":862,"org":863,"tags":864,"stars":24,"repoUrl":25,"updatedAt":873},"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},[865,866,867,870],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":868,"slug":869,"type":15},"CI\u002FCD","ci-cd",{"name":871,"slug":872,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":875,"name":875,"fn":876,"description":877,"org":878,"tags":879,"stars":24,"repoUrl":25,"updatedAt":883},"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},[880,881,882],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":871,"slug":872,"type":15},"2026-07-12T08:42:51.963247",{"slug":885,"name":885,"fn":886,"description":887,"org":888,"tags":889,"stars":24,"repoUrl":25,"updatedAt":898},"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},[890,891,892,895],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":893,"slug":894,"type":15},"Best Practices","best-practices",{"name":896,"slug":897,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":900,"name":900,"fn":901,"description":902,"org":903,"tags":904,"stars":24,"repoUrl":25,"updatedAt":914},"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},[905,906,907,910,911],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":908,"slug":909,"type":15},"Evals","evals",{"name":856,"slug":857,"type":15},{"name":912,"slug":913,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",114,{"items":917,"total":1034},[918,925,932,939,946,952,959,967,984,997,1009,1024],{"slug":815,"name":815,"fn":816,"description":817,"org":919,"tags":920,"stars":24,"repoUrl":25,"updatedAt":828},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[921,922,923,924],{"name":17,"slug":18,"type":15},{"name":822,"slug":823,"type":15},{"name":20,"slug":8,"type":15},{"name":826,"slug":827,"type":15},{"slug":830,"name":830,"fn":831,"description":832,"org":926,"tags":927,"stars":24,"repoUrl":25,"updatedAt":843},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[928,929,930,931],{"name":17,"slug":18,"type":15},{"name":837,"slug":838,"type":15},{"name":840,"slug":841,"type":15},{"name":20,"slug":8,"type":15},{"slug":845,"name":845,"fn":846,"description":847,"org":933,"tags":934,"stars":24,"repoUrl":25,"updatedAt":858},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[935,936,937,938],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":853,"slug":854,"type":15},{"name":856,"slug":857,"type":15},{"slug":860,"name":860,"fn":861,"description":862,"org":940,"tags":941,"stars":24,"repoUrl":25,"updatedAt":873},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[942,943,944,945],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":868,"slug":869,"type":15},{"name":871,"slug":872,"type":15},{"slug":875,"name":875,"fn":876,"description":877,"org":947,"tags":948,"stars":24,"repoUrl":25,"updatedAt":883},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[949,950,951],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":871,"slug":872,"type":15},{"slug":885,"name":885,"fn":886,"description":887,"org":953,"tags":954,"stars":24,"repoUrl":25,"updatedAt":898},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[955,956,957,958],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":893,"slug":894,"type":15},{"name":896,"slug":897,"type":15},{"slug":900,"name":900,"fn":901,"description":902,"org":960,"tags":961,"stars":24,"repoUrl":25,"updatedAt":914},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[962,963,964,965,966],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":908,"slug":909,"type":15},{"name":856,"slug":857,"type":15},{"name":912,"slug":913,"type":15},{"slug":968,"name":968,"fn":969,"description":970,"org":971,"tags":972,"stars":24,"repoUrl":25,"updatedAt":983},"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},[973,974,977,980],{"name":20,"slug":8,"type":15},{"name":975,"slug":976,"type":15},"Database","database",{"name":978,"slug":979,"type":15},"MySQL","mysql",{"name":981,"slug":982,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":985,"name":985,"fn":986,"description":987,"org":988,"tags":989,"stars":24,"repoUrl":25,"updatedAt":996},"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},[990,991,992,995],{"name":20,"slug":8,"type":15},{"name":975,"slug":976,"type":15},{"name":993,"slug":994,"type":15},"PostgreSQL","postgresql",{"name":981,"slug":982,"type":15},"2026-07-16T06:00:34.789624",{"slug":998,"name":998,"fn":999,"description":1000,"org":1001,"tags":1002,"stars":24,"repoUrl":25,"updatedAt":1008},"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},[1003,1004,1005],{"name":17,"slug":18,"type":15},{"name":20,"slug":8,"type":15},{"name":1006,"slug":1007,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":1010,"name":1010,"fn":1011,"description":1012,"org":1013,"tags":1014,"stars":24,"repoUrl":25,"updatedAt":1023},"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},[1015,1016,1017,1020],{"name":20,"slug":8,"type":15},{"name":975,"slug":976,"type":15},{"name":1018,"slug":1019,"type":15},"MongoDB","mongodb",{"name":1021,"slug":1022,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":1025,"name":1025,"fn":1026,"description":1027,"org":1028,"tags":1029,"stars":24,"repoUrl":25,"updatedAt":1033},"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},[1030,1031,1032],{"name":20,"slug":8,"type":15},{"name":975,"slug":976,"type":15},{"name":1021,"slug":1022,"type":15},"2026-07-16T06:00:37.690386",115]