{"slug":"aws-agentcore","title":"aws-agentcore","summary":"Build, test, migrate, integrate, and deploy Amazon Bedrock AgentCore agents. Use for AgentCore runtime, local development, import/migration, deployment, Memory, Gateway/MCP tools, Identity, Observability, Browser, Code Interpreter, Evaluations, Registry, Payments, policy, and har","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-10-05T21:50:50.361658Z","repo":{"url":"https://github.com/VincentChuWaiChow/vanguard-frontier-agentic","stars":24,"forks":3,"license":"Apache-2.0","updatedAt":"2026-10-05T13:00:24Z"},"bodyHtml":"<hr>\n<h2>name: aws-agentcore\ndescription: Build, test, migrate, integrate, and deploy Amazon Bedrock AgentCore agents. Use for AgentCore runtime, local development, import/migration, deployment, Memory, Gateway/MCP tools, Identity, Observability, Browser, Code Interpreter, Evaluations, Registry, Payments, policy, and harness-vs-code-path decisions. Load references only when that component is needed.\nallowed-tools: Read Edit Write MultiEdit Grep Glob Bash\nmetadata:\nauthor: \"github: VincentChuWaiChow\"\nversion: \"0.1.8\"\nupdated: \"2026-06-02\"\ncategory: ai</h2>\n<h1>AWS AgentCore</h1>\n<h2>Purpose</h2>\n<p>Build and operate Amazon Bedrock AgentCore agents without stuffing runtime, harness, Memory, Gateway, Identity, Observability, Browser, Code Interpreter, Evaluations, Registry, Payments, policy, and environment/skills details into every prompt.</p>\n<h2>When to use</h2>\n<p>Use this skill when the user asks to:</p>\n<ul>\n<li>create or adapt an AgentCore project,</li>\n<li>configure local development, invocation, packaging, deployment, runtime settings, harness settings, or environment/skills paths,</li>\n<li>integrate AgentCore Memory, Gateway, MCP tools, Identity, Observability, Browser, Code Interpreter, Evaluations, Registry, or Payments,</li>\n<li>review AgentCore security, least privilege, policy, tool exposure, credential handling, migration, or production readiness.</li>\n</ul>\n<h2>Lean operating rules</h2>\n<ul>\n<li>First decide whether the user has an existing agent or needs a new project. Do not scaffold over an existing codebase.</li>\n<li>For new projects, prefer the npm AgentCore CLI package <code>@aws/agentcore</code> because current AWS documentation recommends it.</li>\n<li>Treat the Python starter toolkit as legacy/migration-oriented unless the user is explicitly working inside an existing Python-based toolkit workflow.</li>\n<li>Separate code-based agents from config-based harnesses. Do not mix their guidance casually; current AWS docs describe the harness path as preview.</li>\n<li>Prefer current AWS documentation tools for AgentCore service behavior. Use the component facts and sampled live evidence in <code>references/official-sources.md</code>; when the user has configured read-only AWS MCP access, use exposed read-only tools for current-state evidence instead of guessing.</li>\n<li>Treat CLI syntax as version-sensitive; verify exact commands with installed tooling before production use.</li>\n<li>Treat Gateway policy, identity propagation, skill-path and filesystem loading, observability prerequisites, evaluation loops, registry governance, and payment spending controls as first-class concerns, not afterthoughts.</li>\n<li>Never ask users to paste AWS credentials, client secrets, access tokens, account IDs, customer data, or private keys into chat.</li>\n<li>Load only the reference needed for the component in scope.</li>\n</ul>\n<h2>References</h2>\n<p>Load these only when needed:</p>\n<ul>\n<li><a href=\"references/workflow-and-output.md\">Workflow and output contract</a> — use for end-to-end AgentCore project, local test, deployment, and output formatting.</li>\n<li><a href=\"references/safety-checklist.md\">Safety checklist</a> — use before deployment, tool exposure, credential integration, Memory/Gateway changes, or production recommendations.</li>\n<li><a href=\"references/official-sources.md\">Official sources</a> — use when grounding current AgentCore service behavior and docs URLs.</li>\n<li><a href=\"references/getting-started.md\">Getting started</a> — use for project/runtime/harness/local workflow details, direct code deployment, filesystem mounts, and CLI/Inspector caveats, then verify commands against current toolkit version.</li>\n<li><a href=\"references/memory-integration.md\">Memory integration</a> — use only for AgentCore Memory resource and agent wiring work.</li>\n<li><a href=\"references/gateway-integration.md\">Gateway integration</a> — use only for Gateway, MCP tools, and tool target integration.</li>\n</ul>\n<h2>Response minimum</h2>\n<p>Return, at minimum:</p>\n<ul>\n<li>the AgentCore component in scope,</li>\n<li>evidence level and docs/tooling used,</li>\n<li>safest next action,</li>\n<li>command or code path to verify,</li>\n<li>security and rollback caveats.</li>\n</ul>\n","files":[{"path":"agents/openai.yaml","sizeBytes":742,"isText":true},{"path":"metadata.json","sizeBytes":4028,"isText":true},{"path":"references/gateway-integration.md","sizeBytes":6577,"isText":true},{"path":"references/getting-started.md","sizeBytes":6450,"isText":true},{"path":"references/memory-integration.md","sizeBytes":5567,"isText":true},{"path":"references/official-sources.md","sizeBytes":11036,"isText":true},{"path":"references/safety-checklist.md","sizeBytes":3206,"isText":true},{"path":"references/workflow-and-output.md","sizeBytes":3630,"isText":true},{"path":"SKILL.md","sizeBytes":3909,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-10-05T21:52:29.811593Z","sha256":"808E190B37875CCF31A92EEC0F03FDBBF4E26F5F8136674F6409D2E83A5CC8B0","sizeBytes":18986},"review":null,"source":{"repositoryUrl":"https://github.com/VincentChuWaiChow/vanguard-frontier-agentic","path":"skills/aws/aws-agentcore","license":"Apache-2.0","commit":"febe32a08e78fd06b1e466187410d673f1958d87","subtreeSha":"08B6D676C91BCD6C1878610E6FD285AA843E689A80740749EC0F5D2112AAED80","lastSyncedAt":"2026-10-05T21:51:58.639905Z"},"reviewedAt":"2026-10-05T21:55:17.910255Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/VincentChuWaiChow/vanguard-frontier-agentic/tree/master/skills/aws/aws-agentcore"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install vincentchuwaichow-vanguard-frontier-agentic@llmmart"},{"target":"git","command":"git clone https://github.com/VincentChuWaiChow/vanguard-frontier-agentic.git"}]}