← ClaudeAtlas

agentcore-harness-builderlisted

Build production-ready AWS Bedrock AgentCore Harness agents end to end — declarative model + prompt, managed/BYO Memory, built-in Browser, Code Interpreter, Web Search and Knowledge Bases (RAG), Gateway/MCP tools + rate limits, inline functions, Skills (incl. AWS catalog), versioning + endpoints, advanced config (truncation, limits, lifecycle, network, inbound auth, BYO S3 Files/EFS mounts or container), Observability (log delivery), Evaluations, Optimizations, Identity (outbound auth, Token Vault, BYO secrets), Policy (Cedar + temporal), Payments, Registry, Runtime Instances (14-day EC2 sessions), Step Functions, export to Strands code. Use whenever the user wants to create, configure, deploy, version, wire, harden, invoke, or troubleshoot an AgentCore Harness — or asks about AgentCore best practices, harness.json, CreateHarness/UpdateHarness/InvokeHarness, endpoints/qualifiers, Memory, knowledge bases/RAG, or observability. Trigger even for a managed declarative Bedrock agent with no "harness" mention.
timwukp/agent-skills-best-practice · ★ 11 · AI & Automation · score 80
Install: claude install-skill timwukp/agent-skills-best-practice
# AWS Bedrock AgentCore Harness Builder ## Overview A **Harness** is AWS Bedrock AgentCore's declarative, fully-managed way to run an agent. You hand AWS a JSON configuration — model, system prompt, tools, memory, skills, limits — and AWS runs the agent loop (Strands under the hood) inside a per-session Firecracker microVM with its own filesystem and shell. No container to build by default (a custom image via `environmentArtifact` is an advanced option), no agent loop to write. You change behavior by changing config, not redeploying code, and you can override model/prompt per invocation. This skill builds a **complete, best-practice Harness use case** that exercises every AgentCore capability the user needs, wired correctly the first time. Harness is **generally available** (GA 2026-06-17, all AWS Commercial Regions where AgentCore is available, plus GovCloud US-West since 2026-08; only Payments remains preview), but it is still fast-moving and the real API shapes often differ from the published docs — this skill encodes the hard-won facts so you don't rediscover them through validation errors. ### The two-plane mental model (internalize this first) AgentCore has two distinct API surfaces. Confusing them is the #1 source of wasted time. | Plane | What it is | How you call it | |---|---|---| | **Control plane** | Create/configure/inspect resources (harness, memory, runtimes) | `boto3.client("bedrock-agentcore-control")` — `create_harness`, `update_harness`, `create_memor