From aws-agents
Sets up evaluators, online monitoring, CI/CD quality gates, CloudWatch/X-Ray observability, and cost optimization for AgentCore agents to measure and improve quality and performance.
npx claudepluginhub aws/agent-toolkit-for-aws --plugin aws-agentsThis skill is limited to using the following tools:
Measure and improve your AgentCore agent's quality through evaluation, monitoring, and observability.
Builds, evaluates, and monitors AI agents using Opik: architecture patterns, metrics like hallucination and task completion, production observability, debugging, and best practices.
Generates production checklists for AgentCore agents: IAM scoping, inbound auth (JWT/SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, quotas.
Designs observability for multi-agent systems with per-agent metrics, aggregate stats, agent cards, and event streams to monitor execution, track costs, log activities, and debug workflows.
Share bugs, ideas, or general feedback.
Measure and improve your AgentCore agent's quality through evaluation, monitoring, and observability.
Do NOT use for:
agents-debugagents-harden$ARGUMENTS can be:
Run agentcore --version. This skill requires v0.9.0 or later.
Read agentcore/agentcore.json to understand existing evaluators, online eval configs, and agent setup.
If agentcore/agentcore.json is not found:
"This skill requires an AgentCore project. Use
agents-get-startedto create one."
| Developer intent | Action |
|---|---|
| Measure quality, add evaluator, run eval, CI/CD gate, online monitoring | Load references/evals.md and follow its workflow |
| Set up observability, CloudWatch, X-Ray, logs, metrics, dashboards | Load references/observability.md and follow its workflow |
| Understand or reduce AgentCore costs | Load references/cost.md |
| Both — "I want to understand and improve my agent" | Start with observability setup, then add evals |
The reference file contains the full procedure. Follow it step by step.
agents-harden for production readinessagents-debug for root cause analysisagents-buildDepends on the workflow — see the loaded reference for specific outputs.