agentcore-patterns
/agentcore-patterns
This skill should be used when an automated agent's output is published under its own identity and carries weight in someone else's work, such as a reviewer whose verdict lands on a pull request, and the open question is how much authority it has actually earned. Covers which conclusions such an agent may state as settled and which it must hand to a person, why a verdict that moves between runs on unchanged input cannot be allowed to decide anything, handing an uncertain item to a human rather than discarding it, grounding each claim in something computed rather than recalled, and the publishe
- Author
- awslabs ↗
- Repository
- startups ↗
- Licence
- Apache-2.0
- Last repository change
- 26.10.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
This skill should be used when an automated agent's output is published under its own identity and carries weight in someone else's work, such as a reviewer whose verdict lands on a pull request, and the open question is how much authority it has actually earned. Covers which conclusions such an agent may state as settled and which it must hand to a person, why a verdict that moves between runs on unchanged input cannot be allowed to decide anything, handing an uncertain item to a human rather than discarding it, grounding each claim in something computed rather than recalled, and the publishe
Original author description
This skill should be used when an automated agent's output is published under its own identity and carries weight in someone else's work, such as a reviewer whose verdict lands on a pull request, and the open question is how much authority it has actually earned. Covers which conclusions such an agent may state as settled and which it must hand to a person, why a verdict that moves between runs on unchanged input cannot be allowed to decide anything, handing an uncertain item to a human rather than discarding it, grounding each claim in something computed rather than recalled, and the publishe
How it works
- Reference files
- Upstream skills to defer to
SKILL.md preview
---
name: agentcore-patterns
description: "This skill should be used when an automated agent's output is published under its own identity and carries weight in someone else's work, such as a reviewer whose verdict lands on a pull request, and the open question is how much authority it has actually earned. Covers which conclusions such an agent may state as settled and which it must hand to a person, why a verdict that moves between runs on unchanged input cannot be allowed to decide anything, handing an uncertain item to a human rather than discarding it, grounding each claim in something computed rather than recalled, and the published-state and recall behaviour that decides whether people keep reading the output or learn to skim it. It should also be used when such an agent is being ignored, contradicts itself between runs, or reports a state that nothing current supports. Not for measuring or improving an agent's own output quality, which belongs to aws-agents:agents-optimize, nor for building, deploying, or hardening an agent."
license: Apache-2.0
metadata:
audience: startup
---
# AgentCore Patterns
Apply these patterns to agents that act inside an engineering pipeline rather than serving end users. Upstream `aws-agents` owns the build, deploy, and hardening mechanics. What it does not cover is the judgment layer, which is where these agents actually fail.
Treat one constraint as primary: nobody is available to babysit the agent. A judge that is wrong, slow, or noisy will not be tuned over a quarter by a platform team. It gets ignored, and then it is worse than nothing, because it occupies the slot where review attention used to be.
Design for that outcome. Measure stability before granting an agent authority to block, report a stance on every axis so silence is never ambiguous, and compute in code anything the judgment depends on.
## Reference files
- **`references/git-code-reviewer-agent.md`**: Read before letting any agent's output
carry weight in someone else's work. End-to-end wiring for a pull-request reviewer,
from the credential identity that decides whether a verdict can be recorded at all,
through reading the pull request as data, the trigger that reaches a credentialed
runtime, what the agent should remember between runs, and the judgment design that
decides whether anyone keeps reading the output. Written as field notes, including
the failures.
## Upstream skills to defer to
Do not restate the mechanics these own. Invoke them directly:
- **`Skill("aws-agents:agents-build")`**: Agent construction, tools, prompts, memory, and multi-agent composition.
- **`Skill("aws-agents:agents-deploy")`**: Container contract, deployment, versioning, rollback, and deploy-failure diagnosis.
- **`Skill("aws-agents:agents-harden")`**: IAM scoping, inbound auth, secret handling, session lifecycle, and quotas.
- **`Skill("aws-agents:agents-debug")`**: Traces, logs, and diagnosis of a deployed agent.
- **`Skill("aws-agents:agents-optimize")`**: Evaluators, online monitoring, CI/CD quality gates, observability, and latency and token-cost tuning. **Read this first if the goal is to measure an agent's quality.** It owns the evaluator and quality-gate machinery; this skill covers only the narrower case where the agent _is_ the gate, and the question is whether its verdicts are stable enough to carry authority.
- **`Skill("aws-core:amazon-bedrock")`**: Model invocation, prompt caching, and throttling diagnosis.
- **`Skill("aws-core:aws-ai-ml")`**: Model selection and inference-cost comparison.
For runtime selection before any of this applies, such as AgentCore against Lambda or ECS, use `Skill("aws-startup-advisor:agent-advisor")`.
Files in this package (2)
- SKILL.md 4 KB
- references/git-code-reviewer-agent.md 42 KB
Versions
The database has no other skills named agentcore-patterns.
Database snapshot: 13.11.2026 · package version 23814f976a93 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100agentcore
Deep-dive into Amazon Bedrock AgentCore platform design, service selection, deployment, and production operations. This skill should be used when the user asks to "design an AgentCore architecture", "deploy agents on AgentCore", "configure AgentCore Runtime", "set up AgentCore… - 100human-in-the-loop-escalation
Define the decisions an agent must hand back to a person instead of making alone. Use when an agent can act on systems where a wrong call is expensive or irreversible - 100deploy-to-agentcore
Deploy the Biodiversity Anomaly Detection agent to Amazon Bedrock AgentCore Runtime using the AgentCore CLI (@aws/agentcore). Use this skill when the user asks to deploy, ship, or promote the local agent to AgentCore, or to invoke the deployed agent. Fills the gateway env vars,… - 100aws-agentic-ai
AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations. Covers agent deployment,… - 100amazon-bedrock-agentcore
Expert guide for designing, developing, testing, and deploying AI agent products using Amazon Bedrock AgentCore. Covers ALL AgentCore components (Runtime, Gateway/MCP, Memory, Identity, Browser, Code Interpreter, Observability, Evaluations, Policy, Registry, Payments) with CDK… - 90aws-agentcore
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…