Agentcore Patterns

Verified Amazon Bedrock AgentCore patterns for Runtime handlers, Gateway MCP clients with SigV4/IAM auth, Memory session management with Strands, and Bedrock cross-region inference-profile IAM policies. Use when building or debugging AgentCore-based agents.

43 stars 9 forksAI, LLMs & AgentsOfficial

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add aws-samples/sample-kiro-cli-multiagent-development --skill agentcore-patterns
Manual install
git clone --depth 1 https://github.com/aws-samples/sample-kiro-cli-multiagent-development.git /tmp/sample-kiro-cli-multiagent-development
mkdir -p ~/.claude/skills
cp -r /tmp/sample-kiro-cli-multiagent-development/skills/agentcore-patterns ~/.claude/skills/agentcore-patterns

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Amazon Bedrock AgentCore Patterns

Verified patterns for AgentCore Runtime, Gateway, Memory, and Bedrock IAM. Use when building or debugging AgentCore-based agents.

## Runtime Handler

The `@app.entrypoint` handler receives `payload` and `context`. The SDK inspects parameter **names** — `context` is required, not just position.

```python
from bedrock_agentcore.runtime import BedrockAgentCoreApp
app = BedrockAgentCoreApp()

@app.entrypoint
def handler(payload, context):  # param MUST be named 'context'
    session_id = getattr(context, 'session_id', 'default')
    user_message = payload.get('prompt', '')
    # ... agent logic ...
    return str(result)

app.run()
```

**Pitfall**: Using `session` instead of `context` causes `TypeError: handler() missing 1 required positional argument`.

## Gateway MCP Client (IAM Auth / SigV4)

Gateway with `IamAuthorizer` requires SigV4-signed requests. Use `mcp-proxy-for-aws`:

```python
from mcp_proxy_for_aws.client import aws_iam_streamablehttp_client
from strands.tools.mcp import MCPClient

mcp_client = MCPClient(lambda: aws_iam_streamablehttp_client(
    endpoint=gateway_url,
    aws_region='us-east-1',
    aws_service='bedrock-agentcore',
))
```

**Pitfalls**:
- `MCPClient(transport=...)` is the old API — it now takes a callable
- Plain `streamablehttp_client` without SigV4 returns 401 against IAM-authenticated Gateways
- `aws_service` must be `bedrock-agentcore`

## Memory (Strands Integration)
Read the full skill on GitHub

Details

Skill name
agentcore-patterns
Path
skills/agentcore-patterns/SKILL.md
License
MIT-0
Repo updated
9 September 2026

FAQ

What does the Agentcore Patterns skill do?

Verified Amazon Bedrock AgentCore patterns for Runtime handlers, Gateway MCP clients with SigV4/IAM auth, Memory session management with Strands, and Bedrock cross-region inference-profile IAM policies. Use when building or debugging AgentCore-based agents.

How do I install the Agentcore Patterns skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add aws-samples/sample-kiro-cli-multiagent-development --skill agentcore-patterns. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agentcore Patterns popular?

It lives in aws-samples/sample-kiro-cli-multiagent-development, which has 43 GitHub stars and 9 forks.

Related skills

AWS Technical Docs

43

aws-samples/sample-kiro-cli-multiagent-development

AWS technical documentation patterns covering procedures, lists, tables, titles, error messages, and content patterns. Use when writing AWS service documentation, procedures, troubleshooting guides, tutorials, or getting started content.

Writing & Content

CLI Execution

43

aws-samples/sample-kiro-cli-multiagent-development

CLI execution best practices covering RTK token compression, AWS discover-then-execute patterns, output control, and bash/zsh scripting with logging. Use when running CLI commands, querying AWS resources, writing automation scripts, or working with shell tooling.

Software Development

Cloudwatch Dashboards

43

aws-samples/sample-kiro-cli-multiagent-development

AWS CloudWatch dashboard observability patterns including dashboard hierarchy, widget selection, CDK implementation, metric math, alarms, and cross-account monitoring. Use when creating dashboards, setting up observability, or instrumenting workloads with CloudWatch.

Data & Analytics

Aqara Agent

48

aqara/aqara-agent-skills

aqara-agent is an official Aqara Home AI Agent skill. It supports natural-language home and space management, device inquiry, device control, ambience_create (氛围创建: apply or compose a named mood in a room or whole home via scene match then lights + optional music), ambience / mood orchestration reference, lighting effect inquiry and control (named lighting presets), device configuration (firmware/OTA upgrade only - not supported: rename devices, move devices between rooms or positions, or other device record edits outside firmware), device logs, scene management (query, execute, create, snapsh

AI, LLMs & Agents

Skill Copilot

115

javiarmesto/ALDC-AL-Development-Collection

AL Copilot capability development for Business Central. Use when implementing PromptDialog pages, AI generation features, or integrating with the Copilot toolkit.

AI, LLMs & Agents36

Correct

107

Dimon94/skills

从仓库历史找出 agent 反复犯的错误类别,逐类在能生效的最高层级让它不可能再犯,并证明新检查会在真实旧错误上失败。用于用户显式调用 /correct 或 $correct。

AI, LLMs & Agents21

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.