Beyond Assistance: The Executive Power of 'Agent Plugins for AWS'

Source: Dev.to

Agent Plugins for AWS

Agent Plugins for AWS – released by AWS Labs on GitHub in February 2026 – is a plugin library that grants executable skill sets to AI agents. Unlike simple code‑completion or natural‑language assistance, these plugins enable AI agents to perform real actions on AWS.

Key Points

• Officially supported as a Claude Code plugin.
• Available through the Cursor marketplace for easy installation.
• Provides an end‑to‑end workflow:
  1. AI‑driven design assistance
  2. Recommendations & cost estimation
  3. Infrastructure‑as‑Code (IaC) generation
  4. Deployment to AWS

Repository

awslabs / agent-plugins

Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.

Important: Generative AI can make mistakes. You should consider reviewing all output and costs generated by your chosen AI model and agentic coding assistant. See the AWS Responsible AI Policy.

Agent plugins are currently supported by Claude Code.

Plugins

Installation

Claude Code

Add the marketplace

/plugin marketplace add awslabs/agent-plugins

Install a plugin

/plugin install deploy-on-aws@agent-plugins-for-aws

Cursor

Use the official Cursor marketplace to install the plugins from this repository. For additional information, please refer to the documentation.

1. Open Cursor Settings → Plugins.
2. In the search bar, type aws.
3. Select the plugin you want to install, click Add to Cursor, then choose the scope.
4. …and you’re ready to go.

Why It’s More Than Just a “Completion Tool”

Previously, development support using LLMs typically followed these patterns:

• Providing natural‑language advice in response to questions like, “How should I implement this architecture on AWS?”
• Humans designing and coding based on that advice.
• Deployment and testing performed manually by humans.

In this flow, the AI’s role is centered on design assistance, while the actual application to the environment depends on humans.

In contrast, Agent Plugins for AWS is a suite of plugins that allows AI agents to proactively handle everything from Design → Recommendations → Cost Estimation → IaC Generation → Deployment. This is qualitatively different from automation tools that simply suggest command completions or trigger a CLI via natural language.

Differences from CLI Automation: Why It’s Not Just “Terminal Operations”

Many might think that with current tools like Claude Code or various AI CLIs, one can already:

• Generate IaC.
• Execute the AWS CLI.
• Proceed to deployment without manual intervention (provided that agent mode is enabled with appropriate permissions).

If we look solely at whether it can be executed, traditional CLI‑based agent environments can perform similar tasks.

So, what is the differentiator for Agent Plugins for AWS?

The difference lies not in executability, but in the layer at which the capability is integrated.

1. Ad‑hoc Inference vs. Structured Capability

In CLI‑based automation, the agent reasons from a prompt each time to generate and execute commands. Design decisions and service selections rely on the model’s internal knowledge and the immediate context.

Agent Plugins for AWS explicitly defines the AWS design workflow itself—Analyze → Recommend → Estimate → Generate → Deploy—as an extended capability of the agent. This is not just a sequence of commands; it is a capability that stages the entire design process.

In other words, it shifts from a model that “executes operations thought up on the spot” to one that “internalizes the AWS design process as a structured capability.”

Mechanisms like Claude’s Skills or Kiro Powers can grant agents additional specialized knowledge or scripts, but they act as modules to enhance behavior for specific domains. They do not systematize the entire design workflow.

Agent Plugins for AWS packages the full sequence from design to execution and provides it as a capability integrated with live data (pricing, documentation, etc.) via MCP.

2. Inference‑Centric vs. Live‑Data‑Connected

While recommendations and generation are possible via CLI execution alone, those judgments rely on the model’s internal training data.

Agent Plugins connects via MCP servers to:

• awsknowledge – official documentation
• awspricing – real‑time pricing
• aws‑iac‑mcp – IaC best practices

This ensures that design recommendations and cost estimates are tied to the latest official information and real‑world data. The distinction is not whether it can be done, but whether the information sources backing the judgment are systematically integrated.

3. Operational Automation vs. Domain Capability Expansion

CLI automation primarily makes operations more efficient.

Agent Plugins grants the agent specific AWS domain knowledge, such as:

• Service‑selection logic
• Cost‑evaluation flows
• IaC output patterns

Thus, it expands the design capability within the AWS domain rather than merely automating command execution.

Positioning in the Capability Stack

Structurally, Agent Plugins sits in the following layer:

While CLI automation optimizes the CLI / API Execution Layer, Agent Plugins adds an AWS Domain Capability intermediate layer above it. This design elevates the agent’s capability stack rather than simply adding another tool.

Organizational Perspective

CLI automation improves individual efficiency.
Agent Plugins standardizes the design workflow, which becomes significant at the organizational level:

• Reproducibility of designs
• Consistency in cost evaluation
• Uniformity of IaC output
• Reviewable rationales for recommendations

Standardization of Processes

Therefore, its differentiator is not “replacing the CLI,” but “stacking AWS‑specific capabilities on top of the CLI.” If CLI automation is the “execution foundation,” Agent Plugins is the “capability‑extension layer” built upon it.

Basic Structure and Workflow of Agent Plugins

Agent Plugins for AWS is a collection of plugin modules that grant AWS‑related functionalities to AI agents. According to the README, the goal is to provide skills that allow AI coding agents to assist with everything from AWS design and deployment to operations.

The 5‑Step Workflow

Real‑Data Integration Powered by MCP Servers

The Model Context Protocol (MCP) server is the crucial underlying mechanism supporting the utility of Agent Plugins. MCP is a standardized protocol for connecting AI models to external data sources and tools. AWS‑side MCP servers provide official documentation, pricing, and best practices.

Welcome to Open‑Source MCP Servers for AWS

• Get started with open‑source MCP Servers for AWS and learn core features.

Source: awslabs.github.io

Key MCP Servers

These servers allow the agent to refer to the latest live data rather than relying solely on the model’s internal knowledge.

Real‑World Value

1. Cloud Migration & Architecture Design Support

In traditional cloud migration, humans handle multiple phases: analyzing current setups, selecting services, decision‑making based on costs, designing IaC, and deploying.

With Agent Plugins, a single natural‑language instruction such as:

“I want to optimize this project for an AWS serverless architecture and deploy it.”

triggers recommendations, cost comparisons, IaC generation, and execution, dramatically reducing manual effort while ensuring design accuracy.

2. Formalizing Team Knowledge

The tacit knowledge of veteran designers often leads to siloing. Because Agent Plugins outputs the rationale for recommendations, costs, and IaC, knowledge sharing and reviews become much easier, resulting in:

• Transparency in the design‑decision process.
• Formalization of best practices.
• Reduced learning costs for new members.

3. Integration with CI/CD and Quality Evaluation

Generated IaC and configurations can be integrated directly into CI/CD pipelines:

• Automatic IaC validation in pull requests.
• Cost‑comparison reports attached to the review stage.
• Links to automated deployment‑approval workflows.

Considerations and Risks

• Model Errors and Recency – As stated in the official README, outputs may contain errors; all results require human review.
• Security and Permissions – Careful design of AWS CLI and IAM settings is essential. Risks increase with excessive permissions; establishing proper approval flows for automated deployments is vital.

Future Outlook

Agent Plugins for AWS is a foundation for evolving AI agents from “explanatory assistants” into “orchestration engines for execution.” The underlying MCP servers and ecosystem (Claude, Cursor, etc.) are continuously developing, potentially leading to further automation of cloud operations.

AWS has announced the preview of the AWS MCP Server, a remote/fully‑managed Model Context Protocol server. This suggests a direction where governance—such as authentication/authorization via IAM and log collection via CloudTrail—will be natively supported.

https://aws.amazon.com/about-aws/whats-new/2025/11/aws-mcp-server/

Conclusion

Agent Plugins for AWS represents a significant evolution that moves the role of AI from “assistance” to “execution.” By providing a foundation based on real‑time data, consistent workflows, and reasoned support, it enables both productivity and quality in cloud design, migration, and operations.