agent-bom discover aws
Discover AWS AI assets and generate standardized inventory
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: agent-bom discover aws. It is used for: Discover AWS AI assets and generate standardized inventory Full Skill content: https://321skill.com/skills/agent-bom-discover-aws-x-7/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the challenge of quickly discovering AI Agent and MCP-related assets within an AWS cloud environment and generating a standardized inventory. In real-world operations or development, teams often need to inventory resources such as Bedrock Agent, ECS, SageMaker, Lambda, EKS, Step Functions, and EC2. Manual collection is time-consuming and prone to omissions, while granting long-term cloud credentials directly to a tool poses security risks.
Usage is straightforward: ensure Python 3.11+ and the agent-bom tool are installed locally, and obtain short-term read-only credentials via AWS SSO, WebIdentity, or STS. Then, use a natural language instruction (e.g., "Inventory the Bedrock Agent and ECS services under the current AWS account") to trigger a scan. The tool automatically calls the AWS SDK to read resources, generates a JSON inventory file compliant with the agent-bom specification, and outputs it to a specified path. Throughout the process, credentials remain within the operator's environment and are never exposed to third parties.
It is ideal for operations engineers, agent development teams, and security/compliance personnel who need to regularly audit AWS AI infrastructure. Organizations already using agent-bom for asset management and scanning can seamlessly integrate this discovery capability without additional configuration. It is particularly useful for scenarios requiring a quick understanding of AI resource distribution in the cloud to provide a data foundation for subsequent policy analysis or cost optimization.
It is recommended to use this in conjunction with agent-bom's scanning functionality when managing multi-account AWS environments centrally: first perform discovery to generate the inventory, then conduct security policy checks or dependency analysis as needed. Note that it only supports read-only operations and will not modify any cloud resources. It also requires the operator to have read-only permissions for the corresponding AWS services, with a preference for using short-term credentials to reduce risk.
Key Features
Unlike AWS Config or AWS Resource Explorer, it specifically focuses on AI Agent and MCP-related assets (e.g., Bedrock, SageMaker, Lambda) and outputs an inventory in the agent-bom standard format, facilitating subsequent policy scanning and dependency analysis. Furthermore, it never requires long-term cloud credentials, offering higher security.
Limitations
Requires a Python 3.11+ environment, the agent-bom tool installed, and the operator must obtain short-term read-only credentials via AWS SSO/WebIdentity/STS. It only supports the AWS cloud platform.
FAQ
Do I need to provide AWS access keys?
No. The tool uses the operator's existing AWS SDK credential chain, prioritizing short-term credentials from AWS SSO, WebIdentity, or STS. It will not ask for long-term keys to be pasted.
Which AWS services are supported?
Supports AI and MCP-related services such as Bedrock Agent, ECS, SageMaker, Lambda, EKS, Step Functions, and EC2. Services can be enabled or disabled via configuration.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agent-bom-discover-aws-x-7/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover aws, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-aws-x-7/raw/index.md