agent-bom discover aws
One-Command Generation of AWS AI Asset Inventory in agent-bom Specification
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: One-Command Generation of AWS AI Asset Inventory in agent-bom Specification Full Skill content: https://321skill.com/skills/agent-bom-discover-aws/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 uniformly inventorying AWS cloud-based AI Agent and MCP-related assets. In real-world operations, teams often need to manually log into multiple services (Bedrock, ECS, SageMaker, Lambda, etc.) to check resources one by one. This approach is not only inefficient but also prone to missing critical components, and it cannot generate a standardized asset inventory for subsequent audits or migration.
Usage is straightforward. Simply run this Skill in an environment where AWS credentials are configured (using AWS SSO or STS temporary credentials is recommended). It automatically invokes the AWS SDK to perform a read-only scan of all AI Agent and MCP-related resources in the current account (including Bedrock Agents, ECS tasks, SageMaker endpoints, Lambda functions, EKS clusters, Step Functions state machines, EC2 instances, etc.) and outputs a JSON inventory file compliant with the agent-bom specification. You can then pass this inventory to agent-bom for deep scanning, dependency graph generation, or compliance reporting.
It is ideal for operations engineers, agent developers, and platform architects managing multi-cloud AI infrastructure. This is especially true for teams already using agent-bom for asset tracking or those conducting AWS AI resource compliance audits, cost optimization, or migration planning.
It is recommended to integrate this Skill into CI/CD pipelines or regular inspection tasks for automated asset inventorying. Note that it performs read-only operations and will not modify any cloud resources; however, ensure the AWS credentials used have read-only permissions for the relevant services (e.g., bedrock:ListAgents, ecs:ListClusters). The output file is saved in the current directory by default, but you can specify a path.
Key Features
Unlike manually writing scripts or using AWS Config, agent-bom-discover-aws not only scans resources but also automatically generates a standardized JSON inventory compliant with the agent-bom specification. This output can be directly fed into agent-bom's dependency analysis, policy checks, and export functions without requiring additional format conversion.
Limitations
Requires a Python 3.11+ environment and the agent-bom library (installable from PyPI). It only supports the AWS cloud platform, and the scan scope is limited by the read-only permissions and region configuration of the current credentials.
FAQ
What AWS permissions are required?
Read-only permissions for the relevant services are required, such as `bedrock:ListAgents`, `ecs:ListClusters`, `sagemaker:ListNotebookInstances`, etc. Using AWS SSO or STS temporary credentials with a read-only policy is recommended.
Are all AWS regions supported?
Yes. It uses the default region of the current credentials by default, but you can also specify a region via the AWS_REGION environment variable.
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/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/raw/index.md