agent-bom discover aws
Discover AI Agent assets on AWS and generate a 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 AI Agent assets on AWS and generate a standardized inventory Full Skill content: https://321skill.com/skills/agent-bom-discover-aws-x/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 inventorying AI Agent and MCP-related assets within the AWS cloud environment. Operations or development personnel often need to manually log into the console or write temporary scripts to gather resource information from services like Bedrock, ECS, SageMaker, Lambda, EKS, Step Functions, and EC2—a process that is both tedious and prone to omissions. With a single natural language instruction, this Skill automatically discovers and outputs a standardized inventory JSON compliant with the agent-bom specification.
Usage is straightforward. Simply run the Skill in an environment where short-term AWS credentials (such as AWS SSO, WebIdentity, or STS) are already configured. It automatically invokes the AWS SDK for read-only scanning, organizes discovered assets—including AI Agents, workloads, and infrastructure—into a standardized inventory JSON file, and saves it to your specified path. You can then optionally pass this inventory to the agent-bom tool for further analysis, dependency graph generation, or security policy creation.
It is particularly well-suited for operations engineers, agent developers, and cloud architects who need to manage AI infrastructure on AWS in a unified manner. This is especially valuable for teams or individuals already using the agent-bom ecosystem who wish to continuously track changes to their cloud-based AI assets in a standardized way while mitigating the risk of long-term credential exposure.
We recommend integrating this Skill into CI/CD pipelines or regular inspection tasks to automate asset inventorying. Please note: it requires a Python 3.11+ environment and depends on the agent-bom library (installable from PyPI). Before operation, ensure your AWS credentials are short-term, valid, and possess read-only permissions; avoid using long-term access keys.
Key Features
Unlike manually writing AWS CLI scripts or using CloudFormation resource collectors, this Skill directly outputs inventory JSON compliant with the agent-bom specification, making it natively compatible with subsequent agent-bom analysis workflows (such as generating dependency graphs or security policies). It also enforces the use of short-term credentials and read-only IAM policies, mitigating the risk of long-term credential exposure.
Limitations
Requires Python 3.11+, the agent-bom library (`pip install agent-bom`), and depends on the availability of short-term AWS credentials (AWS SSO/WebIdentity/STS) in the operational environment. Resource discovery is limited to the scope permitted by the configured read-only IAM policy.
FAQ
What dependencies does this Skill require?
It requires Python 3.11+ and the agent-bom library, which can be installed via `pip install agent-bom`. Additionally, short-term AWS credentials (e.g., AWS SSO or STS) must be configured.
Which AWS services does it support for discovery?
It supports AI-related and infrastructure services such as Bedrock Agent, ECS, SageMaker, Lambda, EKS, Step Functions, and EC2. The specific scope depends on the authorizations granted by the configured read-only IAM policy.
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/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/raw/index.md