From openaca
Generate an OpenACA Agent BOM when the user asks for a bill of materials, Agent BOM, inventory export, or structured list of agent components.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openaca:bom [endpoint|repo] [optional output path][endpoint|repo] [optional output path]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the user asks for an Agent BOM, a structured
Use this skill when the user asks for an Agent BOM, a structured inventory, a CycloneDX export, or a reusable snapshot of agent composition.
uvx --isolated --from openaca openaca bom endpoint --output openaca-agent-bom.json
uvx --isolated --from openaca openaca bom endpoint --project /path/to/project --output openaca-agent-bom.json
uvx --isolated --from openaca openaca bom repo --target /path/to/repo --output openaca-agent-bom.json
If uvx is unavailable but openaca is installed, use the same command
without the uvx prefix.
Describe the Agent BOM as composition data: what components exist, how they are related, and where they were observed. Keep findings separate: scan results and advisories reference BOM components, but the BOM itself is inventory.
When useful, suggest scanning the stored BOM with the current corpus for advisory matches:
uvx --isolated --from openaca openaca scan bom -v --input openaca-agent-bom.json
scan bom cannot surface posture findings — configuration-hygiene
rules (mutable install refs, MCP auto-approval, missing remote auth,
insecure transport) require live endpoint/project configuration that
isn't serialized into the CycloneDX BOM. For posture, run a fresh
endpoint or repo scan with --include-posture instead.
Do not paste the full BOM into chat unless the user asks. BOMs can contain local paths, URLs, component names, and source provenance. Prefer a concise summary and leave the file in the workspace.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub open-agent-security/openaca-claude-plugin --plugin openaca