The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown files that guide the agent in maintaining project documentation like CONTEXT.md and Architectural Decision Records (ADRs).
[NO_CODE]: No scripts, executables, or code-based logic are included in the skill. It relies solely on natural language instructions for the agent's behavior.
[SAFE]: There are no indicators of prompt injection, data exfiltration, or obfuscation. The skill does not request access to sensitive environment variables or perform any network requests.
[SAFE]: The platform configuration in agents/openai.yaml is minimal and does not grant any elevated privileges or access to dangerous tools.

domain-modeling