The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local shell script init-brain.sh to create template files in the project workspace. It also references a Python script heartbeat.py located in the agent's internal skills directory for logging task outcomes. These commands are used for initialization and state management within the local environment.
[DATA_EXPOSURE]: The skill is designed to selectively read markdown files from a local .agent/brain/ directory to incorporate brand voice and audience context into the agent's responses. This is a controlled retrieval of local project data and does not involve sending information to external servers.
[SAFE]: No obfuscation, prompt injection, remote code downloads, or credential harvesting patterns were found. The code and instructions are consistent with the stated purpose of modularizing business context.

business-brain