The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Grep tool to search for specific strings like TODO, FIXME, console.log, and placeholder across the codebase. This is a standard part of its health-check functionality.
[DATA_EXPOSURE]: The skill reads project metadata from CLAUDE.md and various files in production/ and design/ directories to populate the checklist. This access is scoped to the project environment and required for its intended purpose.
[SAFE]: No malicious patterns such as prompt injection, obfuscation, or remote code execution were found. The skill does not request network access, preventing data exfiltration risks.

launch-checklist