The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git rev-parse --show-toplevel and git rev-parse --abbrev-ref HEAD to identify the project root and current branch. These are standard, safe commands used to ensure that files are created in the appropriate project-specific directories.
[SAFE]: The skill possesses a surface for indirect prompt injection as it ingests ticket data (description, acceptance criteria) from Atlassian MCP. However, the risk is mitigated by a mandatory human-in-the-loop checkpoint where the agent must 'ask for permission to proceed' before writing any proposed planning steps to the filesystem. Additionally, it implements basic sanitization for branch-related strings.

dev-plan