The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (scaffold_execplan.py, validate_context_pack.py, and validate_execplan.py) to manage the lifecycle of plan artifacts. These scripts use standard Python libraries for file I/O, regex validation, and project root discovery via git, and do not perform any privileged or dangerous system operations.
[SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were identified. The skill incorporates explicit human-in-the-loop verification gates ('STOP and @ASK_USER_CONFIRMATION') that prevent the agent from proceeding without recorded user approval, mitigating risks of unintended behavior or assumption-based errors.

create-execplan