The Agent Skills Directory

[SAFE]: The skill instructions establish a clear operational boundary, explicitly stating that planning does not authorize product edits or persistent artifacts, which prevents unintended system changes.
[SAFE]: The process requires the agent to verify dependencies and feasibility before committing to a plan, encouraging safe and predictable behavior.
[SAFE]: No evidence of prompt injection, obfuscation, data exfiltration, or unauthorized command execution was found. The skill relies on standard project verification tools and user approvals.

plan-it