The Agent Skills Directory

[SAFE]: The skill implements safety checkpoints by requiring explicit user approval before performing destructive or high-cost operations, such as deleting files or pushing code changes.
[SAFE]: Data flow between agents is managed through structured templates (Input/Output/Handoff), which acts as a boundary marker to prevent accidental instruction execution from processed data.
[SAFE]: Command execution is limited to standard, non-privileged operations (e.g., git status, ls) necessary for the skill's stated purpose of task coordination and environment awareness.
[SAFE]: No obfuscation, hardcoded credentials, or unauthorized remote code execution patterns were found in the instructions or reference materials.

orchestrator