The Agent Skills Directory

[SAFE]: The skill is designed for information retrieval from local project files such as CLAUDE.md and the openspec/changes/ directory.
[SAFE]: No network communication or data exfiltration patterns were detected; the skill is explicitly restricted to no external calls.
[SAFE]: No prompt injection, obfuscation, or persistence mechanisms are present in the skill instructions.
[SAFE]: The skill does not install any external dependencies or execute remote scripts.

orchestrator-status