The Agent Skills Directory

[SAFE]: The skill instructions focus on legitimate context optimization and task persistence strategies. No malicious patterns such as prompt injection or data exfiltration were detected across the analyzed files.
[SAFE]: Subagent delegation patterns (e.g., outfitter:reviewer, outfitter:analyst) are used to isolate complex tasks and preserve the main context window, which aligns with security best practices for maintaining agent stability.
[SAFE]: The tools mentioned (e.g., TaskCreate, episodic-memory:save) are standard platform utilities for state management and do not exhibit any suspicious behaviors or unauthorized access patterns.

context-management