The Agent Skills Directory

[SAFE]: The skill consists entirely of prompt instructions meant to influence the AI's response style (conciseness) and workflow suggestions.
[SAFE]: It contains explicit safety guardrails, instructing the agent to never sacrifice technical accuracy for brevity and to maintain full clarity for security warnings and destructive operation confirmations.
[SAFE]: The skill does not perform any file system modifications, network requests, or command execution. It suggests the use of standard local tools like git, prettier, and eslint for deterministic tasks, which is standard development practice.

cost-mode