The Agent Skills Directory

[NO_CODE]: The skill package consists exclusively of Markdown files providing instructions and reference data; it contains no scripts, binaries, or executable code.- [SAFE]: No obfuscation, prompt injection, or remote code execution patterns were found. The skill's functionality is limited to configuration guidance for the agent's internal reasoning mode.- [SAFE]: References to external services like Claude and OpenAI relate only to comparative pricing and model capabilities. No sensitive file access or unauthorized data exfiltration patterns were identified.

reasoning-controls