The Agent Skills Directory

[SAFE]: The skill provides architectural and operational guidance for AI agents to optimize filesystem exploration. It does not contain executable scripts, third-party dependencies, or network-enabled tools. The instructions focus on reducing token usage and latency by preferring native IDE tools over shell subshells (like ls or dir).
[PROMPT_INJECTION]: While the skill uses mandatory language (e.g., "Agents must NEVER run ls..."), these are legitimate operational directives aimed at task efficiency and do not attempt to bypass safety filters, extract system prompts, or override agent ethical guidelines.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file access, or data exfiltration patterns were detected. An example file path is provided in the documentation for illustration purposes, which does not pose a security risk.

no-ls-bash-listing