The Agent Skills Directory

[SAFE]: The skill focuses on operational efficiency and token conservation. It does not contain executable code, remote dependencies, or instructions that override safety guidelines.
[DATA_EXPOSURE_PREVENTION]: The skill explicitly includes a security best practice under 'Antipatterns', advising the agent to use targeted commands like grep for specific values instead of reading entire configuration files to ensure secrets do not land in the conversation context.
[COMMAND_EXECUTION]: While the skill references standard shell utilities like grep, tail, head, and jq, these are presented as examples of efficient data processing and do not involve unsanitized user input or suspicious execution patterns.

token-discipline