The Agent Skills Directory

[SAFE]: The skill provides organizational and persona-based instructions to guide the AI's behavior during different phases of development (e.g., planning vs. coding).
[EXTERNAL_DOWNLOADS]: No external downloads or remote script executions were detected. The skill operates entirely locally using allowed tools.
[COMMAND_EXECUTION]: The skill does not attempt to execute shell commands. It only requests access to basic file-searching and reading tools (Read, Glob, Grep).
[PROMPT_INJECTION]: The instructions are clear behavioral guidelines for the LLM and do not attempt to bypass safety filters or override system-level security constraints.
[DATA_EXFILTRATION]: No patterns associated with data collection or external transmission were found. The skill has no network tools listed in its allowed-tools.

behavioral-modes