The Agent Skills Directory

[SAFE]: The skill provides guidelines for reviewing changes to the Cog architecture. It is purely documentation-based and does not contain any instructions that attempt to bypass safety filters or override agent behavior.
[NO_CODE]: No executable scripts, shell commands, or dynamic execution patterns are present in the skill content. It mentions project-specific tools like 'mise' and 'cog' in an informational context for developers rather than as commands for the agent to execute autonomously.

cog-review