The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides examples of interacting with a CLI tool named codegraph. These commands are standard for static analysis tasks like init, index, query, and affected. All interactions are local to the user's codebase and no risky command injection patterns or unexpected privilege escalations were found.
[SAFE]: The skill is primarily instructional, outlining how to maintain index freshness and handle stale data during architectural reviews. It does not contain executable code, scripts, or remote dependencies.

tools-codegraph