The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local utility script (.claude/scripts/code_graph) using the Bash tool. This is used to analyze the codebase and trace function calls, which is consistent with the skill's stated purpose.
[SAFE]: Analysis of the skill instructions and metadata found no evidence of prompt injection, data exfiltration, or obfuscation. All operations remain local to the user's environment and use standard platform tools like Grep and Read for code discovery.

graph-trace