The Agent Skills Directory

[SAFE]: The skill is designed to perform architectural audits on local Elixir projects. It does not access sensitive files, perform network operations, or include any obfuscated content.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute mix xref and grep commands. These are standard local utilities used for generating dependency graphs and searching for code patterns within a Phoenix application. These operations are limited to the project directory and are used for their intended purpose of architectural validation.
[PROMPT_INJECTION]: Analysis of the instructions and documentation confirms there are no attempts to bypass safety filters or override agent behavior. The instructions provide clear, domain-specific guidance for interpreting architectural metrics.

boundaries