The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to audit and modify the local codebase.
Evidence: Commands include grep, find, git mv, and mkdir used to search for client-specific identifiers and move files into a structured clients/ directory.
Dynamic Scripting: The skill generates a shell script at .jez/scripts/fork-refactor.sh based on audit results to automate refactoring, which involves writing and potentially executing locally generated code.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its handling of untrusted codebase data.
Ingestion points: Project source files (e.g., src/*.ts) and configuration files are scanned and read via grep and Read tools.
Boundary markers: None. The instructions do not define delimiters or provide warnings to the agent to ignore instructions contained within the analyzed source code.
Capability inventory: The skill is authorized to use Bash for command execution, Write for file creation, and Edit for code modifications.
Sanitization: None. Data retrieved from the codebase is directly used to populate the fork-discipline-audit.md report and the generated fork-refactor.sh shell script.
[SAFE]: The tool is a legitimate developer utility aimed at improving code architecture. All operations are local to the workspace, and no external network activity or unauthorized data access was detected.

fork-discipline