The Agent Skills Directory

[COMMAND_EXECUTION]: The skill runs standard Ruby development and security tools including bundle exec rspec for testing, bundle exec rubocop for linting, and bin/brakeman for security vulnerability scanning. These are executed locally within the user's project environment.
[SAFE]: The orchestration workflow enforces mandatory pauses for user confirmation after every phase, ensuring that no code is generated or executed without explicit human approval of the specifications and plans.
[SAFE]: The skill configuration includes disable-model-invocation: true, which is a security hardening measure that prevents the model from making autonomous tool calls outside of the explicitly defined workflow.

feature