I think it’s complementary - superpowers seems more about what is being told to the agent.
The guardrails outside the agent guarantee it’ll behave a certain way. Still lets the agent write code but makes sure it also writes tests, and prevents boneheaded mistakes I was always telling it not to make.
The guardrails outside the agent guarantee it’ll behave a certain way. Still lets the agent write code but makes sure it also writes tests, and prevents boneheaded mistakes I was always telling it not to make.