So the correct strategy is a global CLAUDE.md with couple lines of colourful "you best behave or else" texts, so all your prompts get routed via the frustrated path?
I find it routes more quickly for patches when in the frustrated path, so after planning sure :)
there already is a global claude using any cloud model is a high probability that theyre context stuffing trying to curate output for the normative use cases. see "dont talk about goblins"
That will not work - you end up with Claude being ADHD and not following any guidelines.
Skills do work, as they ground the agent with constrained context for the task it's performing