multica-ai/andrej-karpathy-skills
This CLAUDE.md turns common agent failure modes into four operating rules: surface uncertainty, minimize code, avoid unrelated edits, and define verifiable completion criteria.
The repository packages **four principles** into one CLAUDE.md: expose assumptions and tradeoffs, write the minimum code, limit edits to the request, and drive work with verifiable goals. A Cursor rule carries the same guidance.
Merge the rules with project-specific instructions, then add concrete tests and acceptance criteria. The strongest operational pattern is **tests-first verification**, giving an agent a target it can check rather than an underspecified command.
The repository packages **four principles** into one CLAUDE.md: expose assumptions and tradeoffs, write the minimum code, limit edits to the request, and drive work with verifiable goals. A Cursor rule carries the same guidance. Merge the rules with project-specific instructions, then add concrete tests and acceptance criteria. The strongest operational pattern is **tests-first verification**, giving an agent a target it can check rather than an underspecified command. These rules intentionally favor caution and may add friction to trivial fixes. They are behavioral instructions, not evidence that every model or task will improve, so judge them by diff scope, clarification timing, and test results.
This condenses conservative coding-agent behavior into a portable instruction layer: surface uncertainty, minimize scope and code, and define outcomes the agent can verify. It reinforces bounded execution as a reliability mechanism, but narrows the claim to a testable operating hypothesis; usefulness must be measured through clarification quality, diff size, and passing acceptance checks, and the rules may be excessive for trivial work.