When Should I Use the Claude Code Harness?

Thariq Shihipar says very complex coding tasks should use the Claude Code harness, while simpler or more domain-specific work can use a harness built for the task, because Claude has gotten better at building harnesses.

Models will eventually one-shot the full Claude Code setup, including auto mode and computer use. They can already one-shot simpler harnesses. When computer use and the more complicated pieces are unnecessary, the full harness is unnecessary. Earlier, the agent SDK wrapped Claude Code, because so much complexity went into building a harness. The complexity is more abstracted now. Claude managed agents keep the complexity and still allow a very bare-bones harness scoped to the task. Harness primitives like managed agents sit on the same barbell: use the Claude Code harness for the hardest coding work, and build a narrower one when the job is simpler.

Projects, artifacts, and a split between brain, hands, and surfaces are where the product is heading, and the path is more token expensive. Creating loops asks Claude to do more work, managing the sub-agents and reviewing them, instead of a person doing that work normally. Outputting to an artifact is more token intensive than outputting normally.