Every agent harness solves the same two problems, and almost every one of them solves both privately. The first problem is decomposition. A task arrives, the harness breaks it into steps, and those steps live in the harness's own memory in the harness's own shape.
Source: [Dev.to](https://dev.to/alexmercedcoder/the-plan-and-the-worker-two-open-specifications-for-agent-harnesses-242h)