Planning with diverse knowledge, i.e., hybrid planning, is essential for robotic applications. However, powerful heuristics are needed to reason efficiently in the resulting large search spaces. HTN planning provides a means to reduce the search space; furthermore, meta-CSP search has shown promise in hybrid domains, both wrt. search and online plan adaptation. In this paper we combine the two approaches by implementing HTN-style task decomposition as a meta-constraint in a meta-CSP search, resulting in an HTN planner able to handle very rich domain knowledge. The planner produces partial-order plans and if several goal tasks are given, subtasks can be shared, leading to shorter plans. We demonstrate the straightforward integration of different kinds of knowledge for causal, temporal and resource knowledge as well as knowledge provided by an external path planner. The resulting online planner, CHIMP, is integrated in a plan-based robot control system and is demonstrated to physically guide a PR2 robot.