Code coverage serves as a crucial metric to assess testing effectiveness, measuring the degree to which a test suite exercises different facets of the code, such as statements, branches, or paths. Despite its significance, coverage profilers necessitate access to the entire codebase, constraining their usefulness in situations where the code is incomplete or execution is not feasible, and even cost-prohibitive. While the utilization of Large Language Models (LLMs) for predicting code coverage has demonstrated success, challenges persist, particularly in achieving high accuracy due to the intricate, expansive space of multiple interdependent execution steps in a program. In this paper, we present CCPlan, a plan-based prompting approach grounded in program semantics, which collaborates with LLMs to enhance code coverage prediction. To address the intricacies of predicting code coverage, CCPlan employs planning by discerning various types of statements in an execution flow. Planning empowers GPT to autonomously generate plans based on guided examples, and then CCPlan prompts the GPT model to predict code coverage (Action) based on the plan it generated (Reasoning). Our experiments evaluating CCPlan demonstrate high accuracy, achieving up to 55% in exact-match and 89% in statement-match. CCPlan performs relatively better than the baselines, achieving up to 33% and 19% relatively higher in those metrics. We also showed that due to highly accurate plans (90%), the GPT model predicts better code coverage. Moreover, we show CCPlan’s utility in correctly predicting the least covered statements as a downstream task.