Co-array fortran is a parallel programming language for scientific applications that provides a very intuitive mechanism for communication, and especially, one-sided communication. Despite the benefits of this integration of communication primitives with the language, analyzing the performance of caf applications is not straightforward, which is due, in part, to a lack of tools for analysis of the communication behavior of co-array fortran applications. In this paper, we present an extension to the kojak toolkit based on a source-to-source translator that supports performance instrumentation, data collection, trace generation, and performance visualization of co-array fortran applications. We illustrate this approach with a performance visualization of a co-array fortran version of the Halo kernel benchmark using the vampir event trace visualization tool.