ROBOPuppet is a method to create inexpensive, tabletop-sized robot models to provide teleoperation input to full-sized robots. It provides a direct physical correspondence from the device to the robot, which is appealing because users form an immediate 'mental mapping' of the input-output behavior. We observe that untrained users can immediately exploit tactile and physical intuition when controlling the puppet to perform complex actions the target robot. The key contribution of this paper is a build procedure that embeds standardized encoder modules into scaled-down CAD models of the robot links, which are then 3D printed and assembled. This procedure is generalizable to variety of robots, and parts cost approximately seventeen dollars per link. We also present a simple software tool for fast calibration of the puppet-robot mapping, and a safety filtering procedure that sanitizes the noisy inputs so that the robot avoids collisions and satisfies dynamic constraints. A prototype ROBOPuppet is built for a 6DOF industrial manipulator and tested in simulation and on the physical robot.