[en] Space systems miniaturization has been increasingly popular for the past decades, with over 1600 CubeSats and 300 sub-CubeSat sized spacecraft estimated to have been launched since 1998. This trend towards decreasing size enables the execution of unprecedented missions in terms of quantity, cost and development time, allowing for massively distributed satellite networks, and rapid prototyping of space equipment. Pocket-sized spacecraft can be designed in-house in less than a year and can reach weights of less than 10g, reducing the considerable effort typically associated with orbital flight. However, while Systems Engineering methodologies have been proposed for missions down to CubeSat size, there is still a gap regarding design approaches for picosatellites and smaller spacecraft, which can exploit their potential for iterative and accelerated development. In this paper, we propose a Systems Engineering methodology that abstains from the classic waterfall-like approach in favor of agile practices, focusing on available capabilities, delivery of features and design "sprints". Our method, originating from the software engineering disciplines, allows quick adaptation to imposed constraints, changes to requirements and unexpected events (e.g. chip shortages or delays), by making the design flexible to well-defined modifications. Two femtosatellite missions, currently under development and due to be launched in 2023, are used as case studies for our approach, showing how miniature spacecraft can be designed, developed and qualified from scratch in 6 months or less. We claim that the proposed method can simultaneously increase confidence in the design and decrease turnaround time for extremely small satellites, allowing unprecedented missions to take shape without the overhead traditionally associated with sending cutting-edge hardware to space.