Metabolomic networks describe correlated change in metabolite levels that crucially link the transcriptome and proteome with the complex matter and energy dynamics of small molecule metabolism. These networks are atypical. They do not directly portray regulatory and pathway information, yet they embed both. Here we study how stress rewires the metabolomic networks of Escherichia coli. Networks with vertices describing metabolites and edges representing correlated changes in metabolite concentrations were used to study time resolved bacterial responses to four non-lethal stress perturbations, cold, heat, lactose diauxie, and oxidative stress. We find notable patterns that are common to all stress responses examined: (1) networks are random rather than scale-free, i.e. metabolite connectivity is dictated by large network components rather than 'hubs' (2) networks rewire quickly even in the absence of stress and are therefore highly dynamic; (3) rewiring occurs minutes after exposure to the Stressor and results in significant decreases in network connectivity, and (4) at longer time frames connectivity is regained. The common biphasic-rewiring pattern revealed in our time-resolved exploration of metabolite connectivity also uncovers unique structural and functional features. We find that stress-induced decreases in connectivity were always counterbalanced by increases in network modularity. Remarkably, rewiring begins with energetics and carbon metabolism that is needed for growth and then focuses on lipids, hubs and metabolic centrality needed for membrane restructuring. While these patterns may simply represent the need of the cell to stop growing and to prepare for uncertainty, the biphasic modularization of the network is an unanticipated result that links the effects of environmental perturbations and the generation of modules in biology.