Habitat fragmentation can restrict geneflow, reduce neighbourhood effective population size, and increase genetic drift and inbreeding in small, isolated habitat remnants. The extent to which habitat fragmentation leads to population fragmentation, however, differs among landscapes and taxa. Commonly, researchers use information on the current status of a species to predict population effects of habitat fragmentation. Such methods, however, do not convey information on species-specific responses to fragmentation. Here, we compare levels of past population differentiation, estimated from microsatellite genotypes, with contemporary dispersal rates, estimated from multi-strata capture–recapture models, to infer changes in mobility over time in seven sympatric, forest-dependent bird species of a Kenyan cloud forest archipelago. Overall, populations of sedentary species were more strongly differentiated and clustered compared to those of vagile ones, while geographical patterning suggested an important role of landscape structure in shaping genetic variation. However, five of seven species with broadly similar levels of genetic differentiation nevertheless differed substantially in their current dispersal rates. We conclude that post-fragmentation levels of vagility, without reference to past population connectivity, may not be the best predictor of how forest fragmentation affects the life history of forest-dependent species. As effective conservation strategies often hinge on accurate prediction of shifts in ecological and genetic relationships among populations, conservation practices based solely upon current population abundances or movements may, in the long term, prove to be inadequate.