Consequentialist reasoning is reasoning which starts from a desired outcome/event/future, and selects what actions, strategies, and intermediate events are likely to have the consequence of bringing about that outcome.
We can see one critical aspect of human intelligence as cross-domain consequentialism; natural selection is the only other optimization process that behaves something like a cross-domain consequentialist.
Note the distinction between consequentialist reasoning and expected utility maximization, which is a special case that isn't necessary to produce those properties that are consequences just of consequentialism.
Consequentialism yields the instrumentally convergent strategies, and produces Nearest Unblocked Neighbor behavior on attempts to block particular strategies.