Human activity affects the Earth's climate while itself being affected by climate change - from rising sea levels to productivity effects of temperatures, natural disasters and climate-driven conflict. To empirically estimate the impact of humanity onto climate and vice versa, climate econometrics has emerged as a field split into two strands: one side focusing on conditional models of the economy taking climate as given, the other side modelling and predicting climate taking economic activity as given. However, economic and environmental systems are determined with feedbacks in both directions. Conditional modelling of one side can be informative about the underlying parameters of interest (e.g. climate impacts onto the economy, or climate sensitivity) if conditions on weak, strong, and super exogeneity are met. Here I attempt to reconcile the two strands of the climate-econometric literature by considering a full (albeit simple) empirical climate-economic system and the conditions under which the system can be studied by only looking at the conditional economic or the climate side. Weak exogeneity is required for valid conditioning, strong exogeneity - required for conditional forecasting - lends itself to the concept of climate-takers and climate-setters (countries measurably affecting climate), while super-exogeneity can be interpreted as policy invariance for the economic impact side, and as a `no-tipping point' condition on the physical side. An application to a simple bivariate climate-economic system using US SO2 emissions and temperatures highlights how these concepts can be applied in practice. A system analysis in climate econometrics allows us to move towards fully-coupled empirical climate-economic models consistent with the underlying physics and fully accounting for the necessary feedbacks, to obtain estimated impacts in both directions. While far from trivial in large systems, this is necessary to obtain rigorous empirical estimates of the impact of climate on humanity and vice versa.