Social inequalities, which translate into unequal development and access to basic infrastructure and care, can lead to increased prevalence in more vulnerable communities during a pandemic. Effective interventions must consider these social heterogeneities and take into account social behavior in communities in order to protect vulnerable or highly exposed groups and suppress the infection wave as a whole. In order to take these into account in the evaluation and design of intervention policies, we developed highly modular and configurable software for stochastic agent model simulations called COMORBUSS. We model in detail the infrastructure of a city and perform a stochastic evolution of agent behavior based on the individual characterization of the agents and their social roles. COMORBUSS has an expandable API for creating new functionally, for example, we can activate an airborne infection model for closed environments. This was key to evaluate protocols to keep school activities safe in the context of the COVID-19 pandemic, a study performed in collaboration with the city of Maragogi-AL. We find that (i) resuming school activities with people only wearing low-quality masks leads to a nearly fivefold city-wide increase in the number of cases even if all staff is vaccinated, (ii) resuming activities with students wearing good-quality masks and staff wearing N95s leads to about a threefold increase, (iii) combining high-quality masks and active monitoring, activities may be carried out safely even with low vaccination coverage.

• Poster