This methodology article presents a novel computational framework for analysing the complex, multi-layered dynamics of conflict and peace in South Sudan. It addresses the limitations of qualitative assessments by proposing a hybrid approach that integrates agent-based modelling with natural language processing of peace agreements and event data. The framework is designed to simulate factional interactions, resource competition, and the impact of external interventions, providing a testbed for evaluating the structural viability of peace accords. The article details the methodology's architecture, data integration processes, and validation procedures using historical data from the Revitalised Agreement on the Resolution of the Conflict in the Republic of South Sudan (R-ARCSS). It argues that such computational tools can offer policymakers and researchers a robust, evidence-based means to stress-test peacebuilding strategies before implementation.