This methodology article proposes a novel computational framework for analysing the complex dynamics of conflict and peace in South Sudan. It addresses the limitations of qualitative assessments by integrating agent-based modelling with natural language processing of peace agreements and event data. The framework is designed to simulate stakeholder interactions, evaluate the structural robustness of peace accords, and identify potential failure points. The proposed methodology is illustrated through a preliminary application to the 2018 Revitalised Agreement on the Resolution of the Conflict in the Republic of South Sudan (R-ARCSS). The article details the evaluation strategy and discusses how such computational tools can provide evidence-based insights for policymakers and conflict analysts.