Objective Triple-negative breast cancer (TNBC) is the breast cancer subtype with the worst prognosis, and lacks effective therapeutic targets. Colony stimulating factors (CSFs) are cytokines that can regulate the production of blood cells and stimulate the growth and development of immune cells, playing an important role in the malignant progression of TNBC. This article aims to construct a novel prognostic model based on the expression of colony stimulating factors-related genes (CRGs), and analyze the sensitivity of TNBC patients to immunotherapy and drug therapy.Methods We downloaded CRGs from public databases and screened for differentially expressed CRGs between normal and TNBC tissues in the TCGA-BRCA database. Through LASSO Cox regression analysis, we constructed a prognostic model and stratified TNBC patients into high-risk and low-risk groups based on the colony stimulating factors-related genes risk score (CRRS). We further analyzed the correlation between CRRS and patient prognosis, clinical features, tumor microenvironment (TME) in both high-risk and low-risk groups, and evaluated the relationship between CRRS and sensitivity to immunotherapy and drug therapy.Results We identified 842 differentially expressed CRGs in breast cancer tissues of TNBC patients and selected 13 CRGs for constructing the prognostic model. Kaplan-Meier survival curves, time-dependent receiver operating characteristic curves, and other analyses confirmed that TNBC patients with high CRRS had shorter overall survival, and the predictive ability of CRRS prognostic model was further validated using the GEO dataset. Nomogram combining clinical features confirmed that CRRS was an independent factor for the prognosis of TNBC patients. Moreover, patients in the high-risk group had lower levels of immune infiltration in the TME and were sensitive to chemotherapeutic drugs such as 5-fluorouracil, ipatasertib, and paclitaxel.Conclusion We have developed a CRRS-based prognostic model composed of 13 differentially expressed CRGs, which may serve as a useful tool for predicting the prognosis of TNBC patients and guiding clinical treatment. Moreover, the key genes within this model may represent potential molecular targets for future therapies of TNBC.