The purposes of this study were first to assess the reliability and criterion-related validity of the Illinois change of direction (COD) Illinois Agility Test (IAGT) and second to determine whether a relationship with power and speed exists. A total of 105 male team sport athletes participated in this investigation. Repeat measurements in 89 subjects out of the 105 were performed to assess the test-retest reliability and the 95% confidence interval (CI) of the difference in the score between paired observations (minimal detectable change [MDC]95) of the COD IAGT. The intraclass correlation coefficient and the SEM values for the COD IAGT test were 0.96 (95% CI, 0.85-0.98) and 0.19 seconds, respectively. The smallest worthwhile change (0.20 seconds) for the IAGT was greater than its SEM (0.19 seconds). The MDC95 value for the IAGT was 0.52 seconds. Criterion-related validity of the COD IAGT was assessed in the 105 subjects. They performed the COD IAGT and the T-test. Both tests were significantly correlated (r = 0.31 [95% CI, 0.24-0.39]; p < 0.05). The correlation between COD IAGT, acceleration, straight speed, and leg power was analyzed in all the 105 subjects. Pearson moment correlation revealed no association between acceleration and the COD IAGT. However, significant correlations were observed between the COD IAGT and leg power (r = -0.39 [95% CI, -0.26 to -0.44]; p < 0.05), and speed (r = 0.42 [95% CI, 0.37-0.51]; p < 0.05). When controlling for speed with partial correlation, the significant relationship between the COD IAGT and leg power disappeared. In conclusion, the COD IAGT seems to be a reliable and valid test, whose performance is significantly related to speed rather than to acceleration and leg power.