In 1957 Crick hypothesized that the genetic code was a comma free code. This property would imply the existence of a universal coding frame and make the set of coding sequences a locally testable language. As the link between nucleotides and amino acids became better understood, it appeared clearly that the genetic code was not comma free. Crick then adopted a radically different hypothesis: the "frozen accident". However, the notions of comma free codes and locally testable languages are now playing a role in DNA Computing, while circular codes have been found as subsets of the genetic code. We revisit Crick?s 1957 hypothesis in that context. We show that coding sequences from a wide variety of genes from the three domains, eukaryotes, prokaryotes and archaea, have a property of testable by fragments, which is an adaptation of the notion of local testability to DNA sequences. These results support the existence of a universal coding frame, as the frame of a coding sequence can be determined from one of its fragments, independently from the gene or the organism the coding sequence comes from.