Automating code security reviews with Claude: Mythos-level capabilities at lower cost
Coding agents are now involved in the majority of the code shipped at Synthesia. The volume of code changes has gone up but the time humans spend reading those changes has not. The practice of doing code security reviews is especially exposed to this pressure because it depends on careful analysis. To solve this, we’ve built an agent skill that approaches Mythos-levels of performance in uncovering complex security issues at a fraction of the cost of running such a model.