A lot of people are acting like code quality doesn’t matter anymore. Coding is solved, agents will write everything, and nobody will need to read code line by line etc etc. I've not really been able to get CC to write good code by default but I chalked it up to a skill issue. So when CC leaked it was pretty shocking from a code maintainability standpoint and it was very clear to me that the issue is structural.

Reading the leaked prompts made the failure mode pretty obvious: the agent is optimized to get its feature working inside local context, not to improve the codebase as a whole. So it makes defensive patch fixes, leaves old paths around, avoids holistic cleanup, and slowly fills the repo with debt. My take is that it's intentionally designed to one shot new projects/features but you have a aggressively prompt it to write maintainable code.

I've been writing typescript for a number of years now (and startups and large companies) and have pretty strong opinions how to do it sustainably. The fact that we code with agents hasn't changed the fundamentals as much as vibe coders will have you believe. Hopefully others find this skill helpful.

Maintaining (and, ideally, improving!) code quality is, IMO, the biggest open problem in agentic development.

I've been coming at this from a slightly different angle, building a system that encodes checks that run against code authored by Claude, with escalating levels of enforcement.

It's still really early, but, among early users, we see that about 40% of agent turns produce code that violates the guidance in the project's own CLAUDE.md. We catch the violations at the end of the turn and direct Claude to correct them.

Still looking for early users and feedback. http://getcaliper.dev

Do you have examples that show concrete improvements when using this?