Wow, I did not expect this much response from my comment. First, let me say I am not flexing. I am very willing and happy to share HOW I'm able to achieve high quality code through my workflows and what my loops look like.

I am currently building 4 projects at the same time using a boilerplate I developed for my own projects.

One thing many people who are new to agentic coding harnesses may be missing is that a lot of workflows are personal to how the developer approaches design and implementation. So if you message me, please keep in mind that my approach may not align with how you approach software development.

That said, I will do my best to abstract my process so it's applicable for your work. I would also recommend reading OpenAI's article on harness engineering: https://openai.com/index/harness-engineering/

DMs are open if you genuinely want to know how I work :)

DISCORD: jayeeeffeff

> Each business domain is divided into a fixed set of layers, with strictly validated dependency directions and a limited set of permissible edges. These constraints are enforced mechanically via custom linters (Codex-generated, of course!) and structural tests.

> The diagram below shows the rule: within each business domain (e.g. App Settings), code can only depend “forward” through a fixed set of layers (Types → Config → Repo → Service → Runtime → UI). Cross-cutting concerns (auth, connectors, telemetry, feature flags) enter through a single explicit interface: Providers.

This sounds so much like CQRS/hexagonal/DDD/other stuff. This is like the stuff that real world software teams actually struggle to execute on. This is the stuff people want solved. I don't think anyone doubts that if you can nail some sort of rigid, well-defined architecture and tooling workflow, agents can fly on filling in implementation. But it's the first part that needs solving.