[owaislone]

You have to treat it like a co-worker send you PRs for review. You review, ask to improve/cleanup stuff and it'll follow up. You can even ask it to remember so it follows the patterns in future. Even better, if you work with it to come up with a design first and then send it coding, you often don't need as much cleanup as the desired architecture is agreed upon early.

[maccard]

I would tell my co worker “this code has so many issues that I’m not actually reviewing it. Please make sure it meets the project standards before sending it back to me”if it happened twice I’d talk to their manager.

[owaislone]

Sure - define your project standards in the repo or agent's skill and tell it just that.

[maccard]

See my other comment here [0] - I’ve not found it possible to actually have the agents follow the explicit instructions. Even single shot tasks once the context window fills up (which it does, very very fast, and repeatedly if you use subagents) will ignore very explicit instructions.

[0] https://news.ycombinator.com/item?id=49036222

[owaislone]

- discuss the plan, dos-and-donts, instructions and have them add it to a PLAN_FEATURE.md with the goal, non-goal, non-negotiables, technical details on the top. - come up with phases to implement your thing. P1, P2, ... P8.. whatever - in each phase add simple one line TODOs with as much explanantion of the task as needed e.g, - [ ] Update DB schema, - [ ] Generate migrations - Ask the agent to go one phase or todo at a time depending on complexity. - if the context fills up, /clear the window and just ask it to do the next line. - if you wrote up all you care about in the plan properly, it'll follow what you need it to do.