|
|
|
|
|
by gojkoa
15 days ago
|
|
(using claude code) I force the agent to work in steps where each step changes no more than 4-5 files, where each step has some observable result, ideally unit testable or e2e integration testable, and do a quick git diff/git add after each step. I have a bunch of deterministic checks (custom linting rules) that verify pretty much any repeatable comment I had to provide to Claude code over time (Claude is also writing/maintaining the rules, and unit tests for the rules) so I can focus on identifying new stuff. It took a few months to grow this rule set but now it exists things work pretty smoothly. |
|