opus 4.6 is a dream for me. Though I’m in the web dev area which is quite mature and with a lot of training data. The life saver to avoid regression is to comprehensively test your code. This works as a kind of quality checkpoint during development.

Secondly, give it the right tooling and context, that means at the very least a good acp server (editor) and appropriate mcp servers. Search for what’s appropriate in your domain. For 3d math, at the very least I’d think it would need a visual snapshotting tool. There are probably tons of relevant ones.

Thirdly, consistently expand on your CLAUDE.md, add and develop new skills as you go (let it write its own on your instructions). Force it to read them.

It probably depends on a lot of factors, but disciplined usage of these approaches will go a long way. Opus’ context window is huge, which makes the approach more consistent.

For one thing if you’re snapshotting your subvolumes for backup purposes then it will ignore nested subvolumes. Eg you dont want to preserve snapshots of huge installed game directories, cache directories, logs or docker / podman images, usually. Saves a lot of space.

Also you can tune copy on write on a subvolume, which is great for some use cases for performance.