Use @cubic_dev_ - #1 ai code reviews on benchmarks - auto merge low risk prs - ai guided diffs to help humans review

we merged 4x more commits last week than we did a month ago (thanks opus 5.5). our dev setup and CI couldn't keep up, so we reworked both: • lint: 4x faster • memory per agent session: half • CI setup step: 50x faster • CI type check: 10x faster we often run 10+ agents at once locally, and each one runs its own lint, type checks and tests. from time to time, several agents would run these at the same time and block each other. a 64 GB MBP would run out of memory and crash. so most of the work was making things faster and lighter, or getting rid of them we revamped our local setup to make checks faster and use less memory: • oxlint and oxfmt instead of eslint and prettier, and type-aware lint only runs in CI. linting a changed file went from over 10s to a few seconds • a hook formats every file an agent edits, so agents don't have to take a turn to format it • typescript 7's native LSP instead of tsserver. each agent session uses about half the memory • agents run one check script after each change. it installs missing packages and env files first, then lints, type-checks and runs the tests for what changed • only 3 type checks or big test runs can run at once across all worktrees, so they don't slow each other down we revamped our CI to make it faster: • every CI job installs pnpm before it can install our packages. the standard github action for this (pnpm/action-setup) installs pnpm through npm, and that hung for 3-7 min on most of our test jobs. we now download the pnpm binary from github releases, which takes about 4s • our type check needs about 9.5 GB of memory. github's standard runners have 8 GB, so it ran out of memory and took 206s. on a 16 GB machine it takes 20s • vercel builds type-check with typescript 7 (85s to 45s), and previews only build for PRs that change the database if you're running lots of agents, look at what they're waiting on. for us it was mostly lint, type checks and CI setup

On benchmarks @cubic_dev_ is #1 best by far! The gap between cubic and #2 is bigger than the gap between #2 and #8. codereview.withmartian.com/

I love seeing @cubic_dev_ customers winning

Hey Peter! - Most teams start in shadow mode with the default, lower approval threshold until they’re comfortable with the risk classification. - Shadow mode doesn’t approve PRs - it leaves a comment explaining whether cubic would have approved the PR and why - Once they’re comfortable, they switch it to live mode. - Some larger teams do create a service account, especially if they want a clear audit trail or tighter control over which repositories it can approve in.