Agents write code faster than a person can review it - and it all lands in one giant pull request. GitHub released gh-stack: a command-line extension that splits the work into ordered, independently reviewable layers. A change in the middle propagates up the stack on its own.
- gh-stack: a new CLI extension from GitHub that arranges a large change into a stack of small, independently reviewable pull requests (04.08).
- The example from the post: a feature that was over 1720 lines as one PR becomes four layers - data, API, chat, interface; a change in the middle layer cascades rebase-by-rebase to the layers above.
- Review: top-down for context, bottom-up for approval. Install: gh extension install github/gh-stack.
If you've ever taken code from an agent, you know the picture: the task is one thing, and the diff is two thousand lines across eight files. Technically it's all there. Practically there's nowhere to grab hold of it.
This is where the craft shows, and the admission along with it. When GitHub builds a tool for slicing up AI diffs, that's an official admission of where the bottleneck has moved - no longer writing, but reading. The only trust pipeline the craft has carried for decades is one person reviewing another's work - piece by piece, at a size the brain can carry.
The good thing about the design: the stack stands on ordinary branch-based work and ordinary pull requests, request-by-request. Nothing new to learn. The same git, arranged with discipline. Tools like that survive.
In our AI workflows you plan the layers before the agent sits down to write, not after it hands you the pile. You cut it into steps right in the brief - then the stack comes out on its own, and review stops being a punishment.