Hi, I'm Nico 👋 Engineering Manager who's back to writing code, mostly together with coding agents. I also just started my own side business building software with AI. Here I share what actually works, what's just hype, and what breaks. What are you building with agents right now?
Nico retweeted
It must be incredibly satisfying for the Roadster team to see tens of thousands of people on this app claim that what they achieved is impossible and must be a trick of some sort lol.
30k merges a day is also great marketing. The wild part is they dropped the merge queue and test after merging now. Would you trust that in your team? 😅
New on our Engineering blog: Creating in-house source control.
In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale.
Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
Code comments or no comments is an old debate and for me it's not black or white. Code should explain itself, but sometimes I still leave the intent as a comment. Otherwise the agent has to dig through tickets and other sources first
ban and delete most if not all code comments!
agents love copying what already exists. a seemingly harmless comment explaining some temporary workaround is one of the worst viruses you can have in your codebase. like a weed it'll spread quickly as a tool for agents to quickly get their job done. before you know it, your codebase is overrun with hacks and stale comments. just one more workaround bro
you can use pstack's /no-comments skill as a weedkiller. it'll seek out useless comments while keeping the ones that actually should exist (like explaining a browser quirk), and figure out how to solve them on a first principles basis
here's a prompt you can try asking @bot:
create a project agent that uses /poteto-mode to spawn a /swarm to use /no-comments and identify useless code comments we can prune in my repo. come back with a high level plan of which of these workarounds would be best solved by refactoring and which we can straight up delete
x.ai/bot/plugin/9717366
Parallel threads coordinated by Claude sounds great. But I already went back to fewer sessions because I lost track of what I shipped. Curious if the overview actually fixes that. Anyone tried it yet?









