2026 04 21 Boris Claude Techniques
You really need to watch every minute of this 11-minute interview. The mind behind Claude Code, Boris Cherny (@bcherny), just opened up abo
view source ↗Charly Wargnier @DataChaz 2026-04-01
🚨 You really need to watch every minute of this 11-minute interview.
The mind behind Claude Code, Boris Cherny (@bcherny), just opened up about his daily workflow and it is pure GOLD 🤯
It’s loaded with 15 incredible tips that fly under the radar.
Did you know he runs 5 to 10 Claudes at the exact same time?
Yes, even straight from his phone!
Some of his best secrets:
→ Choose the smartest model to reduce your token usage and lower your bill
→ Maintain a master claude.md file to prevent Claude from repeating mistakes
→ Empower Claude with feedback loops to run code and see live browser results
His core method is simple:
Outline a plan, lock it into place, then hand execution over to Claude.
I also added an awesome guide by @exploraX_ featuring 20 Agentic Skills for Claude.. or any LLM! 💥
2026-04-01
Michael Murray @MGMurray1 2026-04-21
The Plan then Execute with multiple parallel Claudes pattern using master files for memory is exactly our architecture.
We run it with a refinement: 7 master files instead of 1, each serving a different aspect of institutional knowledge. SOUL.md for voice and judgment. AGENTS.md
Indra Aden @PangestuAden 2026-04-20
running multiple instances simultaneously changes the whole workflow
it's less about one perfect output and more about parallel exploration
Tradesman @dmat13484493 2026-04-21
If only iOS Claude would sync with the Mac mini Claude. Only syncs in One Direction.
lalo @lalopenguin 2026-04-21
@enlitsupply this is the way
Video transcripts
https://x.com/DataChaz/status/2046351105274392670
Transcribed 2026-04-21 with Whisper base. Duration: 11m 51s. Language: English. Uploader: @DataChaz.
You had a you had a post that went absolutely viral. I think you know what post I'm going to talk about 99,000 bookmarks, which is crazy. And I'm going to share my screen. I want to go over it a little bit. This is me learning to use Twitter. I think I made a account like a decade ago and I haven't really used it. It's funny. It's been fun to learn. You have like just a few tweets, but like this, you know, this one you figured it out. You say, I'm Boris, I created Cloud Code. Lots of people have asked for how I use Cloud Code so I want to show off my setup a bit. My setup might be surprisingly even though Cloud Code works great out of the box so I personally don't customize it much. There's not no one correct. There's no one correct way to use Cloud Code. We intentionally built it in a way that you can use it, customize it and hack it however you like. Each person on the Cloud Code team uses it very differently. So here it goes. Could you just talk about some of the just expand on some of these and what you were saying, you know, what you were saying on here? Because I thought it was really interesting. Yeah, I'd love to. So this first one, it's very similar to what I was showing in co-work where my job now isn't to go super deep on one task. It's to do a bunch of tasks in parallel. And so, you know, when I'm working on Cloud Code, I usually work in a terminal or on the mobile app. These are kind of the two surfaces I use the most. But like I said, everyone on the team is different. Every user prefers something different. So we build all of these. And so usually what I do is I'll sort of task in kind of one tab. And once Cloud is thinking about it and starting to work on a plan, I'll move on to the second tab. And I'll ask it to make a plan for the second thing. Then I'll move on to the third one, ask it to make a plan. And then finally, like when, you know, I've run out of immediate tasks to do, I'll go back to the first tab. I'll see if the plan works good. I might go back and forth a little bit. And then once the plan works good, I usually go into just auto-except edits right away. Because I think with Opus 4.5, once the plan is good, the model can just execute it pretty much perfectly. This is definitely not the case with previous models. And so I think there was a lot of excitement about Opus 4.5 in over the last couple of months. And I think this is kind of one of the big reasons. It's just gotten very good at coding, but also excellent at planning. So once the plan is good, the code is good. And so yeah, my work now is just jumping between tabs, kind of tending to the clouds, make sure they're unblocked, answering their questions. With co-work, I think it's actually quite similar now. I like that. I'm going to quote you on that. Once the plan is good, the code is good, because that's so true, right? Because if you nail the plan, the code should, you know, the agents to do the work. Yeah, yeah, exactly. I think like sometimes last year there was all this buzz about spectraven development. Yeah. And you know, it just feels like it feels a little like 2QT and like a little too rigid to me. But I think this is sort of a form of spectraven development. It's like, there are some kind of spec, you know, I think it's just like a plan. That's all it has to be. It's just a text file. It doesn't have to be in a particular format. Once you have that, you're good. Number two, you say I also run five to 10 clouds in parallel with my local clouds. As I code in my terminal, I will often hand off local sessions to web using and or manually kick off sessions in Chrome. And sometimes I will teleport back and forth. I also started a few sessions from my phone, obviously, from Cloud iOS app. It got you every morning and throughout the day and check in on them later. What do you mean by that? This morning I kicked off, I think like three quads as soon as I woke up. It's kind of like some thought in the morning about, well, maybe I should like build this thing or fix this bug or whatever. I was like checking Twitter and someone had a bug report. So I just opened my phone and you know, in the quad app, you on the on the left side, you could put the little menu and there's a code tab. So you can just like access quad code there. That's what I used for a lot of my code. And it's funny. I never would have guessed that this is the way that I code. If you ask me a year ago, I would never have predicted that the way I code now is like probably half of it is just on my phone and it sort of just works. And then web is kind of the other part. So once I've run out of tabs because it's just like, you know, it's kind of a pain to manage a bunch of different get checkouts. Because in each tab in my terminal, I actually have a totally separate get checkout. And I don't really use work trees or anything like that. I just keep it pretty simple. And in web, if I just ran out of terminal tabs, I'll start like overflowing to web and starting to test there. Beautiful. So yeah, I also so recommending use iOS, use web open multiple like that's that's you'll get the most out of it that way. Yeah, absolutely. Yeah. And we have an Android app now too. So yeah, just like use the mobile app and see how far that can take you. If it's not giving you good results, also make sure that you tune the environment setup. And make sure that you invest in your quad.md that's super duper important. And I talk about that in number four also. Number three, you say I use opus 4.5 with thinking for everything. It's the best coding model I've ever used. And even though it's bigger and slower than Sonnet, since you have to steer it less. And it's better at tool use. It's almost always faster than using a smaller model in the end. And cheaper. It's sort of counterintuitive. And I had to explain this to people a few times. But because the model is smarter, it actually uses West tokens in the end. And it uses so many West tokens. It's often cheaper than using a smaller, less intelligent model, even though the per token cost for that model is lower. So little counterintuitive, but yeah, you just use the smartest thing if you can. Oh, we appreciate that. You know, we appreciate that. Number four, our team shares a single quad md for the cloud code repo. We check it in to get the whole team contributes multiple times a week. Anytime we see cloud do something incorrectly, we add it to the md. So cloud knows not to do it next time. Other teams maintain their own quad mds. It is each team's job to keep theirs up to date. And the quad md is just a text file. So there's no special format people ask this all the time. Is there some special format that it has to be in it? No, it's just like, it's just a text file. So you can put whatever you want in it. This is a screenshot of our quad md. This is literally it. So just really simple. And you know, you could format this kind of however you want. Love it. And then finally, I think, yeah, number five. Oh, no, you have a few more. So number five, during code review, I'll often tag at dot cloud on my co-workers PR. So add something to the cloud md as part of the PR. We use the cloud code GitHub action. For this, it's our version of Dan Chipper's compounding engineering. What do you mean? What is compound engineering? Yeah, oh my god. So there's actually like two bugs in this tweet. I think Dan actually calls it compound engineering, not compounding engineering. And then the at dot quad, this is me wording how to use X. But it's actually at cloud. There's no dot. I just didn't. I think there's like an actual user or something whose name is cloud. I didn't want to tag them. But yeah, so what you do is in quad code, you run this slash command slash install GitHub action. And what this does is it installs the cloud app in your GitHub repo. And what that wants you to do is you can then app mentioned cloud whenever you want. And just have it make changes. And it can just work on PR. So it'll push back to your branch and it'll push the changes right back. You can also tag it on issues. You can tag it kind of wherever. I do this multiple times a day. It's really, really useful. I think one of the most common use cases is just like little fixes. I think the other one is updating the quantum D to keep the knowledge based update. And you know, you should never have to comment about something twice. Back when I was at meta something that I did is this is like in a previous life in a previous job. Something that I did is every code review that I did. I would keep a spreadsheet of all the issues that came up. And whenever the same kind of issue came up again, I would just like towelied up on the spreadsheet. And whenever something hit, I think like five or 10 tallies or something, I would write a link rule. And what that is is it's a way to automate that part of the code review. So I don't have to comment about it again. And I was back in the days before a lunch and before the model was any good at coding. And so this is the equivalent nowadays. It's tagclawed and you have it update your quad Md, which is your team's knowledge base. So really simple. And what this means is you don't have to point anything out twice. I'm curious to see what this looks like for co-work. I don't think we figured that out yet. But definitely for quad code, quad Md is kind of the, this is the one thing that you should all be updating all the time. Love it. Number six, most sessions start in plan mode. If my goal is to write a pull request, I will use plan mode, go back and forth with Clawed until I like its plan. From there, I switch into auto accept edit, edit mode and Clawed can usually one shot it. A good plan is really important. Yeah, like I said, planning is just the most underused feature in quad code. Actually, a lot of people use it, but I would say it's still underused. I use it for almost all my sessions. Yeah, it's, it's a no brainer. So if you aren't already doing this, please do. Do we've got, you know, we're not going to have time to do all of them. What are the, I don't think, because you have a hard stop. Do you want to pick one or two to end with? Yeah, let's do, let's do maybe number 13. Yeah, number 13, I think this is probably in addition to using opus four. When people ask about how to get better performance at a quad code, there's three things that I recommend almost every time. Number one is use opus 4.5 with thinking always. Don't try to use a different model because opus will just give you better results and more efficiency overall. The second thing is make sure you have a good quad empty and then the third thing is this, this tip number 13, which is give quad a way to verify its output. And so we just kind of saw with co-work how good quad is at using the Chrome extension in order to write email and in order to work with sheets. And it's exactly the same thing. If I'm building an app, I always use the Chrome extension to have quad test its own work. And if quad can verify its own output, the result is going to be way, way better. And it's sort of like, you know, imagine that you're a painter and you're, you know, you make paintings and they have to be like pretty good, they have to be maybe even like photorealistic or something. Or just like, you know, some kind of like very detailed style. And you have to wear a blindfold. You're just not going to be that good. It's not going to come out that great. Or is the same thing for an engineer like if you have to write code, but you can never run the code or you can never see the output or you can never see the website. It's just not going to be good. And so it's the same thing with quad. As the model gets more intelligent, that first shot is going to get better and better. But really, you want to give it a way to verify the output. And it'll be much better. So this is like running tests. If you're an engineer, starting a server, also if you're an engineer, we're, you know, seeing, seeing the output in a simulator or in a browser. Amazing. And the ultimate tip, I guess, is just get your hands dirty, right? I think that's it. Yeah. I mean, there's no right, there's no one right way to use this stuff. Like, you know, see, see what's useful. See what's not. Find your own workflows. It's sort of, I heard someone describing quad code as like a find your own path book. You know, like one of those books where you have to like, do you do, do you go to the dungeon or do you explore the forest, like this kind of thing or like an old, like RPG video game? It's just kind of like that. It's like, it's very free form. There's no one right way to do it. So just see what works for you.