His Claude Code Workflow Is Insane

Well, hello there. So back in January, the creator of Cloud Code, Boris Chenry, he actually posted about his entire workflow. And I actually had a chance to meet with him and ask him a bunch of questions. And I personally found his personal workflow very enlightening. And I've been trying to replicate a lot of his workflows directly into mine. So today I thought it'd be fun to go over this chain of thread posts that he made and also kind of show you physically what it actually looks like in practice. Now, I have a few local projects. There's nothing really in terms of complexity as my projects for work, but I thought it would actually work pretty well to kind of showcase some of these and kind of like interact with some of them right here. So as usual, I created a little slide deck. So let's get right into it. So this is Boris Henry. For each of these, I'm just going to read it out really quick to show you each of the tips. Hi, I'm Boris, and I created Cloud Code. Lots of people have asked how I use Cloud Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla. CloudCode works great out of the box, so I personally don't customize it much. There is no one correct way to use CloudCode. We intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on CloudCode team uses it very differently, so here goes. i really like how he's set up here that clock code can be customized i personally have been customizing the hell out of it and at some point i'll probably share my own personal setup as well but i really like how it starts out here so let's get to the first tip the first tip is around running clouds in parallel i run five clouds in parallel in my terminal i numbered my tabs one through five and use system notifications to know when a cloud needs input so look at this i will open up my terminal All right, so it looks like what he does is he creates a clod like this. And then he has one that is just for like, just a terminal for bash. So it looks like this is a setup. And then he has multiple tabs like this. And then he probably replicates this clod tab system for all of them. right now i actually work very similarly like this i'll have one instance here one instance there i'm using like hotkeys for iterms is command 2 command 3 command 4 to switch between and then you could switch in between the tabs by doing command left bracket or right bracket now one additional tip here that i like to do to keep things like in my mental context is to like rename it so this could be like local one um or maybe the project that i'm working on local this is push to prod app for example and here maybe instead of this i i work on my anime pomodoro app for example and because i did that i would name this local anime and a pomodoro now you could imagine that you would have like ssh or some kind of on-demand stuff as well and this is exactly what i do at work so that's tip number one it also looks like he uses light mode i am not gonna switch my dark mode to light mode okay tip number two is five to ten web clots so I also run 5 to 10 clods on cloud.ai slash code in parallel with my local clods 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 start a few sessions for my phone from the Cloud iOS app every morning and throughout the day and check in on them later. So this is claw.ai, and I actually haven't done the teleport feature, but let's try the teleport. I don't know if it will work, but for my push to prod app, let's work on some of the printify integrations. Give me a plan. So it looks like it's whatever sessions are on here. It just maintains here. But let me see if I can do a slash teleport. I'm just going to try. Can you can you push to the web? I'm just going to try this. Okay, this is taking a long time. I'm just going to cancel this. And create todos for print to buy integrations. Okay, so it looks like it's creating a backend task. Look at this right here. So you just hit end like this. And then it creates a session. And then you can basically open the session like so. and it's going right here that's really cool i actually haven't been using this but i can imagine doing this especially when i'm like ready to go off for the day or something like that and it's synced to your phone if you look at this it's synced so and so you can start new sessions here so i actually didn't know about this but this is actually mind-blowing to me that's awesome i'm going to start using this all the time okay next tip tip number three is opus with thinking always 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 Snonet, 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. Now he posted this before Opus 4.6 came out. So I wonder what he's thinking about it now because Opus is like known to be a lot slower. So one thing you can do is you can switch though like this. Oh, so using slash model. And I actually also just default to 4.6. They got rid of ultra think, which used to have this little like animation thing. But if you have like just multiple like sessions of cloud code going, then it doesn't matter if it's that slow, in my opinion. All right. Tip number four is share your cloud.md. One cloud.md for the whole team. Check into the git. Update multiple times a week. Okay. Our team shares a single cloud.md for the cloud code repo. We check it into Git, and the whole team contributes multiple times a week. Any time we see Claude do something incorrectly, we add it to the Claude.md. So Claude knows not to do it next. Our team maintains their own Claude.mds. It is each team's job to keep theirs up to date. Now, I actually asked Boris what his personal Claude.md is, and he said there's basically like two lines, and it just points to using the Claude.md. and so so the whole idea is that they're doing compound engineering and then context engineering right within the code base i have a video coming up around this on agentic engineering but but yeah it's very simple i also am doing this now where for example um like this pomodoro app i have the claw.md directly here and it's kind of like Things about my code base for iOS, the navigation flow, the design patterns and things like that. A lot of this stuff you can just create using slash init. But yeah, like this is like very straightforward stuff. All right. Tip number five is add cloud in code reviews. So during code review, I will often tag add cloud on my coworkers PRs and add something to cloud.md as part of the PR. We use cloud code GitHub action slash install GitHub action for this. It's our version of add than shippers compound engineering. Now, so I actually kind of set this up so you can see that like right there, Claude's there in this workflow. Let me try making a quick PR. Write me a quick PR on some of these to-dos and push it. as a separate branch so the whole idea is that you should theoretically once this pushes do an at and then do a review now obviously this is like not a good example that i'm doing because it's just to do's but theoretically the whole idea is you develop a system so that it automatically uses claw to review your diffs or do other actions tip number six is plan mode first most sessions start in plan mode shift tap twice if my goal is to write a pull request i use plan mode and go back and forth with Claude until I like his plan. From there, I switch it into auto accept edits mode and Claude can usually one shot it. A good plan is really important. So I also do plan mode all the time as well. So for example here, I want to create a new live activity for my anime Pomodoro app where it keeps tracks of the timer in my like live activity and also dynamic island. All right. There's something definitely wrong with this UI here. But it's going. So I really like plan mode because it's a way to really analyze and deep dive into your code base before you actually make any changes. Someone asked me recently, why do you even have multiple cloud instances? What are you doing? A lot of times, if I'm not using Git work trees or like some. way to do multiple coding executions i'm actually doing a lot of deep dives using plan mode for like different parts of the code base so maybe i have like some kind of performance optimization project i want to do on media viewer maybe i want to do look into app init or app start whatever i'm trying to investigate i actually use plan mode and also for like investigating saves or investigating like random bugs i'll also start with plan mode to start investigating and plan mode is essentially a way for you to create prompts like gigantic prompts like really good prompts and i talk about context engineering and things like that but plan mode is where you do the orchestration to be able to bring all the context that you need into that cloud instance so that the agent can execute correctly all right tip number seven slash commands for everything i use slash commands for every inner loop workflow that i do many times a day this saves me from repeated prompting and makes it so claude can use these workflows too Commands are checked into the Git and live in .cloud slash commands. For example, Claude and I use a slash commit dash push dash PR slash command every day. The command uses inline bash to pre-compute Git status to make the command run quickly and avoid back and forth with the model. Okay, so if you ever wonder how you want to make a slash a command, it's very, very easy to do. so let's just go here and say i want to create a commit dash push dash pr skill and this skill needs to format my code and then add everything that i just did in this session and then commit the code with a good commit message i always want to push it as a pr rather than directly as main so that i can review the code online something like that and these days actually slash commands and skills are basically the same So Claude will usually create the same thing now. You know, the thing about making these videos is that it just takes a long time because Claude takes a long time to run. I probably should have ran this on Sonnet, but it's okay. Opus is fine. But you can see here that it's exploring the skills first so that it's not remaking the same thing. And I love the fact that Claude Code and Codex, they ask questions rather than just assuming. And I think this is like a big change between like, I don't know. I haven't used cursor in a bit. Maybe I should give it a try. But I remember it just like kind of did stuff without, I always just made assumptions, which, and it always turned out like not great. All right. It decided to name it slash ship, which is fine to me as well. But yeah, that's how you create skills. It's very easy. You remember all you need to do to make skills or slash commands or sub agents or install MCPs. It's just leverage cloud code to ask you to do it. All right. Tip number eight from Boris is custom sub agents. I use a few sub agents regularly. Code Simplifier simplifies the code after Claude is done working. Verify app has detailed instructions for testing Claude code end-to-end and so on. Similar to slash commands, I think subagents is automating the most common workflows that I do for most PRs. Now, one thing about subagents I want to say is that it's really to protect the context. Subagents are really useful if you want to do like side effects or if you want to just have the result. of that like cloud instance running you don't really care how it got there but you just want the output that's really good for sub agents there's a new thing this that just came out with opus 4.6 called agent swarm or agent teams and i'll probably do a video on this but it's the idea of sub agents that have actually different roles and they share context with each other and there's like a master orchestrator i think in my other video i showed what a sub agent is but i should have some sub agents here Agents, you can see here. I actually have, I created the same ones that Boris made because I thought it was very interesting. But yeah, so I could just say right here in another instance, can you run my code architecture subagent to verify the integrity of my build or integrity of my app? I don't know about you guys, but I run out of RAM all the time at work. I think one, my code base is extremely large. and then i i also have like five or so cloud instances running all the time um i had to give up running android studio completely or like i just have my terminal up i don't even have chrome up sometimes when i'm running out of memory so yeah so you can see that it's running two agents here let's do ctrl o to expand it and just see what it's doing yeah code architecture is reviewing i don't know all of this stuff is so cool to me okay So while that's all going, let's go back. All right, Pulse Tool Use Hooks. I don't know why it's hard to say, but we use a Pulse Tool Use Hook to format cloud codes. Cloud usually generates well-formatted code out of the box, and the hook handles the last 10% to avoid formatting errors in CI later. This one, there's not much to show. You can create one just saying Pulse Tool Use, and it's very similar to pre-commit hooks. It's nothing new here. All right, slash permissions and not dangerously skipped. Number 10, I don't use dangerously skipped permissions. Instead, I use slash permissions to pre-allow common bash commands that I know are safe in my environment. To avoid unnecessary permission prompts, most of these are checked into .cloud slash settings.json and shared with the team. This is what I talk about in compound engineering where you need to start putting things like this. into the code base and share with the team a team needs to be like ai native first and everyone has to kind of start agreeing on some of these these like ways that we need to work and that's how you really move quickly but yeah so quickly showing you guys you can do slash permissions here and then yeah slash permissions there's a bunch of things here and i would just say you can update this manually right can you update my permissions list so that all bash scripts are okay to run for example you could do that like i keep saying this but don't manage your clock code instance manually you know just have clock code do it and then after you do this you can always push all of this directly into the code base you see it's uh change trying to change the settings right now all right While that's going, tip number 11, MCP for all tools. Slack, BigQuery, Sentry, Cloud uses your tools, not your code base. 11, Cloud Code uses all of my tools for me. It often searches and posts to Slack via the MCP server. Run BigQuery's questions to answer analytic questions using a BigQuery CLI. Grabs error logs from Sentry and Slack MCP configurations. It's checked into our MCP JSON and shared with Teams. Now, I always say be careful with MCPs because they're known to blow up your context window. Only leverage it when you need it for very specific things. If you see what these are, these are very outside of the norm of regular coding. And even like Slack, right? So we have this integration similar to our internal communication channel. And I use this with a combination of our PR reviewing thing where I'll just pull all of my context from the PRs, read the diffs that I wrote this week. and then i'll have it summarize that and then like send status reports to like specific threads that i want so using clock code to manage your work besides just coding is like a whole like big thing now there's not much to show here but for mcps you should always just kind of be careful because i i think like mcp is also another place where prompt injection is gonna start happening same thing with downloading plugins and stuff like that i think Just be careful when you're doing these and just always have Cloud Code review the MCP before you install it. Okay, for number 12, long running tasks. For very long running tasks, I will either prompt Cloud to verify his work with the background agent when it's done. Use agent stop hook to do that more deterministic or use Ralph Wiggin plugin. I will also use either permission mode equals don't ask or dangerously skip. in sandbox to avoid permission problems for the sessions so claude isn't blocked on me so now i don't really use dangerously skip too often or even ralph wigan i tried ralph wigan ralph is this right so this is the ralph wigan loop basically you just have a task you have the agent you have the file system and then it just keeps looping until it's finished i don't really like this because i feel like there's it's too i don't know there's just so much uh work that needs to happen for you to have like a spec that's like so perfect that you can just have something like ralph build the whole thing but honestly for side projects and things like that i might just spec the whole thing out and i don't really care too much and and it's it's okay to let it run uh overnight or whatever and and it's okay and the whole idea is like you do it a few times maybe and then get a different result every single time. And then you kind of test out if it's good and then you could throw it away and then start engineering. I think there are times when it's actually pretty good. I think the hype around it has died quite a bit. But yeah, like if you want to use it, I'm not going to show how to use it here, but you just install the plugin that I showed you earlier and then just start installing it. But to do dangerously skip permissions, it's very easy to do that. So for example, when you're here, let's exit here. When you do Claude, you can do just Claude dangerously skip permissions like that. And then now when you ask Claude to run something, it won't ask you any permissions, basically. It's OK. 13, a final tip, probably the most important thing to get great results out of Claude code, give Claude a way to verify his work. If Claude has that feedback loop, it will 2 to 3x the quality of final results. Claw tests every change I land in claw.ai slash code using the Chrome extensions. It opens the browsers, tests the UI, and iterates until it works. So let's give this a try. Can you run an end-to-end integration test navigating the website from the homepage to the detail page when you click on a poster? Make sure the title is the same. Okay, so it just launched the website. I'm going to try to show it. Okay, there you go. check that out okay so it navigated to the main website all right so now it went into the detail page and it's clicking on stuff you can see that it's like taking screenshots and stuff it's very cool and this is kind of this agentic validation thing that i'm talking about in one of my other videos and look it passes it like tells you what it did very very cool and this is like a different form of end to end right it's not it's i didn't like write an end-to-end test per se right it just kind of knew how to do it and navigate you can do really a lot of interesting things here so that's boris chenley's workflow i hope you guys enjoy this i think one of the really interesting things is that if you think about what your work might have looked like six months ago and then you compare it to like boris's workflow it's probably like night and day right we were still manually coding at that point but now we have like multiple um clock code instances just going at all times, multiple clock code instances. And you're just like playing StarCraft over here, you know, basically saying, hey, file this PR over here. And then you go to the next one and then you go down and go, oh, update my like backlog task or fix this bug. And you switch over. Now, I know probably this is context switching wise mentally is probably the bottleneck at this point. And these little quick prompts that I'm doing is obviously not ideal. But you should really challenge yourself to try to like take some of the learnings here. Try it yourself. Like one thing I'm going to do this week is definitely figure out how to do the teleport things more often. Obviously, I can't do it for my work because we don't have slash teleport yet. But for my personal products, I could just see myself doing this. And I want to build like an entire agentic validation on GitHub so that I can just. do clock code sessions on my phone and actually code you know i did a video around kind of trying to do this with happy but in that workflow it's very hard to test the flow but with github actions if it can actually navigate the web and send me like a gif of like what it did then it makes me feel a lot more safe and and i just know that it's validated itself using screenshots and stuff like that but yeah i hope you guys enjoyed this video on boris chenry's clock code setup and go and check out my other cloud code videos and my engineering videos and until i see you guys on the next one bye

I met Boris Cherny, the creator of Claude Code, and asked him about his personal setup. He told me he'd posted about it publicly. So I went through every tip in that thread, showed what it actually looks like in practice, and shared my own thoughts on what's worth stealing.

Check out my newsletter where I write about AI and give away some of my personal Claude Code workflows: https://getpushtoprod.substack.com/

📽 Videos You Might Ike
How I use Claude Code (Meta Staff Engineer Tips) https://youtu.be/mZzhfPle9QU?si=vT3htDZl8wkp3bBy

Claude Code Workflows That Will 10x Your Productivity
https://youtu.be/yZvDo_n12ns?si=0KaQMKmaQD5BykC-

⏱️ TIMESTAMPS
0:00 - Who is Boris Cherny and why this matters
0:19 - Boris's philosophy: "My setup might be surprisingly vanilla"
1:31 - Tip 1: Run 5 Claude instances in parallel
3:10 - Tip 2: 5-10 web Claudes + the /teleport feature
5:00 - Tip 3: Opus with extended thinking, always
5:54 - Tip 4: Share your CLAUDE.md across the whole team
7:08 - Tip 5: Add Claude to your code reviews (GitHub Action)
8:06 - Tip 6: Plan mode first, then auto-accept
9:52 - Tip 7: Slash commands for every inner loop workflow
12:00 - Tip 8: Custom subagents (Code Simplifier, Verify App)
14:00 - Tip 9: Post tool use hooks for auto-formatting
14:30 - Tip 10: /permissions instead of --dangerously-skip
15:44 - Tip 11: MCP for Slack, BigQuery, Sentry
17:14 - Tip 12: Long running tasks and background agents
19:14 - Tip 13: Give Claude a feedback loop (2-3x quality)

📲 CONNECT WITH ME
► LinkedIn → https://www.linkedin.com/in/jonnykvids
► Threads →  https://www.threads.net/@jonnykvids

Need a study buddy? Check out my free app Anime Pomodoro App
https://apps.apple.com/us/app/anime-pomodoro/id6749815827

👍 Like, Subscribe & Hit the Bell for more software engineering insights!

#ai #claudecode #claude