completely different coding setups individuals use for programming. On this article, I’ll take you thru my private coding setup and the instruments and purposes that I take advantage of to realize most effectivity when programming.
It is a setup that I’ve created via intensive testing and experimenting myself via trial and error. Whereas testing, I’ve tried to make use of a number of completely different purposes for programming, and every of them has benefits in numerous settings.
I’ll take you thru the present coding setup I’ve, although it’s, after all, topic to alter quickly sooner or later with the speedy development of LLM know-how.
I’m not sponsored by any of the tooling talked about on this video, and it’s merely the tooling I take advantage of on a day-to-day foundation as a programmer.
Why optimize your coding setup
As a programmer, your coding setup is likely one of the most vital components you possibly can optimize. That is the place you spend most of your time fixing completely different issues. Due to on a regular basis you spend along with your coding setup, you must spend time ensuring it’s optimized to your private workflows.
Personally, I all the time search for alternatives to make my setup extra environment friendly. For an extended time period, I used Cursor every day because the platform from which I did all my coding. A couple of weeks in the past, I all of a sudden shifted to utilizing purely Claude Code via Warp, which primarily makes up nearly all of my coding setup.
The swap from utilizing Cursor to utilizing Claude Code via Warp was some of the vital productiveness will increase I’ve skilled since I first observed how environment friendly brokers may program for me. Warp + Claude Code has helped me massively in my each day work as an information scientist in a startup engaged on doc AI.
Strolling via my coding setup
On this part, I’ll stroll you thru the completely different tooling, methods, and approaches I take advantage of to optimize my coding setup. I’ll cowl the purposes I take advantage of on a day-to-day foundation, but in addition how I make the most of and get essentially the most out of those purposes and different vital methods I take advantage of to make my coding as efficient as potential.
The entire ideas I’ll cowl on this part have a big impression on my productiveness as an engineer.
Tooling
Initially, I need to cowl the tooling I take advantage of. I take advantage of Claude Code and Warp for nearly all of my coding. If I need to test some manufacturing logs or if I need to repair a bug or implement a brand new characteristic, I’ll primarily all the time use Claude Code in Warp.
Inside Warp, I’ve the next setup. I’ve every tab in Warp as a separate folder I’m working in. So if I’m working in folder A, that’s my first tab in Warp. And if I’m working in folder B, that’s my second tab. Now, I sometimes discover myself having a number of brokers operating inside the identical folder. On this case, I make a break up pane utilizing CMD + D in Warp, so my tab is break up into a number of panes. Relying on the duty I’m engaged on, I may have as much as 5 brokers working inside the identical repository. After which I’ve completely different repositories in numerous Warp tabs.
I need to observe one exception the place I take advantage of Cursor as a substitute of Claude Code: Once I want full management of the code. For instance, if the characteristic is of essential significance or part of essential infrastructure. Additionally, sometimes once I run vital migration scripts or backfilling scripts, I’ll additionally do it in Cursor as a result of this offers me extra management of the code. I may run the code myself via interactive home windows with Python.
Git worktrees
As I discussed in my earlier part, I typically discover myself operating a number of brokers inside the identical repository. When you’ve got a number of brokers updating recordsdata on the identical time in the identical repository, you’ll run into issues with brokers colliding with one another. To unravel this downside, you need to use Git Worktrees.
Git worktrees are primarily copies of Git repositories that you could make to have brokers run utterly separate from one another. So each time I spin up a brand new agent, I inform it to begin a brand new git worktree for what it’s engaged on. and that agent can now work utterly individually from all different brokers working in the identical repository.
That is a vital characteristic if you wish to work with parallel brokers in Claude Code (which is likely one of the main advantages of working with Claude Code). Thus, you must positively be using Git Worktrees in your day-to-day programming with parallel brokers.
Slash instructions
Slash instructions are one other very highly effective characteristic. Slah instructions are primarily saved prompts, so you possibly can rapidly entry a immediate that you’ve got saved on a earlier event. For instance, in case you have a really repetitive immediate, you must retailer it as a slash command. Some examples of this are:
Slash instructions are extremely highly effective, and I’ve coated them in one in all my earlier articles. The advantage of slash instructions is twofold. Initially, you save time by not having to jot down out the immediate each time. So as a substitute of getting to jot down out an extended immediate, telling the mannequin that it must:
- Pull the newest dev department and rebase on high of it
- Run precommit checks
- PR description
- Make a pull request from a characteristic department to dev
As a substitute of getting to jot down out all of this, you possibly can merely retailer this immediate in a slash command and entry the immediate immediately.
The second benefit is that you just get to be extra constant when writing your prompts. For instance, when creating pull requests to dev, as I discussed, you would need to run a collection of checks (pull newest dev department, rebase, run precommit checks, …). When you write this out each time, you danger forgetting components of the immediate. This isn’t an issue when you use slash instructions, nonetheless, since you’ll all the time be using the identical immediate, and also you’ll be extra constant.
Slash instructions make you each quicker and extra constant
Low threshold to fireside off brokers
One other subject I need to cowl is that you must have an excellent low threshold to fireside off brokers to carry out duties for you. Each time you possibly can consider a brand new job or get a brand new downside it’s important to resolve, you must simply fireplace off an agent. For instance, if I discover a button that’s misaligned, some textual content in my software that must be up to date, or translations that must be up to date. I merely fireplace off a brand new agent, let it run absolutely autonomously, and create a pull request for me.
The primary level is that you must have a low threshold to fireside off brokers as a result of it’s so low cost to run and prices you so little time. The price of firing a brand new agent is actually spending time writing out a very good immediate and, in lots of instances, answering a number of questions the brokers have so that you can correctly perceive the duty you gave them.
There are actually many instruments on the market that supply plenty of token utilization for a comparatively low worth. For instance, I’m utilizing the $200 Claude Code subscription, which is a set quantity per 30 days, and I’ve by no means run into fee limits. This implies I can fireplace off as many brokers as I can with out further price.
Make the most of the most effective fashions
One other tip I’ve would possibly sound very apparent, however I all the time advocate utilizing the most effective fashions everytime you work with programming. The explanation for that is that in the long run, this protects you each money and time.
Sure, the most effective fashions are sometimes the costliest fashions per token and are additionally the slowest fashions. Nevertheless, it seems that when you use cheaper fashions, they are going to extra typically make errors, which takes further time so that you can repair and iterate on, which once more makes the mannequin make the most of much more tokens. Thus, ultimately, it typically seems that utilizing a less expensive, smaller mannequin truly seems to be dearer and time-consuming.
It is best to subsequently be using the frontier fashions comparable to Gemini 3 Professional, Claude 4.5 Opus, and GPT 5.2 Codex. There are additionally some up-and-coming open supply fashions performing nicely on the coding benchmarks, although I haven’t achieved the identical success with open supply fashions as I’ve achieved with frontier closed supply fashions.
Conclusion
On this article, I’ve coated the best way to have a most effectivity coding setup. I’ve mentioned the coding setup I take advantage of on a day-to-day foundation, the place I take advantage of the Warp terminal with Claude Code. Moreover, I take advantage of particular methods comparable to organizing Warp with break up panes and tabs by the folder I’m engaged on. I’m additionally ensuring to all the time use the newest and greatest coding fashions. I imagine spending time optimizing your coding setup is an excellent use of time. As a programmer, your coding setup is likely one of the belongings you spend essentially the most time with, and if you may make that a number of proportion factors extra environment friendly, it can probably repay in the long term.
👉 My Free Assets
💌 Substack
🚀 10x Your Engineering with LLMs (Free 3-Day E-mail Course)
📚 Get my free Imaginative and prescient Language Fashions e book
💻 My webinar on Imaginative and prescient Language Fashions
👉 Discover me on socials:
🧑💻 Get in contact
✍️ Medium
