AI Coding Tips Thread

[mid_gen]

Remembered I get some passes for a free week's Claude Pro. Don't want put the link here as it'll just get scraped, but if anyone wants one drop me a PM. IT does need you to put payment details in I believe so it'll be up to you to cancel.

No kickbacks for me with this btw...

 

[mid_gen]

The little dev house I work at has been tinkering with AI for a while now but yes, we're all copy-pasting back & forth using chat agents - mostly Claude but we'll skip around when we run out of free credits
We're old boys so it's taken a minute for us to cotton on to what coding with AI really means. Boss man is now looking at organising a proper licence for us - likely Claude Code.

Can Claude Code be set up to "see" only the solution you're currently working on? ie could we have a distinct agent PER solution?
We specifically don't want to give it access to our devops repo and don't want it pulling from customer A's code to solve a problem for customer B.

Yes, you open your terminal and navigate to your repository, and run 'claude', it then starts up and that directory is its working directory. You *can* tell it to access stuff outside that working directory, but it'll need explicit permission.

Tis very useful for full stack applications, as it can explore all the different services at the same time to investigate and fix stuff.

I typically have 4 Visual Studio Code instances running, each with a separate Claude Code window, all on different repos. I also have a couple of terminals open, also running Claude, for general stuff.

 

[Mesai]

The little dev house I work at has been tinkering with AI for a while now but yes, we're all copy-pasting back & forth using chat agents - mostly Claude but we'll skip around when we run out of free credits
We're old boys so it's taken a minute for us to cotton on to what coding with AI really means. Boss man is now looking at organising a proper licence for us - likely Claude Code.

Can Claude Code be set up to "see" only the solution you're currently working on? ie could we have a distinct agent PER solution?
We specifically don't want to give it access to our devops repo and don't want it pulling from customer A's code to solve a problem for customer B.

You'd typically open the project in your respective IDE, which scopes the terminal to that parent directory. Running "claude" in the terminal will only give it access to that folder (usually asks for permission/trust on first use). Anything outside of that it'll ask for permission, which you can grant on either a temporary/session level or permanent.

This is how I work but I've also built an MCP server that allows Claude to safely interact with other projects like custom libraries that the current project depends on.

 

[iamgigglz]

Thanks @mid_gen and @Mesai - that's perfect.

 

[On Holiday]

I've been knocking stuff up with Claude in my browser using Opus 4.5/4.6.

Primarily things that just have one python script or html file that I can copy into the server rather than give it any form of direct access / git.

Am I really gimping the performance/efficacy of the code it generates by doing it in the browser as opposed to some terminal/plugin? I'm seeing mixed opinions online.

 

[Mesai]

I've been knocking stuff up with Claude in my browser using Opus 4.5/4.6.

Primarily things that just have one python script or html file that I can copy into the server rather than give it any form of direct access / git.

Am I really gimping the performance/efficacy of the code it generates by doing it in the browser as opposed to some terminal/plugin? I'm seeing mixed opinions online.

For a single script you aren’t going to see much difference, although it is less efficient as it can rewrite entire files instead of doing block edits, but I think that’s been improved.

If the script becomes big enough that it justifies being a project, you’re much better off using an IDE or even just the terminal.

I only ever really use the chat to brainstorm new ideas or do research, but rarely for actual coding.

 

[mid_gen]

I've been knocking stuff up with Claude in my browser using Opus 4.5/4.6.

Primarily things that just have one python script or html file that I can copy into the server rather than give it any form of direct access / git.

Am I really gimping the performance/efficacy of the code it generates by doing it in the browser as opposed to some terminal/plugin? I'm seeing mixed opinions online.

The actual quality of the code it generates won’t be any different.

The benefits are in productivity. The coding agents can do stuff like search files for you, edit any file, they can make new files, create test frameworks., execute tests, run builds, read the build output, automatically fix any errors. They can access APIs directly through cURL and test interfaces.

Basically it does all the driving for you. Let it takes care of all the donkey work.

 

[chrismscotland]

I'm no coder but have been using ChatGPT and CoPilot to some extent for updating and improving some of the scripts and tools I use as a Workplace Engineer (M365/InTune/Azure mainly); but recently started playing around with Claude.
I'm really impressed with what its been able to do in a short time with fairly basic instructions and requirements being able to create a Note-taking app for Android and Windows.

For a long time I've dabbled with Power Platform / MS Power Apps stuff; I don't really see why organisations would go for "no code" when they can use things like Claude Code and get "proper" albeit I'm sure not "clean" code apps.
However like others have said I expect more experienced developers will be able to save loads of time with the automation capabilities of some of these tools.

 

[iamgigglz]

I've been running Claude Code (2.1.59) on a 7 day trial and love it - especially the concept of multiple agents for different parts of the project.
My only complaint is a constant 7% CPU usage, even when idle. It's just enough to keep my laptop fan going at an annoying speed - quite possibly a deal-breaker.

 

[NickK]

There's a few AI threads knocking about now, but thought one just focused on coding tools would be good.

The state of the art is moving so rapidly at the moment, and new tools and tech appearing so fast, it's hard to stay on top. Share your best tips here!

Today I've been configuring a couple of Sub Agents in Claude. One is a miserable C++ programmer like me that is an old school guy that insists on clean, well engineering code, with minimal dependencies. One is a Fintech specific reviewer that ensures certain domain specific stuff is adhered to.

I've added a pre-commit hook to Claude to make sure any changes are run past both these sub agents. Works really well, it now addresses all teh stuff that I was having to nag Claude about before.

Second thing today, I've added the Playwright MCP server, which is a web automation system (that we also use for E2E testing). What this means is that Claude can inspect the debug browser window (web app I'm developing), and instead of guessing it's got things right, it can now capture screenshots and inspect the images, click through the app, and make sure it actually works as expected. Pretty cool stuff.

The fun is solving a real world problem.

I'd configure as a group agents as a team that all peer reviewing, and they focus on the problem domain and that the code solves the problem:
1 is a domain expert analyst - answers domain questions and confirms domain solutions are at least viable
1 is a security expert analyst- ensures that the problem and the proposed solutions are secure (not just the code)
1 operational expert analyst - ensures that the final solution is operationally viable - that includes business continuty, target operational model, operational cost and integration
5 coding sub agents
1 coding standards agent

1 product leader - reviews and approves the suggestions and sequence/timeline to maximise return and ensure both build and operation meet both financial and risk targets.

The pipeline would then have a separate set of analysts that are reviewing the solution and code. It would also have security scanning.

I would also have a cycle of brain storming - new ideas and functionality plus changes to improve the solution (rather than code - you're prompt-to-opcode at this point anyway).

 

[mid_gen]

The fun is solving a real world problem.

I'd configure as a group agents as a team that all peer reviewing, and they focus on the problem domain and that the code solves the problem:
1 is a domain expert analyst - answers domain questions and confirms domain solutions are at least viable
1 is a security expert analyst- ensures that the problem and the proposed solutions are secure (not just the code)
1 operational expert analyst - ensures that the final solution is operationally viable - that includes business continuty, target operational model, operational cost and integration
5 coding sub agents
1 coding standards agent

1 product leader - reviews and approves the suggestions and sequence/timeline to maximise return and ensure both build and operation meet both financial and risk targets.

The pipeline would then have a separate set of analysts that are reviewing the solution and code. It would also have security scanning.

I would also have a cycle of brain storming - new ideas and functionality plus changes to improve the solution (rather than code - you're prompt-to-opcode at this point anyway).

You can do this pretty easily in Claude Code. I just have one custom agent for my Unreal stuff right now (which is prompted to be an Unreal expert and enforce good Unreal patterns, look for performance code smells etc).

Just make the custom agent in Claude, save down to your project config....then add it into your Claude.MD and the orchestrator will take care of it.

You can go much deeper than that obviously, but CC makes these things pretty trivial

 

[Mr Jack]

Claude Code really is something else. I'd tried other AI coding things before and found them to be somewhere between useless and actively harmful, but this? I gave it a couple of tests this morning, the first doing a refactor on a PHP/JS hobby project, and the second against the million line C++ codebase that I spend most of my work time working on, giving it a ticket I had from last week to solve. In both cases, it needed to be given further instruction to get it right but in both cases it did it substantially faster than I could.

If think this stuff is going to be mandatory for professional programmers from here on.

 

[GeorgeStorm]

Not tried Claude Code, but have tried 'Junie' as part of rider recently, having previously just used chatgpt or the 'normal' llm within rider for bits and pieces.
Something I'm aware I need to try and make more use of/become better at using as the tools will only get better, but personally makes work less interesting if anything rather than more

 

[mid_gen]

Claude Code really is something else. I'd tried other AI coding things before and found them to be somewhere between useless and actively harmful, but this? I gave it a couple of tests this morning, the first doing a refactor on a PHP/JS hobby project, and the second against the million line C++ codebase that I spend most of my work time working on, giving it a ticket I had from last week to solve. In both cases, it needed to be given further instruction to get it right but in both cases it did it substantially faster than I could.

If think this stuff is going to be mandatory for professional programmers from here on.

No way I could go back to not using coding agents and actually typing every character of code in like a caveman. It'd be like going back to using punch cards.

Anyone not learning how to use these tools is going to get left behind...well, at some point you'll have to come round.

Absolutely no way I could do what I'm doing at the moment building my own game studio while working full time on client work without Claude Code. Not just making the actual coding of the games quicker (because I've done that for a very long time professionally).....but just filling the gaps in areas outside my expertise. Building CI workflows, writing shaders, building website stuff, various automations and plugins. Completely transformational, especially for small nimble businesses that can suddenly get so much more done so quickly.

 

[Noxia]

I spent a few hours learning how to use CC properly the other day. Going through setting up the MD files to set it up with ‘skills’, screenshot loop (was using it for frontend) etc, was way more to it than I initially thought.

 

[mid_gen]

I spent a few hours learning how to use CC properly the other day. Going through setting up the MD files to set it up with ‘skills’, screenshot loop (was using it for frontend) etc, was way more to it than I initially thought.

if you're doing web work, it's worth installing the chrome extension. It lets CC connect straight to the browser, it can test drive stuff itself, access all the dev tools. Playwright MCP (can be installed from the plugin marketplace /plugin ) is also very powerful for that kind of thing.

 

[Mr Jack]

No way I could go back to not using coding agents and actually typing every character of code in like a caveman. It'd be like going back to using punch cards.

Anyone not learning how to use these tools is going to get left behind...well, at some point you'll have to come round.

Not sure I share your enthusiasm for it, but I agree with the latter sentiment. What's a good place to go and read about setting up Claude properly for a project?

 

[mid_gen]

What's a good place to go and read about setting up Claude properly for a project?

Claude

Getting your Claude.MD right is the critical thing. It's added to the context of every agent. You can ask it to author it for you.....it's also worth making sure the Claude.MD includes an instruction to keep the Claude.MD updated, so as you make changes, it should keep itself maintained.

 

[Mesai]

Not sure I share your enthusiasm for it, but I agree with the latter sentiment. What's a good place to go and read about setting up Claude properly for a project?

These things change so rapidly that I end up changing my approach almost monthly. The docs are decent in terms of what config is available, but I'll often ask Claude in a project session for suggestions on managing it's context for that scenario and to have it write those prompts itself as it'll be better at describing what's needed.

The healthiest way to use these agents is to be constantly sceptical and focus on acceleration rather than replacement. Claude Code is probably top of the list as far as agents go but it still makes a ton of mistakes so you're either writing the important code yourself and having Claude fill in the gaps, or letting it do everything but spending the time to thoroughly review everything, which is ultimately harder since it's the same as reviewing someone else's code.

Most of the hype and "it'll replace developers" is from people who used it to write a hobby calculator app, or companies with really simple code.

 

[Mr Jack]

The healthiest way to use these agents is to be constantly sceptical and focus on acceleration rather than replacement. Claude Code is probably top of the list as far as agents go but it still makes a ton of mistakes so you're either writing the important code yourself and having Claude fill in the gaps, or letting it do everything but spending the time to thoroughly review everything, which is ultimately harder since it's the same as reviewing someone else's code.

Yeah, totally. That's what I see in my tests so far, what it does is impressive but flawed, it needs work -- and more importantly knowledge -- to get it to generate code fit to check in.