[HN Gopher] Getting good results from Claude Code
       ___________________________________________________________________
        
       Getting good results from Claude Code
        
       Author : ingve
       Score  : 198 points
       Date   : 2025-08-08 13:45 UTC (9 hours ago)
        
 (HTM) web link (www.dzombak.com)
 (TXT) w3m dump (www.dzombak.com)
        
       | aosaigh wrote:
       | I'm just today after having my first real success with Claude
       | (and generally with coding agents). I've played with Cursor in
       | the past but am now trying Claude and others.
       | 
       | As mentioned in the article, the big trick is having clear specs.
       | In my case I sat down for 2 hours and wrote a 12 step document on
       | how I would implement this (along with background information).
       | Claude went through step by step and wrote the code. I imagine
       | this saved me probably 6-10 hours. I'm now reviewing and am going
       | to test etc. and start adjusting and adding future functionality.
       | 
       | Its success was rooted in the fact I knew exactly how to do what
       | it needed to do. I wrote out all the steps and it just followed
       | my lead.
       | 
       | It makes it clear to me that mid and senior developers aren't
       | going anywhere.
       | 
       | That said, it was amazing to just see it go through the
       | requirements and implement modules full of organised documented
       | code that I didn't have to write.
        
         | philipwhiuk wrote:
         | Frankly, even if you ignore Claude entirely, being able to
         | write a good spec for yourself is a worthwhile endeavour.
        
           | aosaigh wrote:
           | Complete agree. It's a core skill of a good developer. What's
           | interesting is that in the past I'd have started this process
           | but then jumped into coding prematurely. Now when you know
           | you are using an agent, the more you write, the better the
           | results.
        
             | danielbln wrote:
             | Yes but let's not forget the lessons of waterfall planning.
             | You can't anticipate everything, so the detail level of the
             | implementation plan should be within a goldi locks zone of
             | detailed but not too detailed, and after each
             | implementation and test phase one should feel comfortable
             | adjusting the spec/plan to the current state of things.
        
               | aosaigh wrote:
               | Another good point. I noticed this happening while
               | writing my document.
               | 
               | A few times while writing the doc I had to go back and
               | update the previous steps to add missing features.
               | 
               | Also I knew when to stop. It's not fully finished yet.
               | There are additional stages I need to implement. But as
               | an experienced developer, I knew when I had enough for
               | "core functionalty" that was well defined.
               | 
               | What worries me is how do you become a good developer if
               | AI is writing it all?
               | 
               | One of my strengths as a developer is understanding the
               | problem and breaking it down into steps, creating
               | requirements documents like I've discussed.
               | 
               | But that's a hard-earned skill from years of client work
               | where I wrote the code. I have a huge step up in getting
               | the most from these agents now.
        
               | danielbln wrote:
               | Agents raise the floor for all, but they raise the
               | ceiling for those of us with sufficient priors.
        
               | closewith wrote:
               | The downside of waterfall was not overly detailed specs.
               | In fact, the best software development is universally
               | waterfall following a good, ideally formal spec.
               | 
               | The downside that Agile sought to remedy was
               | inflexibility, which is an issue greatly ameliorated by
               | coding agents.
        
               | danielbln wrote:
               | Maybe if you know the entire possibility space
               | beforehand, in which case that's a great position to be
               | in. In other cases and if the spec doesn't align with
               | reality after implementation has begun or unforseen
               | issues pop up, the spec needs revision, does it not?
        
               | zer00eyz wrote:
               | > In other cases and if the spec doesn't align with
               | reality after implementation has begun or unforeseen
               | issues pop up, the spec needs revision, does it not?
               | 
               | Yes and then it gets pumped back to the top of the
               | waterfall and goes through the entire process. Many
               | organizations became so rigid that this was a problem. It
               | is what Tom Smykowski in office space is a parody of.
               | It's why you get much of the early web having things like
               | the "feature creep" and "if web designers were
               | architects".
               | 
               | Waterfall failed because of politics mingled into the
               | process, it was the worst sort of design by committee. If
               | you want a sense of how this plays out you simply have to
               | look at Wayland development. The fact that is has been as
               | successful as it is, is a testament to the will and
               | patience of those involved.
        
         | esafak wrote:
         | You can use Claude to write the spec next time.
        
         | mft_ wrote:
         | Can you (or anyone) share an example of such a specification
         | document? As an amateur programmer experimenting with CC, it
         | would be very helpful to understand the nature and depth of the
         | information that is helpful.
        
           | bongodongobob wrote:
           | I do a multistep process
           | 
           | Step 1: back and forth chat about the functionality we want.
           | What do we want it to do? What are the inputs and outputs?
           | Then generate a spec/requirements sheet.
           | 
           | Step 2: identify what language, technologies, frameworks to
           | use to accomplish the goal. Generate a technical spec.
           | 
           | Step 3: architecture. Get a layout of the different files
           | that need to be created and a general outline of what each
           | will do.
           | 
           | Step 4: combine your docs and tell it to write the code.
        
           | jamesponddotco wrote:
           | I have multiple system prompts that I use before getting to
           | the actual specification.
           | 
           | 1. I use the Socratic Coder[1] system prompt to have a back
           | and forth conversation about the idea, which helps me hone
           | the idea and improve it. This conversation forces me to think
           | about several aspects of the idea and how to implement it.
           | 
           | 2. I use the Brainstorm Specification[2] user prompt to turn
           | that conversation into a specification.
           | 
           | 3. I use the Brainstorm Critique[3] user prompt to critique
           | that specification and find flaws in it which I might have
           | missed.
           | 
           | 4. I use a modified version of the Brainstorm Specification
           | user prompt to refine the specification based on the critique
           | and have a final version of the document, which I can either
           | use on my own or feed to something like Claude Code for
           | context.
           | 
           | Doing those things improved the quality of the code and work
           | spit out by the LLMs I use by a significant amount, but more
           | importantly, it helped me write much better code on my own
           | because I know have something to guide me, while before I
           | used to go blind.
           | 
           | As a bonus, it also helped me decide if an idea was worth it
           | or not; there are times I'm talking with the LLM and it asks
           | me questions I don't feel like answering, which tells me I'm
           | probably not into that idea as much as I initially thought,
           | it was just my ADHD hyper focusing on something.
           | 
           | [1]: https://github.com/jamesponddotco/llm-
           | prompts/blob/trunk/dat...
           | 
           | [2]: https://github.com/jamesponddotco/llm-
           | prompts/blob/trunk/dat...
           | 
           | [3]: https://github.com/jamesponddotco/llm-
           | prompts/blob/trunk/dat...
        
             | time0ut wrote:
             | Thank you for sharing these prompts. These are excellent.
        
             | indigodaddy wrote:
             | Wish we could star files in addition to repos
        
               | addandsubtract wrote:
               | You mean like adding a bookmark, or downloading the
               | files? Yeah, wish that was possible on the web.
        
               | indigodaddy wrote:
               | Well I use GitHub stars kind of like coding/cool
               | project/idea/whatever bookmarks, so yeah would be neat to
               | be able to star just any file within a repo in addition
               | to the repo itself
        
             | ctoth wrote:
             | You may want to turn these good prompts into slash
             | commands! :)
        
               | jamesponddotco wrote:
               | They are subagents and slash commands, depending on the
               | project. Eventually, I need to come up with a "dotclaude"
               | repository with these and a few others I use in.
               | 
               | Edit: Sorry, I had a brain fart for a second, thought you
               | were talking about other prompts. I prefer to keep those
               | as chats with the API, not Claude Code, but yeah, they
               | might work as slash commands too.
        
             | alecco wrote:
             | Good stuff. A minor observation:
             | 
             | > I use the Socratic Coder[1] system prompt to have a back
             | and forth conversation about the idea. (prompt starts with:
             | 1. Ask only one question at a time)
             | 
             | Why only 1? IMHO it's better to write a long prompt
             | explaining yourself as much as possible (exercises your
             | brain and you figure out things), and request as many
             | questions to clarify as possible, review, and suggestions,
             | all at once. This is better because:                 1. It
             | makes you think deeper and practice writing clearly.
             | 2. Even though each interaction is quite slower, since you
             | are more active and engaged it feels shorter (try it), and
             | you minimize interactions significantly.       3. It's less
             | wasteful as going back and forth        4. You converge in
             | much shorter time as your misconceptions,
             | misunderstandings, problems expressing yourself, or
             | confusion on the part of the LLM are all addressed very
             | early.       5. I find it annoying to wait for the replies.
             | 
             | I guess if you use a fast response conversational system
             | like ChatGPT app it would make more sense. But I don't
             | think that way you can have deep conversations unless you
             | have a stellar working memory. I don't, so it's better for
             | me to write and read, and re-write, and re-read...
        
               | jamesponddotco wrote:
               | I do one question at a time so I don't feel overwhelmed
               | and can answer questions with more details.
               | 
               | I start with an idea between <idea> tags, write as much
               | as I possibly can between these tags, and then go one
               | question at a time answering the questions with as much
               | details as I possibly can.
               | 
               | Sometimes I'll feed the idea to yet another prompt,
               | Computer Science PhD[1], and use the response as the
               | basis for my conversation with the socratic coder, as the
               | new basis might fill in gaps that I forgot to include
               | initially.
               | 
               | [1]: https://github.com/jamesponddotco/llm-
               | prompts/blob/trunk/dat...
               | 
               | [2]: Something like "Based on my idea, can you provide
               | your thoughts on how the service should be build, please?
               | Technologies to use, database schema, user roles,
               | permissions, architectural ideas, and so on."
        
           | taude wrote:
           | Search Claude-code Planning mode. You can use claude to help
           | you write specs. Many YouTube videos, as well. I think spec
           | docs are pretty personal and project specific....
        
         | miroljub wrote:
         | > That said, it was amazing to just see it go through the
         | requirements and implement modules full of organised documented
         | code that I didn't have to write
         | 
         | Small side remark, but what is the value added of the AI
         | generated documentation for the AI generated code. It's just a
         | burden that increases context size whenever AI needs to re-
         | analyse or change the existing code. It's not like any human is
         | ever going to read the code docs, when he can just ask AI what
         | it is about.
        
           | nisegami wrote:
           | It's entirely possible that the parameters that get activated
           | by comments in code are highly correlated with the parameters
           | involved in producing good code.
        
           | infecto wrote:
           | Doc strings within the code could be helpful for both humans
           | and AI. Sometimes spoken word intent is easier to digest then
           | code and help identify side effects for both human and AI.
        
           | felixgallo wrote:
           | frequently your session/context may drop (e.g. claude
           | crashes, or your internet dies, or your computer restarts,
           | etc.). Claude does best when it can recover the context and
           | understand the current situation from clear documentation,
           | rather than trying to reverse engineer intent and structure
           | from an existing code base. Also, the human frequently does
           | read the code docs as there may be places where Claude gets
           | stuck or doesn't do what you want, but a human can reason
           | their way into success and unstick the obstacle.
        
             | manwe150 wrote:
             | From Claude -r you can resume any conversation at any
             | previous point, so there isn't a way to lose context that
             | way. As opposed to compact, which I find makes it act brain
             | dead afterwards for a while
        
               | r_murphey wrote:
               | Oh God yes, I wish there were better tools to help one
               | curate and condense a context when one finds that sweet
               | spot where it's writing great code.
        
             | Der_Einzige wrote:
             | I promise you that token context rot is worse than the
             | gains from added natural language explanations
        
               | felixgallo wrote:
               | This hasn't been my experience.
        
               | alwillis wrote:
               | Keep in mind each Claude subagent gets its own context.
        
           | aosaigh wrote:
           | I'm not sure I agree that I'll never look at the code. I
           | think it's still important to know how the code is working
           | for your own mental model of the app. So in this case I'll be
           | testing and reviewing everything to see how it's implemented.
           | With that in mind it's useful for me as well as serving as
           | context for the AI. That said, you may be right.
        
           | weego wrote:
           | written once, looked at 100 times.
           | 
           | I try to prompt-enforce no line by line documentation, but
           | encourage function/class/module level documentation that will
           | help future developers/AI coding agents. Humans are generally
           | better, but AI sometimes needs a help to stop it not
           | understanding a piece of code's context and just writing it's
           | own new function that does the same thing
        
           | r_murphey wrote:
           | Often someone will have to maintain the code. Whether the
           | maintainer is a human or an AI, an explanation of the intent
           | of the code could be helpful.
        
           | cpursley wrote:
           | Claude's proclivity for writing detailed comments and inline
           | comments and very near perfect commit messages is one of the
           | best things about it.
        
           | SatvikBeri wrote:
           | Examples. Examples are helpful for both humans and LLMs,
           | especially if you have a custom framework or are using an
           | unusual language. And I find I can generate ~10 good examples
           | with LLMs in the time it would take me to generate ~3 good
           | examples manually.
        
           | lurking_swe wrote:
           | This is sort of like asking "why do pilots still perform
           | manual takeoffs and landing even though full autopilot is
           | possible?" It's because autopilot is intended to help pilots,
           | not replace them. Too much could go wrong in the real world.
           | Having some skills that you practice daily is crucial to
           | remaining a good pilot. Similarly, it's probably good to
           | write some code daily to keep skills sharp.
           | 
           | 1) when your cloud LLM has an outage, your manager probably
           | still expects you to be able to do your work for the most
           | part. Not to go home because openai is down lol. You being
           | productive as an engineer should not depend on the cloud
           | working.
           | 
           | 2) You may want to manually write code for certain parts of
           | the project. Important functions, classes, modules, etc.
           | Having good auto-generated docs is still useful when using a
           | traditional IDE like IntelliJ, WebStorm, etc.
           | 
           | 3) Code review. I'm assuming your team does code review as
           | part of your SDLC??? Documentation can be helpful when
           | reviewing code.
        
             | fragmede wrote:
             | > You being productive as an engineer should not depend on
             | the cloud working.
             | 
             | lol where do you work? This obviously isn't true for the
             | entire industry. If Github or AWS or your WiFi/ISP is down,
             | productivity is greatly reduced. Many SaaS company don't
             | have local dev, so rely on the cloud broadly being up.
             | "Should" hasn't been the reality in industry for years.
        
               | lurking_swe wrote:
               | My company deploys everything in the cloud, but we can
               | still do some meaningful work locally for a few hours if
               | needed in a pinch. Out gitlab is self hosted because
               | that's extra critical.
               | 
               | I continue writing code and unit tests while i wait for
               | the cloud to work again. If the outage is a long time, I
               | may even spin up "DynamoDB Local" via docker for some of
               | our simpler services that only interact with DynamoDB.
               | Our apache flink services that read from kafka are a lost
               | cause obviously lol.
               | 
               | It's also a good opportunity to tackle any minor
               | refactoring that you've been hoping to do. Also possible
               | without the cloud.
               | 
               | You can also work on _designing_ new features
               | (whiteboarding, creating a design document, etc). Often
               | when doing so you need to look at the source to see how
               | the current implementation works. That's much easier with
               | code comments.
        
               | xcf_seetan wrote:
               | Well, the only thing i need to write code is to be alive.
               | No Github or AWS? No problem, have local copies of
               | everything. No Claude? ok, i have local llm to give some
               | help. So, internet is not so needed to write code. No
               | IDE's just a CLI? Sure all i need is a text editor and a
               | compiler/linker working. No computer or electricity? Get
               | a pen and paper and start writing code on paper, will get
               | to the computer when possible. I do not depend on cloud
               | working to be productive.
        
               | Xss3 wrote:
               | You said productivity is greatly reduced. He said
               | productivity should not stop.
               | 
               | You are making different points.
        
           | jaggederest wrote:
           | Leaving aside the value for humans, it's actually very
           | valuable for the AI to provide indexed summary documents of
           | what code goes where, what it does, and what patterns it
           | uses, and what entry points and what it's API conventions
           | are.
           | 
           | This is useful because if you just have Claude Code read all
           | the code every time, it'll run out of context very quickly,
           | whereas if you have a dozen 50 line files that summarize the
           | 200-2000 lines of code they represent, they can always be
           | fresh in context. Context management is king.
        
             | xcf_seetan wrote:
             | The way I use Claude is like first i ask about research
             | about what i want to do, what's new, any little known
             | stuff, etc. As soon i get something i like, I ask Claude to
             | make a specification with everything it needs for making
             | this happen (this is for me to understand how things will
             | be done. Then i ask for an analysis of the specification
             | and ways it can make it short, but in a way it understands
             | the specification and can use it to make things happen.
             | When i got the specification ready, I just upload the
             | specification and ask: start building phase 2. And that's
             | it. It just generates the code, i move it to the ide and
             | start reading and change whatever i want. If i find
             | something diferent from the specification, or a new
             | development, i just update the specification.
        
         | spyckie2 wrote:
         | Can't you send the same spec through cursor? Am I missing
         | something there?
        
           | aosaigh wrote:
           | Yes certainly. I'm sure Cursor would do a good job.
           | 
           | That said, I think that the differing UIs of Cursor (in the
           | IDE) and Claude (in the CLI) fundamentally change how you
           | approach problems with them.
           | 
           | Cursor is "too available". It's right there and you can be
           | lazy and just ask it anything.
           | 
           | Claude nudges you to think more deeply and construct longer
           | prompts before engaging with it.
           | 
           | That my experience anyway
        
             | danielbln wrote:
             | Fun fact: there is a Cursor CLI now
        
         | camel_gopher wrote:
         | Many mid and senior developers cannot write specs. I agree with
         | the intent of your statement.
        
         | dewey wrote:
         | After someone mentioned that recently I've started to write
         | really detailed specs with the help of ChatGPT Deep Research
         | and editing it myself. Then getting this exported as a Markdown
         | document and passing it to Cursor really worked very well.
         | 
         | It puts you in a different mind space to sit down and think
         | about it instead of iterating too much and in the end feeling
         | productive while actually not achieving much and going mostly
         | in circles.
        
           | sillyfluke wrote:
           | The test and review cycle is what determines time saved in my
           | view. Since you were satisfied overall I take it that cycle
           | was not too cumbersome?
           | 
           | The parent wrote:
           | 
           | >I imagine this saved me probably 6-10 hours. I'm now
           | reviewing and am going to test etc.
           | 
           | Guessing the time saved prior to reviewing and testing seems
           | premature fron my end.
        
         | The_Fox wrote:
         | I too just yesterday had my first positive experience with
         | Claude writing code in my project. I used plan mode for the
         | first time and gave it the "think harder" shove. It was a
         | straightforward improvement but not trivial. The spec wasn't
         | even very detailed- I mentioned a couple specific classes and
         | the behaviour to change, and it wrote the code I would have
         | expected to write, with even a bit more safety checking than I
         | would have done.
        
         | mfalcon wrote:
         | That's the way I'd used it, I've built a document with all the
         | requirements and then gave it to CC. But it was not a final
         | document, I had to go back and make some changes after
         | experimenting with the code CC built.
        
         | noiv wrote:
         | This is the way.
        
         | andrewgleave wrote:
         | Yeah. Read "Programming as Theory Building" by Naur [1] to
         | understand why you need to still need to develop a theory of
         | the problem and how to model it yourself lest the LLM concoct
         | (an incorrect) one for you.
         | 
         | [1] https://gwern.net/doc/cs/algorithm/1985-naur.pdf
        
       | delichon wrote:
       | Asking the agent to perform a code review on its own work is
       | surprisingly fruitful.
       | 
       | I do this routinely with its suggestions, usually before I apply
       | them. It is surprising how often Claude immediately dumps on its
       | own last output, talking both of us out if it, and usually with
       | good reasons. I'd like to automate this double-take.
        
         | doctorhandshake wrote:
         | I found that for a period of time Claude was almost excessively
         | negative when reviewing its own work. It was only after some
         | contemplation that I realized that it was the phrasing of my
         | code review slash command that framed the review with a
         | negative bent, essentially prompting Claude to dump on its own
         | stuff. The phrasing of that prompt has been a focus of a lot of
         | effort on my side since.
        
         | rcfox wrote:
         | Seems like a good use case for a subagent.
         | https://docs.anthropic.com/en/docs/claude-code/sub-agents
        
       | bgirard wrote:
       | I'm playing with Claude Code to build an ASCII factorio-like. I
       | first had it write code without much code supervision. It quickly
       | added most of the core features you'd expect (save/load, options,
       | debug, building, map generation, building, belts, crafting, smart
       | belt placing, QoL). Then I started fixing minor bugs and each
       | time it would break something eg. tweaking movement broke belts.
       | So I prompted it to add Playwright automation. Then it wasn't
       | able to write good quality tests and have them all pass, the test
       | were full of sleep calls, etc...
       | 
       | So I looked at the code more closely and it was using the React
       | frontend and useEffect instead of a proper game engine. It's also
       | not great at following hook rules and understanding their timing
       | in advance scenarios. So now I'm prompting it to use a proper
       | tick based game engine and rebuilding the game up, doing code
       | reviews. It's going 'slower' now, but it's going much better now.
       | 
       | My goal is to make a Show HN post when I have a good demo.
        
         | FeepingCreature wrote:
         | Yep, human contribution is extremely valuable especially very
         | early in before the AI has a skeleton it can work off of. You
         | have to review those first few big refactors like a hawk. After
         | that you can relax a bit.
        
       | berlinismycity wrote:
       | Including Claude Code into the normal subscription was a genius
       | move by Anthrophic. It's so much better than copy and pasting
       | code from chat windows, but that's hard to tell if I had to pay
       | via an API for that service
        
       | iambateman wrote:
       | if you use Laravel, I wrote github.com/iambateman/speedrun to
       | help get good results. You type /feature [[description of
       | feature]] and it takes it from there.
       | 
       | The system helps you build out a spec first, then uses a few
       | subagents which are tuned for placing files, reviewing for best
       | practice, etc.
       | 
       | I've been using it for about a week and about 70% of my Claude
       | Code usage runs through /feature right now.
       | 
       | The nice thing is you can give it a _lot_ of requests and let it
       | run for 10-15 minutes without interruption. Plus, it makes a set
       | of planning documents before it implements, so you can see
       | exactly what it thought it was changing.
        
         | wriggler wrote:
         | Using this now - works brilliantly! What makes it Laravel
         | specific? Would also love to use this with a React Native app
         | I'm struggling to build.
        
       | tobyhinloopen wrote:
       | That's a great, short prompt. I'm going to steal it.
        
         | OJFord wrote:
         | Do you mean the claude.md?
        
       | softwaredoug wrote:
       | I get a lot of success when I've laid out the patterns and first
       | implementation of an idea in my code. Then tell Claude to repeat
       | the pattern to implement X feature.
       | 
       | And do it very step by step in what would equate to a tiny PR
       | that gradually roles out the functionality. Too big and I find
       | lots of ugly surprises and bugs and reorganizations that don't
       | make sense.
        
       | time0ut wrote:
       | I've been working with Claude Code daily for a month or so. It is
       | quite excellent and better than the other agents I have used
       | (Cursor, Q). This article has some good tips that echo some of
       | the things I have learned.
       | 
       | Some additional thoughts:
       | 
       | - I like to start with an ideation session with Claude in the web
       | console. I explain the goals of the project, work through high
       | level domain modeling, and break the project down into milestones
       | with a target releasable goal in mind. For a small project, this
       | might be a couple hours of back and forth. The output of this is
       | the first version of CLAUDE.md.
       | 
       | - Then I start the project with Claude Code, have it read my
       | global CLAUDE.md and the project CLAUDE.md and start going. Each
       | session begins this way.
       | 
       | - I have Claude Code update the project CLAUDE.md as it goes. I
       | have it mark its progress through the plan as it goes. Usually,
       | at the end of the session, I will have it rewrite a special
       | section that contains its summary of the project, how it works,
       | and how to navigate the code. I treat this like Claude's long
       | term memory basically. I have found it helps a lot.
       | 
       | - Even with good guidelines, Claude seems to have a tendency to
       | get ahead of itself. I like to keep it focused and build little
       | increments as I would myself if it is something I care about. If
       | its just some one off or prototype, I let it go crazy and churn
       | whatever works.
        
         | kace91 wrote:
         | Does the $20 subscription hold a similar bang for your buck as
         | cursor?
         | 
         | I'm curious about the tool but I wonder if it requires more
         | significant investment to be a daily driver.
        
           | time0ut wrote:
           | Using claude code feels like pairing with another programmer.
           | Cursor feels like a polished extension of the IDE. They are
           | both good tools and easily worth $20/mo. I think Anthropic
           | has a 7 day free trial going on. Worth trying it out.
        
       | nlh wrote:
       | One fantastic tip I discovered (sorry I've forgotten who wrote it
       | but probably a fellow HNer):
       | 
       | If you're using an AI for the "architecture" / spec phase, play a
       | few of the models off each other.
       | 
       | I will start with a conversation in Cursor (with appropriate
       | context) and ask Gemini 2.5 Pro to ask clarifying questions and
       | then propose a solution, and once I've got something, switch the
       | model to O3 (or your other preferred thinking model of choice -
       | GPT-5 now?). Add the line "please review the previous
       | conversation and critique the design, ask clarifying questions,
       | and proposal alternatives if you think this is the wrong
       | direction."
       | 
       | Do that a few times back and forth and with your own brain input,
       | you should have a pretty robust conversation log and outline of a
       | good solution.
       | 
       | Export that whole conversation into an .md doc, and use THAT in
       | context with Claude Code to actually dive in and start writing
       | code.
       | 
       | You'll still need to review everything and there will still be
       | errors and bad decisions, but overall this has worked
       | surprisingly well and efficiently for me so far.
        
         | enobrev wrote:
         | I do something very similar for the planning phase, as well as
         | for the code-review after a task is complete. I like to switch
         | between opus in claude code and gemini cli, so I can work from
         | the same files rather than copying and pasting things.
         | 
         | One tip I picked up from a video recently to avoid sycophancy
         | was to take the resulting spec and instead of telling the
         | reviewing LLM "I wrote this spec", tell it "an engineer on my
         | team wrote this spec". When it doesn't think it's insulting
         | you, it tends to be a bit more critical.
        
           | jihadjihad wrote:
           | "The summer intern wrote this spec."
        
       | abroun_beholder wrote:
       | Nice post, I'll try a few of those in my own file. From my side,
       | one thing in the troubleshooting section that I think is missing
       | is telling the agent that it should collect some proof of what it
       | thinks is wrong before trying to proceed with a fix. I have burnt
       | through a large number of tokens in the past in situations where
       | Claude took a look at the dodgy code (that it had written) and
       | went 'aha! I know what the problem is here' before proceeding to
       | make things worse. Telling Claude to add in debug print
       | statements can be remarkably effective but I'm sure it can also
       | come up with other approaches.
        
         | enobrev wrote:
         | Nothing quite like "I see what the problem is", and then seeing
         | Claude start reading a bunch of files and strategizing the re-
         | architecture of a feature just resolve its own 3-line blunder.
         | 
         | If you happen catch it and you're quick to "esc" and just tell
         | it to find a simpler solution, it's surprisingly great at
         | reconsidering, resolving the issue simply, and picking up where
         | it left off before the blunder.
        
           | nightshift1 wrote:
           | yes, that is why even in full automated mode, it is better to
           | pay attention. Sometimes it even tries to git checkout the
           | file when it is stuck with some i indentation issues.
        
         | toxik wrote:
         | I just never run it in full auto, I look at its proposed
         | changes and more often than not ask it to do it another way.
         | Sometimes I'm just so disappointed that I just go code it up
         | myself.
        
       | libraryofbabel wrote:
       | I use Claude Code regularly and have been responsible for
       | introducing colleagues to it. The consensus here seems to be that
       | it's the best coding agent out there. But since it's the only
       | coding agent I've used, when colleagues ask _why_ it's better
       | than Cursor, Cline, GitHub Copilot, Gemini CLI, etc., I sometimes
       | struggle to articulate reasons.
       | 
       | Claude Code power users, what would you say makes it superior to
       | other agents?
        
         | aosaigh wrote:
         | I mentioned this is another comment, but for me one of the big
         | positives is nothing to do with the model, it's the UI of how
         | it presents itself.
         | 
         | I hated at first that it wasn't like Cursor, sitting in the
         | IDE. Then I realised I was using Cursor completely differently,
         | using it often for small tasks where it's only moderately
         | helpful (refactoring, adding small functions, autocompleting)
         | 
         | With Claude I have to stop, think and plan before engaging with
         | it, meaning it delivers much more impactful changes.
         | 
         | Put another way, it demands more from me meaning I treat it
         | with more respect and get more out of it
        
           | libraryofbabel wrote:
           | This is a good point, the CLI kind of forces you to engage
           | with the coding process _through the eyes of the agent_ ,
           | rather than just treating it as "advanced autocomplete" in
           | the IDE.
           | 
           | However, there are a lot of Claude Code clones out there now
           | that are basically the same (Gemini CLI, Codex, now Cursor
           | CLI etc.). Claude still seems to lead the pack, I think?
           | Perhaps it's some combination of better coding performance
           | due to the underlying LLM (usually Sonnet 4) being fine-tuned
           | on the agent tool calls, plus Claude is just a little more
           | mature in terms of configuration options etc.?
        
             | enobrev wrote:
             | I haven't tried codex or cursor-cli yet, but I have tried
             | to give gemini a few tasks and in my experience, compared
             | to claude code, it's not great.
             | 
             | Gemini's been very quick to dive in and start changing
             | things, even when I don't want it to. But those changes
             | almost always fall short of what I'm after. They don't run
             | or they leave failing tests, and when I ask it to fix the
             | tests or the underlying issue, it churns without success.
             | Claude is significantly slower and definitely not right all
             | the time, but it seems to do a better job of stepping
             | through a problem and resolving it well enough, while also
             | improving results when I interject.
        
         | CamouflagedKiwi wrote:
         | Not a power user, but most recently I tried it out against
         | Gemini and Claude produced something that compiled and almost
         | worked - it was off in some specifics that I could easily
         | tweak. The next thing I asked it (with slightly more detailed
         | prompting) it more or less just nailed.
         | 
         | Meanwhile Gemini got itself stuck in a loop of compile/fail/try
         | to fix/compile/fail again. Eventually it just gave up and said
         | "I'm not able to figure this out". It does seem to have a kind
         | of self-esteem problem in these scenarios, whereas Claude is
         | more bullish on itself (maybe not always a good thing).
         | 
         | Claude seems to be the best at getting something that actually
         | works. I do think Gemini will end up being tough competition,
         | if nothing else because of the price, but Google really need a
         | bit of a quality push on it. A free AI agent is worthless if it
         | can't solve anything for me.
        
         | paulhodge wrote:
         | Lots of signs point to a conclusion that the Opus and Sonnet
         | models are fundamentally better at coding, tool usage, and
         | general problem solving across long contexts. There is some
         | kind of secret sauce in the way they train the models. Dario
         | has mentioned in interviews that this strength is one of the
         | company's closely guarded secrets.
         | 
         | And I don't think we have a great eval benchmark that exactly
         | measures this capability yet. SWE Bench seems to be pretty
         | good, but there's already a lot of anecdotal comments that
         | Claude is still better at coding than GPT 5, despite having
         | similar scores on SWE Bench.
        
           | libraryofbabel wrote:
           | Yeah, agree that the benchmarks don't really seem to reflect
           | the community consensus. I wonder if part of it is the better
           | symbiosis between the agent (Claude Code) and the Opus and
           | Sonnet models it uses, which supposedly are fine-tuned on
           | Claude Code tool calls? But agree, there is probably some
           | additional secret sauce in the training, perhaps to do with
           | RL on multi-step problems...
        
       | monkeydust wrote:
       | Been playing around with Claude Code for a home project over the
       | last week.
       | 
       | I started with an idea but no spec. I got it to a happy place I
       | can deploy yesterday. Spent around $75 on tokens. It was starting
       | to feel expensive towards the end.
       | 
       | I did wonder if I had started with a clearer specification could
       | I have got there quicker and for less money.
       | 
       | The thing is though, looking back at the conversations I had with
       | it, the back and forth (vibe coding I guess) helped me refine
       | what I was actually after so in two minds if a proper tight
       | specification upfront would have been the best thing.
        
         | electroly wrote:
         | Switch from Opus to Sonnet. When people report high spending in
         | Claude Code it's always because they're using Opus. Opus is for
         | people on unlimited plans who aren't paying API rates.
        
           | JulesRosser wrote:
           | You could also define a subagent that uses Opus, for special
           | cases such as planning
        
       | maherbeg wrote:
       | I highly recommend having fairly succinct project level CLAUDE.md
       | files, and defer more things into sub-folders. Use the top level
       | as a map. Then during your planning of a feature, it can reach
       | into each folder as it sees fit to find useful context to build
       | out your phased implementation plan. I have it use thinking mode
       | to figure out the right set of context.
       | 
       | At the end of each phase, I ask claude to update my
       | implementation plan with new context for a new instance of claude
       | to pick it up. This way it propagates context forward, and then I
       | can clear the context window to start fresh on the next phase.
        
       | andrew_lastmile wrote:
       | Creating temporary artifacts of implementation plans seem to be
       | very useful for breaking down complex tasks and even more so, for
       | me to double check the logic and plans.
        
       | naiv wrote:
       | The update to Opus 4.1 really improved the quality.
       | 
       | I personally really like to use Claude Code together with Zen MCP
       | https://github.com/BeehiveInnovations/zen-mcp-server to analyse
       | existing and review fresh code with additional eyes from Gpt5 and
       | Gemini.
        
       | JulesRosser wrote:
       | For anyone like me who was struggling to manage work and personal
       | Claude subscriptions, you can just use an alias like this:
       | 
       | alias claude-personal="CLAUDE_CONFIG_DIR=~/.claude-personal
       | claude"
       | 
       | https://julesrosser.com/blog/Multiple-Claude-accounts.html
        
       | michaelteter wrote:
       | There's an interesting transition point that we must keep in mind
       | when using these tools.
       | 
       | For research, investigation, and proof of concept, it is good to
       | be flexible and a bit imprecise.
       | 
       | But once a path seems clear, writing a single detailed document
       | (even with "help") is valuable before working with a separate AI
       | assistant.
       | 
       | The challenge is recognizing that transition point. It's very
       | easy to just meander from zero to sort-of-product without making
       | this separation.
        
       | renewiltord wrote:
       | Claude code is fantastic. For me, the insight was that you have
       | to give it the ability to close the loop. If it writes code it
       | will try to reason about the code. "The button has the right CSS
       | and so should be visible".
       | 
       | But everything is better if it can close the loop. So I instead
       | instruct it to always use the puppeteer tool to launch the app
       | and use some test credentials and see if the functionality works.
       | 
       | That's for a web app but you can see how you can do this for
       | other things. Either unit tests, integration tests, or the
       | appropriate MCP.
       | 
       | It needs to see what it's done and observe the resulting world.
       | Not just attempt to reason to it.
       | 
       | Claude also leans towards what it's good at. Repetition costs it
       | nothing so it doesn't mind implementing the same 5 times. One
       | thing it did when I started is implement a sidebar on every page
       | rather than using a component. So you need to provide some
       | pressure against that with your prompts or at least force it to
       | refactor at the end.
        
       | gabrielpoca118 wrote:
       | I don't write any structured specs and I still get a lot of value
       | out of it. I basically use it in incremental steps where I'm
       | telling it what I want at a much lower level. Am always watching
       | what it is doing and stopping it to correct the action. At least
       | for me this approach has worked much better than asking it for
       | bigger things.
        
       | kleyd wrote:
       | Does anyone else find themselves starting projects that wouldn't
       | otherwise be worth the time investment, while avoiding Claude
       | Code for the tasks that actually have high priority?
       | 
       | Who has had success using Claude Code on features in older,
       | bigger, messier projects?
        
       | 1zael wrote:
       | I've found my workflow is much faster now after implementing a
       | dedicated Claude agent for test-driven development. This TDD
       | agent reviews code and generates comprehensive tests for my
       | primary agent before commits enter the CI/CD pipeline. I have
       | multiple terminals open running various Claude agents.
        
       ___________________________________________________________________
       (page generated 2025-08-08 23:00 UTC)