Writing and updating CLAUDE.md or AGENTS.md feels like pointless to me. Humans are the real audience for documentation. The code changes too fast, and LLMs are stateless anyway.
What’s been working is just letting the LLM explore the relevant part of the code to acquire the context, defining the problem or feature, and asking for a couple of ways to tackle it. All in a one short prompt.
That usually gets me solid options to pick and build it out.
And always do, one session for one problem.
This is my lazy approach to getting useful help from an LLM.
Quirks are pretty much unavoidable. I tend to get better results using Codex. It sticks to established patterns. Slow, but more deliberate. Claude focuses more on speed.
I use .md to tell the model about my development workflow. Along the lines of "here's how you lint", "do this to re-generate the API", "this is how you run unit tests", "The sister repositories are cloned here and this is what they are for".
One may argue that these should go in a README.md, but these markdowns are meant to be more streamlined for context, and it's not appropriate to put a one-liner in the imperative tone to fix model behavior in a top-level file like the README.md
I’m definitely interested in reducing token usage techniques. But with one session one problem I’ve never hit a context limit yet, especially when the problem is small and clearly defined using divide-and-conquer. Also, agentic models are improving at tool use and should require fewer tokens. I’ll take as many iterations as needed to ensure the code is correct.
A well-documented codebase lets both developers and agentic models locate relevant code easily. If you treat the model like a teammate, extra docs for LLMs are unnecessary. IMHO. In frontend work, code moves quickly.
Seeing "real" is a warning flag here that either-or thinking is in play.
Putting aside hopes and norms, we live in a world now where multiple kinds of agents (human and non-human) are contributing to codebases. They do not contribute equally; they work according to different mechanisms, with different strengths and weaknesses, with different economic and cultural costs.
Recall a lesson from Ralph Waldo Emerson: "a foolish consistency is the hobgoblin of little minds" [1]. Don't cling to the past; pay attention to the now, and do what works. Another way of seeing it: don't force a false equivalence between things that warrant different treatment.
If you find yourself thinking thoughts that do more harm than good (e.g. muddle rather than clarify), attempt to reframe them to better make sense of reality (which has texture and complexity).
Here's my reframing: "Documentation serves different purposes to different agents across different contexts. So plan and execute accordingly."
Let cc/codex do research by themselves.
I usually ask claude to scan codebase about specific part for context, describe my issue or feature then ask it to suggest solutions.
Example :
Study <subject>, I want to <fix/add feature>. What do you suggest ?
From there, I have 2-3 different strategies options. Pick one, refine then implement.
Yeah I get that, I think I’ve just found myself too lazy to wait / annoyed about hallucinations when building specific things in growing codebases. I rather instead of spawning an entire sub agent in cc to review if a file exists just ask it to use this tool. I’ve found it useful
Appreciate the feedback, I do agree we're going to change that. For now if you want to try it and see the results there's nothing beyond creating an account with your email (no payment etc)
Thanks! So I tried again. Here’s what I noticed
1. Date time is not local to the country I’d like to travel
2. Lack information about transport, routes, weather season, hotels, foods or restaurants, price… why not start with a country or region and be very good at it? Trip planning should be predictable
3. I want to see the places on map. Maybe?
4. Responsive but not fully on mobile
Overall this a hard problem you are trying to solve. I don’t even know where to start if I were you. Good luck!
This is great feedback! Much appreciated!
1. Yep, shipping a fix ASAP.
2. That’s a good point. We’ve been trying to balance getting this out to users to get feedback and adding everything in we’d like, have some work in progress on some of these and hope to get out some good updates soon.
3. We show them on desktop but I think not showing the places on the map is a mobile responsiveness bug. Please correct me if I’m wrong!
4. Yep! We are working to have better mobile support soon!
I had a similar idea and ended up using either Airtable or Sheets. If you're creating a portfolio, I suggest including more screenshots of your application and storing the data using local storage. For me, the problem was not real - all I had to do was label the status of my applications as either applied, rejected, or pending for response.
