How to code Claude Code in 200 lines of code • Hacker News Board

Re: How to code Claude Code in 200 lines of code

#131

Post by rrvsh » Thu, Jan 08, 2026, 11:44 PM UTC

lmeyerov wrote: post #63

Something I would add is planning. A big "aha" for effective use of these tools is realizing they run on dynamic TODO lists. Ex: Plan mode is basically bootstrapping how that TODO list gets seeded and how todos ground themselves when they get reached, and user interactions are how you realign the todo lists. The todolist is subtle but was a big shift in coding tools, and many seem to be surprised when we discuss it -…

I've had a LOT of success keeping a "working memory" file for CLI agents. Currently testing out Codex now, and what I'll do is spend ~10mins hashing out the spec and splitting it into a list of changes, then telling the agent to save those changes to a file and keep that file updated as it works through them. The crucial part here is to tell it to review the plan and modify it if needed after every change. This keeps the LLM doing what it does best (short term goals with limited context) while removing the need to constantly prompt it. Essentially I feel like it's an alternative to having subagents for the same or a similar result

Re: How to code Claude Code in 200 lines of code

#132

Post by alansaber » Thu, Jan 08, 2026, 11:53 PM UTC

libraryofbabel wrote: post #35

It's a great point and everyone should know it: the core of a coding agent is really simple, it's a loop with tool calling. Having said that, I think if you're going to write an article like this and call it "The Emperor Has No Clothes: How to Code Claude Code in 200 Lines of Code", you should at least include a reference to Thorsten Ball's excellent article from wayyy back in April 2025 entitled "How to Build an Age…

Ah I just assumed it was the same article reposted

Re: How to code Claude Code in 200 lines of code

#133

Post by andai » Fri, Jan 09, 2026, 12:00 AM UTC

    from ddgs import DDGS

    def web_search(query: str, max_results: int = 8) -> list[dict]:
        return DDGS().text(query, max_results=max_results)

Re: How to code Claude Code in 200 lines of code

#134

Post by bjt12345 » Fri, Jan 09, 2026, 12:07 AM UTC

OsrsNeedsf2P wrote: post #113

Yea.. our startup greatly overestimated how hard it is to make a good agent loop. Handling exit conditions, command timeouts, context management, UI, etc is surprisingly hard to do seamlessly.

Do you mean they underestimated how hard it is?

Re: How to code Claude Code in 200 lines of code

#135

Post by rvz » Fri, Jan 09, 2026, 12:11 AM UTC

tomhow wrote: post #96

dana321 wrote: post #43

[flagged]

Please don't fulminate on HN. The guidelines make it clear we're trying for something better here. https://news.ycombinator.com/newsguidelines.html

Agreed. Aside from the guideline violation, he has a tiny point.

Python is quite garbage for this sort of thing.

Re: How to code Claude Code in 200 lines of code

#136

Post by shnpln » Fri, Jan 09, 2026, 12:11 AM UTC

renjimen wrote: post #125

shnpln wrote: post #119

Earlier quoted context omitted.

Oh yes, I commonly add something like "Use a very granular todo list for this task" at the end of my prompts. And sometimes I will say something like "as your last todo, go over everything you just did again and use a linter or other tools to verify your work is high quality"

If you have pre-commit hooks it should do this last bit automatically, and use your project settings

Yes, I do. But it does not always use them when I change contexts. I just get in the habit of saying it. Belt and suspenders approach.

Re: How to code Claude Code in 200 lines of code

#137

Post by schmuhblaster » Fri, Jan 09, 2026, 12:20 AM UTC

As an experiment over the holidays I had Opus create a coding agent in a Prolog DSL (more than 200 lines though) [0] and I was surprised how well the agent worked out of the box. So I guess that the latest one or two generations of models have reached a stage where the agent harness around the model seems to be less important than before.

[0] https://news.ycombinator.com/item?id=46527722

Re: How to code Claude Code in 200 lines of code

#138

Post by shnpln » Fri, Jan 09, 2026, 12:21 AM UTC

hadlock wrote: post #124

shnpln wrote: post #119

Earlier quoted context omitted.

Oh yes, I commonly add something like "Use a very granular todo list for this task" at the end of my prompts. And sometimes I will say something like "as your last todo, go over everything you just did again and use a linter or other tools to verify your work is high quality"

Right now I start chatting with a separate LLM about the issue, the best structure for maintainability and then best libraries for the job, edge and corner cases, how to handle those, and then have it spit out a prompt and a checklist. If it has a UI I'll draw something in paint and refine it before having the LLM describe it in detail and primary workflow etc. and tell it to format it for an agent to use. That will…

Yeah, this is a good idea. I will have a Claude chat session and a Claude Code session open side by side too.

Like a manual sub agents approach. I try not to pollute the Claude code session context with meanderings to much. Do that in the chat and bring the condensed ideas over.

Re: How to code Claude Code in 200 lines of code

#139

Post by fastball » Fri, Jan 09, 2026, 12:32 AM UTC

lmeyerov wrote: post #63

Something I would add is planning. A big "aha" for effective use of these tools is realizing they run on dynamic TODO lists. Ex: Plan mode is basically bootstrapping how that TODO list gets seeded and how todos ground themselves when they get reached, and user interactions are how you realign the todo lists. The todolist is subtle but was a big shift in coding tools, and many seem to be surprised when we discuss it -…

Planning mode actually creates whole markdown files, then wipes the context that was required to create that plan before starting work. Then it holds the plan at the system prompt level to ensure it remains top of mind (and survives unaltered during context compaction).

Re: How to code Claude Code in 200 lines of code

#140

Post by tomhow » Fri, Jan 09, 2026, 12:35 AM UTC

rvz wrote: post #135

tomhow wrote: post #96

Earlier quoted context omitted.

Please don't fulminate on HN. The guidelines make it clear we're trying for something better here. https://news.ycombinator.com/newsguidelines.html

Agreed. Aside from the guideline violation, he has a tiny point. Python is quite garbage for this sort of thing.

Sure, and the opposite of shallow dismissal isn't shallow praise, it's substantive explanation of the reasoning behind one's assessment.