Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Maximizing the value of your Claude Code sessions

claude.com

Post reply on HN
Print view View original

181–190 of 206 posts

Re: Maximizing the value of your Claude Code sessions

#181

Post by subscribed »

3371 wrote: post #113
superasn wrote: post #69

Recently I came across the /handoff skill, which I've been using a lot. I find it much better than /compact. Basically: - /handoff file creates a short document with the important context from your current session and maybe next steps as checklist. - You can then start a fresh session with /continue file - You can also hand the work from Claude to ChatGPT, or the other way around. Very useful at time of session limit…

> Plus your handoff files becomes a useful piece of project memory that you can reference later. I've been doing this since I started agentic development, and have a whole framework based on this; Simply put I define workflow s that output templated files for everytype of tasks that happens in development. It's a powerful pattern I'd recommend everyone.

Oh, so there's whole _skill_ for that!

I now feel a bit silly but I reinvented the wheel during my last lil project and indeed found it very powerful. A variant of it is the "implementation (handover) prompt" when I conclude the planning session with plans and design documents, updated handoff, clean tree and a file for a new Opus implementing orchestrator (unusually do a single, highly specific implementer and a single, highly specific tester).

After implementation and task-level tests I end up with a long and very detailed implementation progress ledger and a summary findings from the orchestrator.

Then in the new session I do the whole branch tests.

Works really well, uses much less tokens than any other approach with more of Opus and very little repetitions/corrections.

Re: Maximizing the value of your Claude Code sessions

#182

Post by subscribed »

CBLT wrote: post #88
ls612 wrote: post #72

Earlier quoted context omitted.

I have been doing this a lot even without a skill, having Fable write a planning document, then spawning an Opus subagent with instructions to strictly follow the plan and report any deviance at the end. It also helps that then the plan is always saved in an md file so any future agent can look at it and see what happened.

Interestingly, this was tackled in this blog post[0] a month ago. They claim that plan files aren't token-efficient, because after reading the plan the workhorse model then reads all the relevant files anyways. [0] https://news.ycombinator.com/item?id=48916512

My plan and implementation files are task specific (so specific workhorse reads only its own slice), and the workhorse itself is spawned from an orchestrator with a very specific small prompt.

I managed even the orchestrator to NOT read the plan whole, at once, but in sections.

The most useful thing is the task ledger the task agent leaves behind, which alongside its structured status message makes a very resilient handoff between all stages.

Re: Maximizing the value of your Claude Code sessions

#183

Post by cityofdelusion »

subscribed wrote: post #181
3371 wrote: post #113

Earlier quoted context omitted.

> Plus your handoff files becomes a useful piece of project memory that you can reference later. I've been doing this since I started agentic development, and have a whole framework based on this; Simply put I define workflow s that output templated files for everytype of tasks that happens in development. It's a powerful pattern I'd recommend everyone.

Oh, so there's whole _skill_ for that! I now feel a bit silly but I reinvented the wheel during my last lil project and indeed found it very powerful. A variant of it is the "implementation (handover) prompt" when I conclude the planning session with plans and design documents, updated handoff, clean tree and a file for a new Opus implementing orchestrator (unusually do a single, highly specific implementer and a sin…

This is where I landed too. Basic skill for a Jira-like task board and another for keeping an orchestration ledger. Let’s me arbitrarily clear context without losing big picture knowledge.

Re: Maximizing the value of your Claude Code sessions

#184

Post by tarekabi »

superasn wrote: post #69

Recently I came across the /handoff skill, which I've been using a lot. I find it much better than /compact. Basically: - /handoff file creates a short document with the important context from your current session and maybe next steps as checklist. - You can then start a fresh session with /continue file - You can also hand the work from Claude to ChatGPT, or the other way around. Very useful at time of session limit…

[flagged]

Re: Maximizing the value of your Claude Code sessions

#185

Post by tarekabi »

alekstret wrote: post #142

Here is my working flow, confirmed by more than 400 pr merged over the last 4 months. More than half of them were following my current strategy: 1. My agent writes code. 2. Then it creates tests and verifies that all of them actually work, not just pass. To do this, my agent writes the test, then it deletes the code it covers, reruns the test, confirms it goes red, and finally puts the code back. 3. I receive the rea…

[flagged]

Re: Maximizing the value of your Claude Code sessions

#186

Post by hardbass »

HappMacDonald wrote: post #171
StilesCrisis wrote: post #161

Earlier quoted context omitted.

Three years ago, a computer that can write working C++ on the first try would have been considered to be a miracle. It's amazing how quickly the goalposts move.

I mean `printf("printf(\"Hello World!\\n\")");`, so...

Fail: Bad/legacy C library used. An LLM won't have generated C code if asked for C++.

Re: Maximizing the value of your Claude Code sessions

#187

Post by mhitza »

dist-epoch wrote: post #148
mhitza wrote: post #144

Earlier quoted context omitted.

I'm a pleb developer, don't have the smarts, the prestige or the salary of those working at BigTech. When AI firms ate more than half of global VC private investment in 2025 https://www.oecd.org/en/about/news/announcements/2026/02/ai-... I would expect better results than what we have today. The most well paid people in the industry brought us here. And "here" is very much as fuzzy as last year with better harnessing…

> I would expect better results than what we have today. Not sure what your baseline was, if you said 10 years ago "in 2026 you'll be able to describe an app into the microphone, and the computer will write by itself in one day 50k lines of code to implement it, in a language and tech stack of your choosing, costing $200, and it will sort-of-work, and it will be at least as good as a junior-level programmer writing i…

Yes, it is very impressive what they can do by recycling copyrighted material. They are more impressive for me when they are not used in agentic contexts. Though that doesn't sell hype anymore to inflate valuation.

For more than a year now I was renting a limited GPU server for ~300$/month to learn, experiment, research and build internal tooling around open weight models. Thinking they are tools with potential and buying the exaggerated marketing are different things.

My history of comments on HN lands often on both providing what I believe to be my insights working with LLMs and calling out exaggerations, stupid terms of service, and the other mishaps in the field. You are free to browse them if you'd like to see my broader opinion.

Re: Maximizing the value of your Claude Code sessions

#188

Post by brachkow »

ramraj07 wrote: post #169
brachkow wrote: post #165

Considering that I'm mostly unable to reach the limit of my X5 subscription and we have 1M context, it is a guide to maximize Anthropic PnL pre-IPO

This very much applies to most enterprises. These unlimited subscriptions are only available to individuals and teams less than 150 folks..

API is highly overpriced and keeps Anthropic profitable or at least close to break even, as was reported recently. Why would you think they will be interested in advising enterprises in cutting their bills pre-IPO?

Re: Maximizing the value of your Claude Code sessions

#189

Post by janalsncm »

foota wrote: post #75
janalsncm wrote: post #16

Earlier quoted context omitted.

I’m guessing that there’s a system prompt at the top telling the model about its reasoning budget. So when you switch reasoning effort it busts the cache.

Hmmm... Why wouldn't this be handled like other end of prompt things like the current mode?

Prompt caching only works based on the prefix. Let’s call your output Y and the low reasoning prompt A and a medium reasoning prompt B.

Previously you were at A+Y. Switching to medium reasoning makes it B+Y. There’s no prefix which can be cached, so the entire B+Y needs to be reprocessed.

Re: Maximizing the value of your Claude Code sessions

#190

Post by janalsncm »

cellularmitosis wrote: post #133
janalsncm wrote: post #16

Earlier quoted context omitted.

I’m guessing that there’s a system prompt at the top telling the model about its reasoning budget. So when you switch reasoning effort it busts the cache.

Maybe switching effort routes you to a different rack of gpu’s which don’t have the cache

The KV cache is probably offloaded to RAM after a generation is complete. Then it is pulled back into any rack in the data center that has the model you’re using.
Post reply on HN