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

Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

systima.ai

Post reply on HN
Print view View original

301–310 of 433 posts

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#301

Post by lemagedurage »

nvch wrote: post #201
mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

I had learnt that trick, so now I explicitly disallow Fable subagents. Yesterday, I wanted to review a complex piece after a large refactoring, and requested a review plan beforehand. The first step was 8 agents + one more to verify the findings (all Fable). Looks good, approved. The verification step turned into an attempt to throw a party with 41 Fable verifiers. It will find a way.

"LGTM"

That'll be $50 — please.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#302

Post by joshcartme »

ValentineC wrote: post #100
mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

> What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. Probably because the general purpose subagents inherit the parent model. I tell Claude explicitly to use Explore subagents, which use Haiku only, now.

They changed it with the release on July 1 Explore now inherits the model, it isn't always haiku.

https://code.claude.com/docs/en/changelog#2-1-198

> The built-in Explore agent now inherits the main session’s model (capped at opus) instead of running on haiku

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#304

Post by lemagedurage »

mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

True. For Claude Code, I disabled explore subagents globally by adding this to ~/.claude/settings.json:

  "permissions": {
    "deny": [
      "Task(Explore)"
    ]
  }

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#305

Post by Computer0 »

mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

Subagents are quite inefficient and the lossy context transfer between them does lead to more cost and more waiting. However I have found it to produce more reliable output, whether that is worth it for a given task has been a consideration.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#306

Post by searealist »

rendx wrote: post #120
onlyrealcuzzo wrote: post #107

Earlier quoted context omitted.

This is why I happily use Codex. I run it basically 24/7 on a ~500k line repo, and only rarely run out of quota before the end of the week. My experience with Claude Code was very good until about 2.5 months ago, and then it suddenly turned unbelievably terrible for me. I have not and will hopefully never look back. I still have PTSD from how ungodly terrible it was that last week of using it.

> I still have PTSD from how ungodly terrible it was Please, for the sake of everyone suffering from actual PTSD: Don't. It's hard enough already for victims to communicate what difficulties they are facing without people watering down terminology like that.

Please don't act as the hyperbole police. People exaggerate all the time (I'm starving, etc). It's normal, and you are being a jerk to call them out.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#307

Post by hgoel »

mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

I like to use subagents a lot, but I find them to be most useful when explicitly specified. E.g. "assign these tasks to 2 Sonnet, 2 Opus and 1 Fable subagent". Helps keep allocation consumption under control.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#308

Post by simondotau »

int_19h wrote: post #237
Cider9986 wrote: post #105

Grok 4.5 is really fast, has more usage at $10/month than $20/month Claude pro, and Opus-level. Claude pro feels like a demo. Claude is much better in OpenCode then in Claude Code, OpenCode is just better than Claude Code. Claude Code feels like a complete mess to use comparatively.

Elon saying that it is "Opus level" doesn't actually make it so.

True of anything anyone says about anything, including int_19h and simondotau.

I'm quite impressed with Grok 4.5 because its speed and single-task effectiveness feels better than anything else for a human-in-the-loop workflow. (For the stuff I do, I'm not interested in having AI race ahead of what I can oversee.)

All models do things in a way I personally disagree with at least some of the time. The "dumber" models sometimes fail to recognise how to fit a solution into existing code. The "smarter" models sometimes get too clever and over-engineer their solutions. Cleverness is occasionally interesting, but is just as likely to trigger a distracting rabbit hole where I spend time analysing whether something unexpected was a legit insight, or mere opinion.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#310

Post by prince005 »

I have been using claude code for a big project for a while and I feel like I have optimized my workflow now.

Brainstorm - Gemini/Antigravity

Plan - Gemini/Antigravity

Detailed Plan - Sonnet

Coding - Fable

Do not use any subagents, especially the default ones. They are dumb. The top level agent works well enough

Post reply on HN