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

Universal Claude.md – cut Claude output tokens

github.com

Post reply on HN
Print view View original

121–130 of 192 posts

Re: Universal Claude.md – cut Claude output tokens

#121

Post by joquarky »

xianshou wrote: post #18

From the file: "Answer is always line 1. Reasoning comes after, never before." LLMs are autoregressive (filling in the completion of what came before), so you'd better have thinking mode on or the "reasoning" is pure confirmation bias seeded by the answer that gets locked in via the first output tokens.

For the more important sessions, I like to have it revise the plan with a generic prompt (e.g. "perform a sanity check") just so that it can take another pass on the beginning portion of the plan with the benefit of additional context that it had reasoned out by the end of the first draft.

Re: Universal Claude.md – cut Claude output tokens

#122

Post by addandsubtract »

sillysaurusx wrote: post #12
david_allison wrote: post #11

Earlier quoted context omitted.

Is this available online? I'd love documentation of my prompts.

I’ll post it here, one minute. Ok, here you go: https://gist.github.com/shawwn/56d9f2e3f8f662825c977e6e5d0bf... Installation steps: - In your project, download https://gist.github.com/shawwn/56d9f2e3f8f662825c977e6e5d0bf... into .claude/commands/handoff.md - In your project's CLAUDE.md file, put "Read `docs/agents/handoff/*.md` for context." Usage: - Whenever you've finished a feature, done a coherent "thing", or oth…

Thanks! The last link is broken, though, or maybe you didn't mean to include it? Also, if you've never actually resumed a session, do you use these docs at some other time? Do you reference them when working on a related feature, or just keep them for keepsake to track what you've done and why?

Re: Universal Claude.md – cut Claude output tokens

#123

Post by lilOnion »

While LLM are extremely cool, I can't see how this gets on the front page? Anyone who interacted with llms for at least a hour, could've figured out to say somethin like "be less verbose" and it would? There are so many cool projects and adeas and a .md file gets the spotlight.

Re: Universal Claude.md – cut Claude output tokens

#124

Post by jstanley »

dataviz1000 wrote: post #26
sillysaurusx wrote: post #7

Earlier quoted context omitted.

I wrote a skill called /handoff. Whenever a session is nearing a compaction limit or has served its usefulness, it generates and commits a markdown file explaining everything it did or talked about. It’s called /handoff because you do it before a compaction. (“Isn’t that what compaction is for?” Yes, but those go away. This is like a permanent record of compacted sessions.) I don’t know if it helps maintain long term…

Did you call it '/handoff' or did Claude name it that? The reason I'm asking is because I noticed a pattern with Claude subtly influencing me. For example, the first time I heard the the word 'gate' was from Claude and 1 week later I hear it everywhere including on Hacker News. I didn't use the word 'handoff' but Claude creates handoff files also [0]. I was thinking about this all day. Because Claude didn't just use…

FWIW I have worked with people using the word "gate" for years.

For example, "let's gate the new logic behind a feature flag".

Re: Universal Claude.md – cut Claude output tokens

#125

Post by _the_inflator »

I see no point in this project. There ain’t any examples for the usage the author states his project is made for.

389 tokens saved? Ok. Since I pay per million tokens, what is the ratio here? Is there are any downside associated with output deletion?

Is Claude really using this behavior to make user bleed? I don’t think so.

PS: the author seems like a beginner. Agents feedback is always helpful so far and it also is part of inter agent communication. The author seems to lack experience.

As a lead I would not allow this to be included until proven otherwise: A/B testing.

Re: Universal Claude.md – cut Claude output tokens

#127

Post by joquarky »

miguel_martin wrote: post #25

Is there a "universal AGENTS.md" for minimal code & documentation outputs? I find all coding agents to be verbose, even with explicit instructions to reduce verbosity.

There might be a reason it works that way.

https://en.wiktionary.org/wiki/Chesterton%27s_fence

Re: Universal Claude.md – cut Claude output tokens

#128

Post by joquarky »

Razengan wrote: post #114
sunaookami wrote: post #112

Earlier quoted context omitted.

It needs to be called CLAUDE.md for Claude Code

Oh my god, why Why do they have to have that "I'm special" syndrome and do everything weirdly

You can symlink it or put `@AGENTS.md` as the only line in your CLAUDE.md

Re: Universal Claude.md – cut Claude output tokens

#129

Post by wongarsu »

hatmanstack wrote: post #20
btown wrote: post #4

It seems the benchmarks here are heavily biased towards single-shot explanatory tasks, not agentic loops where code is generated: https://github.com/drona23/claude-token-efficient/blob/main/... And I think this raises a really important question. When you're deep into a project that's iterating on a live codebase, does Claude's default verbosity, where it's allowed to expound on why it's doing what it's doing when it…

Seems crazy to me people aren't already including rules to prevent useless language in their system/project lvl CLAUDE.md. As far as redundancy...it's quite useful according to recent research. Pulled from Gemini 3.1 "two main paradigms: generating redundant reasoning paths (self-consistency) and aggregating outputs from redundant models (ensembling)." Both have fresh papers written about their benefits.

There was also that one paper that had very noticeable benchmark improvements in non-thinking models by just writing the prompt twice. The same paper remarked how thinking models often repeat the relevant parts of the prompt, achieving the same effect.

Claude is already pretty light on flourishes in its answers, at least compared to most other SotA models. And for everything else it's not at all obvious to me which parts are useless. And benchmarking it is hard (as evidenced by this thread). I'd rather spend my time on something else

Re: Universal Claude.md – cut Claude output tokens

#130

Post by swimmingbrain »

levocardia wrote: post #68
joshstrange wrote: post #16

As with all of these cure-alls, I'm wary. Mostly I'm wary because I anticipate the developer will lose interest in very little time and also because it will just get subsumed into CC at some point if it actually works. It might take longer but changing my workflow every few days for the new thing that's going to reduce MCP usage, replace it, compress it, etc is way too disruptive. I'm generally happy with the base Cl…

I also share something of an "efficient market hypothesis" with regards to Claude Code. Given that Anthropic is basically a hothouse of geniuses recursively dogfooding their own product, the market pressure to make the vanilla setup be the one that performs best at writing code is incredibly high. I just treat CLAUDE.md like my first draft memo to a very smart remote colleague, let Claude do all its various quirks, a…

The "efficient market" framing assumes Anthropic wants to minimize output, but they don't. They charge per token, so the defaults being verbose isn't a bug they haven't gotten around to fixing.

That said, most of this repo is solving the wrong problem. "Answer before reasoning" actively hurts quality, and the benchmark is basically meaningless. But the anti-sycophancy rules should just be default. "Great Question!" has never really helped anyone debug anything.

Post reply on HN