Rendered at 22:49:42 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
hungryhobbit 2 days ago [-]
I just used Claude to write a plug-in which changed the bottom of the CLI to say:
( ) Usage: 34% (resets in 2h 47m) Context: 56% [Opus 4.6]
auto mode on (shift+tab to cycle)
That way if my usage starts shooting up, it's very easy to notice (and the color of "( )", which is a circle that I couldn't paste here, changes when it gets high, ensuring I don't miss it).
I coupled that with a hook that watches for usage spiking (basically when I've been talking too long or did something to add a ton of context, so suddenly every turn sends a ton of context back, using up a ton of usage).
Between the two I haven't hit usage caps in weeks.
Tadpole9181 2 days ago [-]
This is actually a built-in Claude Code feature: `/statusline` will ask how you want it to look and set it up for you.
marak830 2 days ago [-]
A) Oh nice! that's cool
B) Warning everyone, it slowly eats tokens - If you're like me and on the pro plan, perhaps not a good idea to have its (albeit slow) drain on the tokens.
chorsestudios 2 days ago [-]
I didn't think statusline ate tokens, is this true?
Tadpole9181 16 hours ago [-]
No, when you run it Claude just writes a bash script used to generate the status line. Not sure what they're talking about.
marak830 15 hours ago [-]
I set it up and saw the token notifier down the bottom slowly ticking up. I'll try again and report back, perhaps I misread something? I was surprised something like thst (which I assumed was an API call) was trickling token usage.
brookst 9 hours ago [-]
When was it ticking up? The status line only updates after each turn. If you submitted a turn, tokens were used. The status line itself is a bash script, you can go look at it.
ericd 2 days ago [-]
I have something like this persistent in my waybar, with session, weekly, and fable usage, with little color coded percentage bars for each. Super helpful, highly recommend it.
Great idea on the hook alert.
I feel like the advent of LLMs has made a super customizable OS like Linux so, so much better than the closed source alternatives, and so much better than they were before.
e40 1 days ago [-]
Wanna share?
DarmokTanagra 2 days ago [-]
I didn't know it was still possible to develop software after your ai quota runs out.
francisofascii 2 days ago [-]
You wait until the month resets.
arealaccount 2 days ago [-]
You’re joking but from the readme
> Is it safe to start a big refactor now, or should I wait for my window to clear?
dakolli 2 days ago [-]
Why not juat write the code. Its not that much faster to produce good code with AI. I spend nearly identical amoubts of time reviewing AI code as it would take to write. Im honestly not convinced there is all that much of a productivity boost, maybe 20% faster.
francisofascii 2 days ago [-]
I was mostly joking, but to answer your question, the productivity boost entirely depends on your concern for code quality. Sometimes is it faster to just write the code than to try to explain in the prompt what to do. But if you don't care or don't need to understand what it is creating, you can get a ton of functionality fast.
weego 2 days ago [-]
Is this the new 10x engineer hammock meme? No one is vesting anymore they just burned their quarterly token quote in 10 days.
aaronbrethorst 2 days ago [-]
Darmok and Jalad, after their quota ran out.
intothemild 2 days ago [-]
Shaka, when they discovered open models!
Xorakios 2 days ago [-]
omg. so awesome
rkagerer 2 days ago [-]
Shaka, when the bubble burst!
thadt 2 days ago [-]
Zinda, his face black, his eyes red…
cyanydeez 2 days ago [-]
Local AI has no quote, except cold hard WATTs
thot_experiment 2 days ago [-]
I genuinely don't even understand how people run out of tokens with the basic subscription. I had Claude write an entire app that has completely replaced Adobe Illustrator for my specific usecases (mostly inking sketches, and embellishing generated SVGs). It does everything exactly the way I want and has much better ergonomics (blender hotkeys ftw) and the whole thing took me like 700k tokens over the course of a couple days.
Do people just let Opus ultra extra max thinking run amok on their whole codebase with a single context? I don't even think I could even design sensible features faster, I'm the limiting factor here, the robot pretty much oneshots everything I ask for.
2 days ago [-]
PhilippGille 1 days ago [-]
Token usage is generally lower in greenfield projects.
thot_experiment 1 days ago [-]
Sure I get that, but the part where the robot has to read the repo and figure stuff out can be done by a weak model for near-free with no thinking. The delta isn't that big.
ryandrake 2 days ago [-]
I made an "amateur hour" error with Codex. Given Anthropic's recent reliability problems I thought I'd take a little time to try Codex with their $20/mo plan. So I downloaded it and gave it a whirl, not realizing that the default model was gpt-5.6-sol. Well after just an hour or two, I blew through my entire week's quota. Whoops! It would be cool if these harnesses could all graphically display your quota usage on the screen at all times.
jdthedisciple 2 days ago [-]
You can enable showing the quota usage (and much more) in codex via /statusline
sva_ 2 days ago [-]
In 95% of cases it is because you had a large context for which the cache expired.
bearjaws 2 days ago [-]
The amount of people I see running around at 800k context and wondering why they are burning through tokens is always surprising.
brookst 9 hours ago [-]
Yep, even with cache hits that like submitting uncached 80k-token prompts over and over.
My Claude.md + framework stuff has it tell me when it recommends /clear before the next prompt (and write itself handoff notes) and I rarely see >100k context size even on large work.
enraged_camel 2 days ago [-]
Yeah. I like the way Claude Design handles this: if you come back to a chat after the cache expires, the chat UI shows a message like "start a new chat to save 300k tokens" or whatever. It's pretty nice if you're working in multiple design sessions and are quota-constrained.
Surprised they haven't brought the same UX to CC.
ElFitz 2 days ago [-]
I have that in CC when I resume a session.
Suggests either starting from a summary, a new conversation, or keep going.
nonameiguess 2 days ago [-]
23 em-dashes in the span of a single README. I gotta hand it to Anthropic. They seriously managed to find a completely legal way to sell crack to crack addicts using other crack addicts as their unpaid sales force.
Pretty cool tool! Congrats!
Not sure if I'm missing something but this tells you where your tokens went, breakdown per day/tool.
So the "why" is still a question left for the user to answer. Can be something like "Because I was missing a good CLAUDE.md file so it had to explore the whole repo before doing any work" or anything else. Just my take.
tare is a Python project. Why distribute it with npm rather than PyPI? Weird
jasonjmcghee 2 days ago [-]
I care more about your experience. I'd read the blog post of the story behind this.
underlines 2 days ago [-]
You can't ask Claude if your quota ran out. You have to wait for the reset...
chews 2 days ago [-]
for claude, it's response headers contain available usage, you can get it there. My deepseek harness plugin auto stops asking things when I am at 80% to allow inflight prompts to finish.
LuD1161 2 days ago [-]
I just checked the repo. Nice work
A suggestion:
1. Adding which repo/project was where my most tokens were consumed. I checked the image in the repo README, didn't see that graph.
Zak 2 days ago [-]
The only time I've ever managed to burn through a quota that fast (on the cheap plan) was with an open-ended request to check a codebase for any defects or deficiencies. It dispatched five Fable subagents.
skeledrew 2 days ago [-]
I've been recording every statusline output for months now so I can easily get answers to questions like this whenever I wish.
defied 2 days ago [-]
I’ve been using headroom to save on token usage and it’s pretty effective.
jdthedisciple 2 days ago [-]
this kind of stats feature should be shipped by default with every harness imvho
lbrito 2 days ago [-]
How on Earth does one use 1.1B tokens in a week?
hetspookjee 2 days ago [-]
With cache reads and writes and a couple of long running session without /clear or /compact it can get there rather fast
sigseg1v 1 days ago [-]
Take a 2 million line of code repo and ask it to convert from programming language A to B and statically verify every logic flow with an AST for each lang, and then get it to write a test harness that hits 100% code coverage, screenshots every major state and compares screenshots for each state between the old and new. Request it uses an agent team with up to 20 agents. You will use that in a few hours easily.
what-the-grump 2 days ago [-]
Can do that in a day...
Sohcahtoa82 2 days ago [-]
By doing ALL your work in a single chat. The context window explodes.
I typically do one context per feature.
_zoltan_ 2 days ago [-]
last 7 days I've used ~4.8B tokens. most of that was during a 2 day span when codex was using one of my harnesses to iterate over a codebase to improve performance of some parts of it - fully automated.
Of course, it's impossible to know for sure what was LLM processed or not, but some of your posts (like this one) have been getting classified that way.
KinetiNode 2 days ago [-]
only one of my post/reply is flagged other than this one tho?? Also yea i admit i used AI here , sorry for that
seki285 2 days ago [-]
[flagged]
sdcfgy 2 days ago [-]
At least it's not rewriting stuff in Rust.
zuuna 2 days ago [-]
Genuinely of the best reasons to build a tool tho? "I had a problem X, so I did nothing and kept complaining (without LLM)" would be pretty tiring to me personally
jghn 2 days ago [-]
The problem is that anyone can type "I have this problem, plz fix" into Claude Code.
What unique insight or skill did they bring to the process? That's the interesting part. Otherwise it's just a small part of a huge sea of people's individual attempts to solve the same problems that everyone else is solving by themselves.
hetspookjee 2 days ago [-]
These kinds of trivial CLI vibes tools save an evening and some tokens. And sometimes it’s also not something you think of, or done with better or worse taste than your own. I think it’s nice
remus 2 days ago [-]
Indeed. Pre-LLM this kind of thing was a little interesting because you'd need to put a little thought and effort in whereas now it's a one-shot thing straight from an LLM. Don't be a slop proxy, as the saying goes.
I coupled that with a hook that watches for usage spiking (basically when I've been talking too long or did something to add a ton of context, so suddenly every turn sends a ton of context back, using up a ton of usage).
Between the two I haven't hit usage caps in weeks.
B) Warning everyone, it slowly eats tokens - If you're like me and on the pro plan, perhaps not a good idea to have its (albeit slow) drain on the tokens.
Great idea on the hook alert.
I feel like the advent of LLMs has made a super customizable OS like Linux so, so much better than the closed source alternatives, and so much better than they were before.
> Is it safe to start a big refactor now, or should I wait for my window to clear?
Do people just let Opus ultra extra max thinking run amok on their whole codebase with a single context? I don't even think I could even design sensible features faster, I'm the limiting factor here, the robot pretty much oneshots everything I ask for.
My Claude.md + framework stuff has it tell me when it recommends /clear before the next prompt (and write itself handoff notes) and I rarely see >100k context size even on large work.
Surprised they haven't brought the same UX to CC.
Suggests either starting from a summary, a new conversation, or keep going.
That avoids surprises
tare is a Python project. Why distribute it with npm rather than PyPI? Weird
I typically do one context per feature.
Of course, it's impossible to know for sure what was LLM processed or not, but some of your posts (like this one) have been getting classified that way.
What unique insight or skill did they bring to the process? That's the interesting part. Otherwise it's just a small part of a huge sea of people's individual attempts to solve the same problems that everyone else is solving by themselves.
Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something.
If you're going to fully vibe code a repo, maybe we should get the build artifacts (i.e., the claude session).
Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes.
> If you're going to fully vibe code a repo,
I'm not the OP.
Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith.
> If you're going to fully vibe code a repo,
> I'm not the OP.
https://www.collinsdictionary.com/us/dictionary/english/you
"In spoken English and informal written English, you is sometimes used to refer to people in general."
If you are going to repeatedly point out technicalities of a flagged post, please get your ducks in order first.
100% Human written slop