Live data from Hacker News

Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

github.com

91–100 of 143 posts

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#92
post #54

I really like this idea as I find Claude's transparency frustrating. Claude code's killer features revolve around better tools to manage context and limits vs the desktop app (compact and the % remaining until auto compact), but it's not enough. If I can offer any advice, it's that the high use of emojis in a project readme (at least for me) looks so unprofessional and makes me worry that a project was vibe -coded in…

> looks so unprofessional and makes me worry that a project was vibe -coded in the sense that the AI was possibly not babysat to the extent I think they should. That's just me, though The irony of comments like this on software designed entirely for ai coding...

AI coding where the human stays in control and reads and confirms code is totally different from vibe coding where you don't read code and just prompt until it sort of works.

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#93
post #54

I really like this idea as I find Claude's transparency frustrating. Claude code's killer features revolve around better tools to manage context and limits vs the desktop app (compact and the % remaining until auto compact), but it's not enough. If I can offer any advice, it's that the high use of emojis in a project readme (at least for me) looks so unprofessional and makes me worry that a project was vibe -coded in…

It strikes me as very much a current aesthetic in younger companies or smaller startups, maybe highly influenced by Notion. No one makes a list or page or calendar invite in my current company without choosing an emoji for it.

It was cool until 2022. Then LLMs started injecting these emoji everywhere and it became the chief marker for code/doc smell.

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#94
post #54

I really like this idea as I find Claude's transparency frustrating. Claude code's killer features revolve around better tools to manage context and limits vs the desktop app (compact and the % remaining until auto compact), but it's not enough. If I can offer any advice, it's that the high use of emojis in a project readme (at least for me) looks so unprofessional and makes me worry that a project was vibe -coded in…

My goto for AI generated PR descriptions and README is this addition to the prompt: tight, no purple prose, no emojis.

That turns thrse meandering emoji fests into suitable documentation. YMMV

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#95

This is great. I built a UI tool to run simultaneous Claude Code sessions ( https://github.com/stravu/crystal ) but by working on multiple features at once I hit the limits of my max account. Usually close to the reset, but it would be nice to know when it is time to take a break.

This is excellent. I am an EXTENSIVE Claude Code user but I've been a bit scared to write my own tooling around worktrees + multiple sessions because I don't understand git well enough.

To be honest, I'm a little scared to use this also. I feel like ideally each worktree would also run in a container, but that seems quite a bit harder to make work as smoothly as this does.

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#96
post #52
post #48

Earlier quoted context omitted.

Or just straight to CO2. Google said 1000 tokens emits 8.3g CO2. How many tokens used in a heavy vibe coding day? Average US daily per capita is like 40kg CO2

I don’t understand the concern of this. Let’s say it says you’ve used 1.521kg of CO2 today. How is that actionable? A single flight from JFK to LAX produces around 20,000kg of CO2. Using the 8.3g value means a flight is equivalent to 2.41 billion tokens.

Per capita that is what, 500kg?

So on that day you are 10x'ing the US person day

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#97
post #59
post #52

Earlier quoted context omitted.

I don’t understand the concern of this. Let’s say it says you’ve used 1.521kg of CO2 today. How is that actionable? A single flight from JFK to LAX produces around 20,000kg of CO2. Using the 8.3g value means a flight is equivalent to 2.41 billion tokens.

I really dislike when people don't see this. They try to cut 10 grams of CO2 per day while other industries (shipping, aviation, rails) produce hundreds of tons per day and even this transportation modes are less that 20% with most CO2 produced mainly being in energy production and used by industry.

Sure, but that's all accounted for in per capita numbers.

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#98
post #48
post #25

This is pretty cool.. I like the idea, could I make a semi-snarky feature request and could we add the estimated power consumed to produce results for each session ?

Or just straight to CO2. Google said 1000 tokens emits 8.3g CO2. How many tokens used in a heavy vibe coding day? Average US daily per capita is like 40kg CO2

I just hit my usage limit this morning, and the article shows how to get these numbers so I can answer this myself -- I'd be curious to see what other people are doing token wise day-to-day

ccusage says I had 1k input tokens, 12k output and 1.2m cache create.

I'm not sure if that is 18.3g, 138.3g or 1213 * 8.3g.

At the highest number that's 10kg or 25% of average US daily per capita emission or 1 gallon of gas.

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#99
post #92

Earlier quoted context omitted.

> looks so unprofessional and makes me worry that a project was vibe -coded in the sense that the AI was possibly not babysat to the extent I think they should. That's just me, though The irony of comments like this on software designed entirely for ai coding...

AI coding where the human stays in control and reads and confirms code is totally different from vibe coding where you don't read code and just prompt until it sort of works.

I completely agree. Andrej's definition was pretty explicit and in my experience it is two separate worlds of AI use.

Re: Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

#100
post #54

I really like this idea as I find Claude's transparency frustrating. Claude code's killer features revolve around better tools to manage context and limits vs the desktop app (compact and the % remaining until auto compact), but it's not enough. If I can offer any advice, it's that the high use of emojis in a project readme (at least for me) looks so unprofessional and makes me worry that a project was vibe -coded in…

if you actually look at the code, it's a single 400 line python file that just wraps https://github.com/ryoppippi/ccusage, so it's possible
Post reply on HN