Discussion
Search code, repositories, users, issues, pull requests...
sgarland: curl -fsSL https://raw.githubusercontent.com/liorwn/claudetop/main/install.sh | bash Installing claudetop... cp: /Users/sgarland/claudetop.sh: No such file or directory You need to have it handle being piped; right now it expects to find itself at $PWD. It also makes several other assumptions, like the location of Claude, and that the user wants stats being `/usr/local/bin`.
liorwn: I built this after noticing a $65 charge for what felt like a $10 session. Turns out, context compaction was hiding 80% of my token usage. Real cost, no visibility.claudetop is a status line for Claude Code that shows your burn rate, cache efficiency, model cost comparison, and smart alerts (like "TRY /fast" when Opus is overkill for the task). Plugin system for extensibility — Spotify, CI status, calendar, etc.Single bash script, zero dependencies beyond jq. One-command install.
cortesoft: I am always a hit confused when people talk about these charges... are you not using the subscriptions with the flat rates? I am on the $100 a month plan, and am constantly using clause code and never coming close to my limits. Maybe I am just not using it at the levels of some people...
copperx: $100 is for casual usage. To use it for work requires $200/mi plus extra usage.
Gobd: CC does all of my work and I have hit the $100/mo Max plan limit only once, and I probably could have just called it quits for the day at that point.
Gobd: I have noticed the same with the $100/mo plan, I hit the limt only once with heavy usage. Then when I use my employer's AWS Bedrock it's not uncommon for my spend to $50/day of serious work. It doesn't make much sense.
verdverm: The paid plans require you to use their interfaces or tooling. The main reason I pay per token is so I have tooling freedom. I'm not keen to let Big AI decide how I interact with this game changing technology.
jakeinspace: Please type things yourself. Or at least prompt your LLM of choice to sound less canned.
CubsFan1060: 41 minute old account. "I built post". LLM sounding everything. I'd be surprised if there was a real person behind this at all.
sroussey: Anthropic is subsidizing Claude Code. It makes lots of sense.
verdverm: I pay per token using an API (Vertex)1. Higher limits2. I don't think it gets quant nerf's during busy times, since you are paying directly3. With Gemini flash + CC prompts, it's nearly as good, so less spend and latency. I don't know how people deal with the delays between turns. I get to iterate much faster for most tasks
MattGaiser: How many agents are you using at once?
h1r1ms: Try this mcp for agents https://github.com/itsamruth/subagent-reuse
brcmthrowaway: Have you tried a local model?
rvz: The Qwen series are very good local models.
cortesoft: I haven't yet been blocked by their tooling. All the current tools I use seem to work fine with the claude code interface, can just call it with -p.
cortesoft: I don't seem to have any delays between turns with my Claude subscription, so not sure what you mean there.Your second point seems like a guess.For your first point, I bumped to the $100 plan because i was hitting limits with the $20 one, but haven't hit the limit with the new one yet...
cortesoft: Are you saying that is the Claude rules for the subscription or saying because work uses more of it?
cortesoft: 3 or 4? Plus whatever sub agents they spawn...
Self-Perfection: > like "TRY /fast" when Opus is overkill for the taskIn fact using /fast in this case would only increase spending. /fast mode uses the same opus but consumes $$$$ faster to produce tokens faster )https://code.claude.com/docs/en/fast-mode
brikym: /authentic-writer skill: No em dashes or emojis. add in a few typos and bad grammmer. Avoid it's not not X but Y. imagine you're a mere human and your pinky finger is very tired so you forget to uppercase sometimes.
brikym: Nice idea. A sounds plugin would be great. Imagine if you could gauge the spend just by a geiger counter, or the tempo of a song. Any chance of opencode support?
