I have made a Claude Code Mod that helps me keep a very accurate track of my usage limits on Claude, down to the last $ & %. Some key findings > I would save unto 30% usage if I set /autocompact to 400K > Sonnet 5.5 (old pricing) barely saved me any usage compared to Opus 5.5 and was not worth it > We are NOT getting the full discount on cache reads in our subs on Sonnet 5.5 (more on this later) > I have burnt $7K in Claude tokens in 30 days apparently This was a great experiment!
I have made a Claude Code Mod that helps me keep a very accurate track of my usage limits on Claude, down to the last $ & %. Some key findings > I would save unto 30% usage if I set /autocompact to 400K > Sonnet 5.5 (old pricing) barely saved me any usage compared to Opus 5.5 and was not worth it > We are NOT getting the full discount on cache reads in our subs on Sonnet 5.5 (more on this later) > I have burnt $7K in Claude tokens in 30 days apparently This was a great experiment!
I have made a Claude Code Mod that helps me keep a very accurate track of my usage limits on Claude, down to the last $ & %.
Some key findings
I would save unto 30% usage if I set /autocompact to 400K Sonnet 5.5 (old pricing) barely saved me any usage compared to Opus 5.5 and was not worth it We are NOT getting the full discount on cache reads in our subs on Sonnet 5.5 (more on this later) I have burnt $7K in Claude tokens in 30 days apparently
This was a great experiment!
Check the author's README for the marketplace and plugin name first. Commands may change as the repository evolves.
claude plugin marketplace add rohit3a/usage-meter claude plugin install usage-meter
I have made a Claude Code Mod that helps me keep a very accurate track of my usage limits on Claude, down to the last $ & %.
Some key findings
I would save unto 30% usage if I set /autocompact to 400K Sonnet 5.5 (old pricing) barely saved me any usage compared to Opus 5.5 and was not worth it We are NOT getting the full discount on cache reads in our subs on Sonnet 5.5 (more on this later) I have burnt $7K in Claude tokens in 30 days apparently
This was a great experiment!
Claude Code plugin that compresses tool output, checkpoints before compaction, scores context quality, and reports token/cost savings on a local dashboard; ships hooks and a localhost daemon.
A Claude Code mod that keeps the one-hour prompt cache warm during breaks and stops a cold send once with its estimated rewrite cost. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+.
A Claude Code mod that keeps an idle session's prompt cache warm with silent pings, then compacts large sessions once while the cache is still warm.