BazaarLink
One key for 140+ AI models
bazaarlink.aiVisit sponsor ↗70 mods for Claude Code cost and token trackers, ordered by the votes people give them on ClaudeMods. A good place to start: token-optimizer,cache-warmer or cache-warmer.
Each entry links to its original repository or post, and shows how to install it.
70One key for 140+ AI models
bazaarlink.aiVisit sponsor ↗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+.

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!
Set a session budget, receive warnings near the limit and restrict further spending.

One key for 140+ AI models
bazaarlink.aiVisit sponsor ↗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.

Display session spending as a flame progress bar, with plan limits and per-turn costs.

Record session spending, tokens in the latest turn and cache-hit rates, with a usage table.

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.
A Claude Code plugin that surfaces per-turn cost and 5-hour plan usage live in the spinner and prompt band, applies model/effort switches from `optimaizr live`, counts down before the conversation cache expires, offers `/optimaizr handoff` notes, and guards against retry loops — all running locally.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗A fixed status line showing usage in the five-hour and seven-day plan windows.

Claude Code mod that keeps the prompt cache warm during breaks by sending small refresh forks shortly before expiry, reducing the cost of the next prompt.
Keeps a big chat's prompt cache warm, warns before an expensive cold restart, shows every local chat on one board (/board), and hands a chat off to a fresh one (/handoff)