How much of your context window have you actually used?

An estimate. The turns-based mode uses this project's own measured average of about 31,600 cumulative tokens per turn; the token-count mode takes whatever you paste, most reliably straight from Claude Code's own /context command. For your real, per-session number, run the free scan below - it reads your actual local history instead of modeling one.

It's this site's own modeled figure, not something Anthropic publishes as a fixed percentage. It comes from the worked example in the 1M context window guide, where Sonnet 5's default auto-compaction lands around 967,000 of its 1,000,000-token window - about 96.7%. This tool applies that same ratio to whichever window size is selected, and says so rather than presenting it as an official number.

Because Claude Code gates the 1M window by model and plan, not just by model. Sonnet 5 always runs at 1M on every plan, Pro included, with nothing to buy. Opus 4.6 and later get the same 1M window free on Max, Team, and Enterprise, but need purchased usage credits to unlock it on Pro - otherwise Opus runs the 200K standard window. Haiku 4.5 has no 1M variant documented at all.

Because that's what actually gets rebilled. Claude Code resends the whole conversation on every turn, and everything already sitting in context comes back as a cache read, not fresh input - measured across 1,037 real sessions, cache reads alone are 93.9% of billed tokens. Pricing the carry cost at the input rate would understate it the same way a naive tokens-times-input-price calculator does.

Yes. The scan and every fix are free - no card, no subscription, no signup. You only give an email if you want the optimization plan and one-command undo sent to your inbox.

The scan runs entirely on your machine. It never uploads your code, never reads your API key, and never sends your prompts or conversations anywhere. Only anonymous summary counts leave, and only if you choose to share them.

It reads your local setup and session history to find waste - idle MCP servers loaded into every session, an oversized CLAUDE.md re-sent on every request, duplicate file reads, and bloated tool output - then trims it losslessly, so each session carries less context and you hit your limit far less often.

ClockedCode is the curated, conflict-free Claude Code setup from the same maker. UsageCut makes your current setup leaner; ClockedCode makes it genuinely better - a set of hand-picked tools, specialist agents, and a tuned CLAUDE.md, installed in one paste.

Developers who use Claude Code daily and want a setup that is powerful out of the box instead of spending hours researching and wiring up plugins, agents, and MCP servers themselves.

A vetted, conflict-free bundle of hand-picked tools, specialist agents, and a tuned CLAUDE.md - everything installed together in one paste, with no setup archaeology.

Yes. ClockedCode is a one-time purchase with an instant download - no subscription and no recurring fees.

Yes. It installs alongside what you already have and is fully reversible. Run UsageCut first to clean your current setup, then add ClockedCode to level it up.