How much is repeated compaction actually costing your sessions?

Anthropic's own compaction documentation, whose worked usage example shows a compaction step reprocessing 180,000 input tokens to produce a 3,500-token summary - about 1.94% of what it read. That's a single documented example, not a ratio Anthropic guarantees, so treat it as a modeled estimate: a real summary can run shorter or longer depending on how much detail the conversation asked to keep.

Because a compaction request rereads your entire history before it can write a summary, and where that reread lands - cache-read rate or full input rate - depends on Claude Code's cache TTL: about an hour on a subscription, five minutes by default on an API key. Inside that window a compaction reads cheap; past it, the same reread bills as fresh input, which is 5-10x pricier per token depending on the model. See /compact vs /clear for the full breakdown.

Claude Code's own compaction, the same mechanism whether it fires automatically or you run /compact yourself: reread the history, write a summary, replace everything before it. Anthropic's compaction docs describe the same reread-then-summarize shape at the API level, which is what this tool's summary-size figure is sourced from.

Sonnet 5 always runs the full 1M-token window, on every plan including Pro, so its modeled auto-compact point sits around 967,000 tokens - roughly 30 turns away at this site's measured per-turn average. Opus on Pro's 200K standard window and Haiku 4.5 hit their auto-compact point far sooner, which is why switching the model or context window toggle changes the compaction count so much.

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.