How many tokens is your CLAUDE.md actually costing you?
Paste it below for an estimated token count, split into what reads as an always-on rule and what looks conditional enough to move out.
A clean setup is just the beginning.
UsageCut trims that for free. Want Claude Code to be genuinely better, not just leaner? ClockedCode is the curated, conflict-free setup - installed in one paste.
Upgrade your Claude Code- 10x your Claude Code with hand-picked tools
- Specialist agents on your team
- Stop spending hours researching plugins
A count, plus what to actually do with it
A plain token count tells you a number; it doesn't tell you what to do about it. This tool estimates your total, then walks each ## or ###section and flags the ones that read as scoped to a specific situation - language like "when," "only if," or a heading named after one workflow - rather than a rule every session needs. That split matters because of what this site's own measured CLAUDE.md turned out to look like: 64% of its global header was exactly this kind of trigger-gated content sitting in the always-on tier, detailed in CLAUDE.md best practices, judged by token cost.
The estimate itself is a heuristic, not Anthropic's actual tokenizer - there is no public client-side tokenizer for Claude models, so this counts characters (denser for code, lighter for prose) and lets you toggle for the ~30% jump the newer tokenizer in Opus 4.7 and later models produces over older ones. For the honest, non-estimated version of this - what your real sessions load, not what you paste in - see the Claude Code cost calculator or run the free scan below.
More free tools for Claude Code
Small, focused, no-signup tools from the maker of ClockedCode. Free to use, forever.
More free Claude Code tools are on the way - built one at a time by a solo dev who ships daily.
Claude Code tips, every Sunday
One short email a week: the token-saving tricks, setup tweaks, and tools worth your time. Free, unsubscribe anytime.
About this estimate
Is this an exact token count, like Anthropic's own API?
No - it's a heuristic estimate computed in your browser (roughly 4 characters per token for prose, 3.2 for fenced code), because a purely client-side tool can't call Anthropic's Token Count API. For an exact number, use that API directly, or run the free UsageCut scan, which reads your real files.
Why does the tokenizer toggle matter?
Claude Opus 4.7 and later models, including Sonnet 5, use a newer tokenizer that produces about 30% more tokens for the same text than the tokenizer earlier models used. Toggling it applies that documented difference to the estimate instead of quietly assuming one generation.
How does it decide a section is 'likely conditional'?
It looks at each heading and its body for language that reads as scoped to a specific situation - words like "when," "only if," or a heading named after one workflow - versus a standing rule with no such qualifier. It's pattern matching, not an understanding of your actual workflows, so treat the flags as candidates to review, not a verdict.
Does @import reduce my token count?
No. An imported file still expands and loads in full at session start alongside the file that references it - splitting content behind @import only helps organization, never the always-on token cost. See CLAUDE.md best practices for the full breakdown of what actually shrinks it.
Questions, answered
Is UsageCut really free?
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.
Is my code safe? Does UsageCut upload anything?
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.
How does it reduce Claude Code token usage?
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.
What is ClockedCode?
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.
Who is ClockedCode for?
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.
What's included in ClockedCode?
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.
Is ClockedCode a one-time payment?
Yes. ClockedCode is a one-time purchase with an instant download - no subscription and no recurring fees.
Does ClockedCode work with my existing setup?
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.