⚡ Free tier · No credit card

See what Claude Code actually costs you

Claude Code already writes down every token it spends. It just never adds it up. Pulse Code reads those records across all your machines and shows you which project, which MCP server and which scheduled job the money went to.

★★★★★ Built for Claude Code power users · 100% private — never reads your prompts · Installs in 60 seconds · Linux, macOS, Windows
Quick answer

Pulse Code is a usage monitor for Claude Code, the command-line tool. A small agent reads the session transcripts Claude Code already writes to your disk and uploads only counts — tokens, tool names, timestamps — never your prompts or your code. You get cost per session, per project, per MCP server and per scheduled job, across every machine you work on. There is a free tier for one machine.

Six things you cannot see today

The cache split

Input, output, cache write and cache read, priced separately. Most spend is cache reads — one combined number hides that completely.

Cost per project

Taken from the working directory each session started in. No tagging, no setup, no way to forget.

Per-MCP-server cost

Which server fills your context, how big its results are, and how often it errors. A chatty server is paid for on every later turn.

Scheduled runs

Headless runs are separated automatically. Name them with cc-run and every job gets its own line.

Every machine, one view

Laptop, desktop, server. One account, one total, and a filter for any single machine.

Alerts before the bill

Tell it when spend passes what a normal day looks like — by project, machine, server or job.

Three steps, about a minute

1

Create a key

One click after you sign up. It is shown once.

2

Run one command

The installer checks its own download against a published checksum before it runs anything.

3

Watch it fill in

Your whole history imports, then it keeps up on its own. Nothing else to do.

Does it read my prompts or my code?

No. The agent opens every transcript read-only and writes nothing inside your Claude Code directory. It sends counts and names — never content. We measured this rather than claiming it: a full agent run across 29,558 files changed not one byte.

  • Never sends your prompts or Claude's replies
  • Never sends your file contents or tool arguments
  • Never sends what your tools returned — only how many bytes it was
  • Never writes to ~/.claude/
  • Project paths can be hashed before upload with --redact-paths
Read exactly what is sent, field by field

Questions people actually ask

No. The agent sends token counts, model names, tool names, timestamps and the size of each tool result. It never sends your prompts, Claude's replies, your file contents, your tool arguments, or what your tools returned. It opens every transcript read-only and writes nothing inside your Claude Code directory.

Other things worth knowing

How much does Claude Code cost per day?

It depends entirely on how you use it, and the honest answer is that most people have no idea until they measure. A light day of interactive work looks very different from a day with a scheduled job running every hour. The point of measuring is that the answer stops being a guess.

Does Claude Code show token usage by itself?

Claude Code writes detailed usage data to disk for every session, but it does not add it up for you across sessions, projects or machines. The numbers are already there — they just need reading, deduplicating and totalling.

Can I see which project costs the most?

Yes. Every session records the working directory it started in, so cost is attributed per project automatically. No tagging, no configuration.

What happens if I stop paying?

Your account drops to the free tier. Nothing is deleted immediately — you keep one machine and seven days of detail, and your longer-term daily totals stay intact, so your history does not vanish.

Do I have to send my data anywhere?

The counts, yes — that is what makes the dashboard work. The content, never. If even project paths are sensitive, the agent has a --redact-paths flag that hashes them before upload, so you still get per-project totals without the names.

Stop guessing what Claude Code costs

Get started free

Free tier · No card · 60-second install