Claude Code Usage Limits

Use tokentrim to keep your Claude Code conversations within budget. It trims output, reads only needed file ranges, and saves history so you pay less.

How it works for a single Claude Code session

1. Install the plugin or clone the repo.
2. Run your Claude Code script.
3. tokentrim trims the tool output and spools long replies to disk.
4. The replay command shows your token usage and savings.

What you get / what it costs

• All hooks, 3 strength profiles, replay, dashboard, daily budget guard, cold‑cache alert – free.
• Pro lifetime $49 (first 500 buyers) or Pro monthly $9/month.
• Pro adds a hosted dashboard, Monday digest, weekly budget alert at 80%, Slack totals, up to 3 machines.

FAQ

Question? How much can I save? Answer: In 135 real conversations, history re‑read dropped 75%, limits lasted 4.0x longer, and billed cost fell 55‑70%. Shrinking output alone saved 6.9%.

Question? Does anything leave my machine? Answer: Nothing leaves by default. Only the hosted dashboard in Pro uses external servers.

Question? Which OS works? Answer: Tested on macOS and Linux with Python 3.9 or newer.

Start trimming your Claude Code usage

Updated 2026-10-30