Trimloop
Trimloop tells you what to change in how you use Claude Code, and what
each change would save: money, if you pay per token; room under your usage
limits, if you are on Pro or Max. It reads the session logs Claude Code
keeps on your machine and sends nothing anywhere.
A usage tracker (Claude Code's own /cost, or a tool that adds up your
tokens) tells you how much you used. Trimloop tells you why, what to
do about it, and afterwards whether it worked:
| |
|---|
| Why | Which habits cost the most: long sessions, breaks that let the cache expire, bulky tool output, a dearer model than the work needs (all nine) |
| What to do | Changes ranked by what they would save, each with the steps to make it |
| Did it work | Week-by-week figures, and --since the day you made a change |
| If you pay per token | Savings in dollars at list prices |
| If you are on Pro or Max | How often you hit a usage limit, and each saving as a share of your weekly limit |
| While you work | A status line and nudges in Claude Code, before a costly message is sent |
brew install --cask chrisadkin8/tap/trimloop # macOS or Linux; other ways are under Install
trimloop # what to do first
trimloop --open # the full report, in your browser
Status: early prototype (milestone M0 in the roadmap).
It analyses Claude Code logs and gives live nudges inside Claude Code. It
recommends; it does not change anything for you. The wider product
(gateway plugin, team collector, automatic fixes) is design only: see
The plan.
What you get
A run on one developer's 46 days of logs, shortened (the full output also
covers their usage limits):
Read 611 logs: 594 sessions, 20,256 turns.
Spent $2,465 at list prices from 25 Sep to 10 Nov 2026 (46 days), about $375 a week.
Claude Code's own records show $221 (11%) more than its logs: requests the logs do not record.
What to do first (these savings overlap, so do not add them):
1. Compact long sessions earlier: likely about $618 ($585–$680), up to $947 (38%)
Compact when a session passes about 200,000 tokens, or between tasks.
2. Run sub-agents on a cheaper model: up to $337 (14%)
Run sub-agents that search, read and summarise on Sonnet 5.5.
3. Start fresh after a long break: likely about $302, up to $312 (13%)
After a break of over an hour, start a new session with a short note instead of carrying on.
In plain words: every turn re-sends the whole conversation, so long
sessions get expensive. Compacting (/compact in Claude Code) replaces
the conversation so far with a short summary. Sub-agents are helpers
Claude starts for side tasks, such as searching the code.
The full report explains each finding, shows the sessions behind it, and
gives the fix step by step. See one in your browser:
the web page from the same run, with session titles left out and project
folders renamed to neutral words (oak, larch, ...). This is its top:
(The page's file is
docs/examples/example-report.html.)
How far to trust the figures. They are estimates:
- Costs are at Anthropic's list prices: what the tokens would cost if you
paid per token, not your bill.
- On a Pro or Max plan you pay a flat fee instead. The report says so and
counts how often you hit a usage limit. Once trimloop's status line is set
up (Live nudges), it also shows, in time,
each saving as a share of your weekly limit
(ADR 0048; ADRs are the
project's decision records).
- "Up to" is the most a change could save. "Likely", where an action has
it, replays your logs as if you had made the change.
- Savings overlap (the same tokens can be saved by several changes), so
they are never added up.
- Claude Code makes some requests its logs do not record. The report says
how much: 11% in the run above.
- Quality is not measured. Check a change marked "untested for quality" (a
cheaper model, lower effort) after you make it.
How each figure is worked out is in docs/measurements.md.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
