Performance Issue Description
Right now cli commands use more tokens than necessary, increasing costs and runtimes.
https://github.com/rtk-ai/rtk aka "rust token killer" is a rust cli command wrapper that recoverably filters cli commands to the necessary outputs, saving tokens, and in many cases improving model performance due to decreased context filler.
Token Savings (30-min Claude Code Session)
| Operation |
Frequency |
Standard |
rtk |
Savings |
ls / tree |
10x |
2,000 |
400 |
-80% |
cat / read |
20x |
40,000 |
12,000 |
-70% |
grep / rg |
8x |
16,000 |
3,200 |
-80% |
git status |
10x |
3,000 |
600 |
-80% |
git diff |
5x |
10,000 |
2,500 |
-75% |
git log |
5x |
2,500 |
500 |
-80% |
git add/commit/push |
8x |
1,600 |
120 |
-92% |
cargo test / npm test |
5x |
25,000 |
2,500 |
-90% |
ruff check |
3x |
3,000 |
600 |
-80% |
pytest |
4x |
8,000 |
800 |
-90% |
go test |
3x |
6,000 |
600 |
-90% |
docker ps |
3x |
900 |
180 |
-80% |
| Total |
|
~118,000 |
~23,900 |
-80% |
Of course, I saw you take care to optimize for model idiosyncrasies per your blog and I expect rtk integration would need some optimization to work properly.
Issue Type
Other
Steps to Reproduce
see tokens savings table, cli commands like ls / tree produce lots of extraneous output.
Expected Performance
see tokens savings table
Actual Performance
see token savings table
Performance Measurements
Project Size
No response
Environment Details
Macos M3 Max, but applies across all platforms.
Configuration
Profiling Data
Frequency
Always
Workarounds
No response
Additional Context
No response
Performance Issue Description
Right now cli commands use more tokens than necessary, increasing costs and runtimes.
https://github.com/rtk-ai/rtk aka "rust token killer" is a rust cli command wrapper that recoverably filters cli commands to the necessary outputs, saving tokens, and in many cases improving model performance due to decreased context filler.
Token Savings (30-min Claude Code Session)
ls/treecat/readgrep/rggit statusgit diffgit loggit add/commit/pushcargo test/npm testruff checkpytestgo testdocker psOf course, I saw you take care to optimize for model idiosyncrasies per your blog and I expect rtk integration would need some optimization to work properly.
Issue Type
Other
Steps to Reproduce
see tokens savings table, cli commands like ls / tree produce lots of extraneous output.
Expected Performance
see tokens savings table
Actual Performance
see token savings table
Performance Measurements
Project Size
No response
Environment Details
Macos M3 Max, but applies across all platforms.
Configuration
Profiling Data
Frequency
Always
Workarounds
No response
Additional Context
No response