GitHub · Python
ilien-dev/sharur
Cut Claude Code token usage and cost with a one-line output style. Shorter replies than Concise on every Claude model: 29% fewer output tokens and 23% lower cost on Opus 5.5. Benchmarked.
- Stars
- 10
- Forks
- 0
- Stars gained in 24 hours
- +1
- Forks gained in 24 hours
- 0
Topics: ai-coding-assistant, anthropic, benchmark, caveman, claude, claude-code, concise, cost-reduction, developer-tools, llm
Latest data point: Nov 20, 2026 · 10 stars · 0 forks