claude-token-efficient

A single CLAUDE.md file you drop into a project to keep Claude's replies short. It aims to cut output tokens on heavy workflows with no code changes.

Share on XLicense: MIT

Overview

claude-token-efficient is a single CLAUDE.md file you drop into a project to keep Claude's replies short. It targets habits such as opening pleasantries, closing offers of help, restating the question, unrequested suggestions and over-engineered code. It needs no code changes and aims to reduce output tokens on output-heavy workflows. The author notes that instruction files add input tokens every turn, so the file should stay short.

Key features

  • One drop-in CLAUDE.md file, no code changes
  • Curbs filler openings, closings and restated questions
  • Discourages unrequested suggestions and over-engineering
  • Rules are model-agnostic, benchmarked on Claude only

Best for

Claude Code users with output-heavy workflows who want terser answers. If the file grows too large it can cost more than it saves. Results on other models are untested.

Upstream
drona23/claude-token-efficient
Fork on GitHub
Guo-astro/claude-token-efficient
Upstream stars
6.1k
Category
AI agents and LLM tools
License
MIT
Forked
2026-04-01
Sync status
Status unknown