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.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
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
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub