Claude Token Efficient

claude-token-efficient
One file. Drop it in your project. Keeps responses terse and can reduce total tokens on output-heavy workflows.
Note: instruction files add input tokens on every turn. Keep this file short - if it grows too much, it can cost more than it saves.
Model support: benchmarks were run on Claude only. The rules are model-agnostic and should work on any model that reads context - but results on local models like llama.cpp, Mistral, or others are untested. Community results welcome.

The Problem

When you use Claude Code, every word Claude generates costs tokens.
Most people never control *how* Claude responds - they just get whatever the model decides to output.

By default, Claude:
- Opens every response with "Sure!", "Great question!", "Absolutely!"
- Ends with "I hope this helps! Let me know if you need anything!"
- Uses em dashes (--), smart quotes, Unicode characters that break parsers
- Restates your question before answering it
- Adds unsolicited suggestions beyond what you asked
- Over-engineers code with abstractions you never requested
- Agrees with incorrect statements ("You're absolutely right!")

All of this wastes tokens. None of it adds value.

Two Options

Option 1: Paste rules in chat (quick start)
Copy these rules into any new session:

Works immediately. No setup. Good for one-off tasks.

Option 2: Drop CLAUDE.md file (set and forget)

Automatic on every message. Better for regular work. More efficient at scale.

Pick based on your workflow. Both work.

How They Compare

When This Helps vs When It Doesn't

This file works best for:
- Automation pipelines with high output volume (resume bots, agent loops, code generation)
- Repeated structured tasks where Claude's default verbosity compounds across hundreds of calls
- Teams who need…