# Claude Token Efficient — Drop-in CLAUDE.md for Terse Output

> A single CLAUDE.md file that reduces Claude Code output verbosity by 63%. Includes 5 specialized profiles for coding, benchmarks, agents, and analysis workflows.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

Download and add to your project root:

```bash
curl -o CLAUDE.md https://raw.githubusercontent.com/drona23/claude-token-efficient/main/CLAUDE.md
```

Or manually create `CLAUDE.md` in your project root with this content:

```markdown
## Approach
- Think before acting. Read existing files before writing code.
- Be concise in output but thorough in reasoning.
- Prefer editing over rewriting whole files.
- Do not re-read files you have already read unless the file may have changed.
- Test your code before declaring done.
- No sycophantic openers or closing fluff.
- Keep solutions simple and direct.
- User instructions always override this file.
```

---

## Intro

Claude Token Efficient is a single drop-in CLAUDE.md file that makes Claude Code responses terse and reduces output verbosity by approximately 63% (from 465 to 170 words on average), with 3,100+ GitHub stars. It includes 5 specialized profiles — Universal, Coding, Benchmark, Agents, and Analysis — each tuned for different workflow types. Independent benchmarks showed 17.4% cost savings compared to the next-best configuration. Zero code changes needed — just add the file to your project root.

Best for developers with high-volume Claude Code usage who want to reduce token costs and get faster responses. Works with: Claude Code. Setup time: under 30 seconds.

---

## Available Profiles

### Universal Profile (Default CLAUDE.md)

The base configuration that works for any project:

```markdown
## Approach
- Think before acting. Read existing files before writing code.
- Be concise in output but thorough in reasoning.
- Prefer editing over rewriting whole files.
- Do not re-read files you have already read unless the file may have changed.
- Test your code before declaring done.
- No sycophantic openers or closing fluff.
- Keep solutions simple and direct.
- User instructions always override this file.
```

### Coding Profile (`profiles/CLAUDE.coding.md`)

For dev projects, code review, and debugging. Adds code-specific rules:
- Simplest working solution first
- No over-engineering or speculative features
- For bug reports: state bug → show fix → stop
- No em dashes or smart quotes (copy-paste safe)
- No trailing summaries after code changes

### Benchmark Profile (`profiles/CLAUDE.benchmark.md`)

For token-to-green coding benchmarks. Optimized for passing tests with minimal output.

### Agents Profile (`profiles/CLAUDE.agents.md`)

For automation pipelines and multi-agent systems. Tuned for structured, parseable output.

### Analysis Profile (`profiles/CLAUDE.analysis.md`)

For data analysis, research, and reporting. Allows slightly more verbose output where detail matters.

### Versioned Config Sets

| Version | Style | Call Budget |
|---------|-------|-------------|
| J-drona23-v5 | Multi-file structured | 50 calls |
| K-drona23-v6 | One-shot execution | 50 calls |
| M-drona23-v8 | Ultra-lean | 20 calls |

### Benchmark Results

| Metric | With Token Efficient | Without |
|--------|---------------------|---------|
| Average words per response | 170 | 465 |
| Word reduction | 63% | — |
| Cost savings vs next-best | 17.4% | — |

**Note**: Best for high-output-volume workflows. At low volume, the input overhead of the CLAUDE.md file may exceed the output savings.

### FAQ

**Q: What is Claude Token Efficient?**
A: A single CLAUDE.md config file that reduces Claude Code's output verbosity by 63%, saving tokens and costs on high-volume workflows.

**Q: Is Claude Token Efficient free?**
A: Yes, fully free and open source under the MIT license.

**Q: How do I install Claude Token Efficient?**
A: Run `curl -o CLAUDE.md https://raw.githubusercontent.com/drona23/claude-token-efficient/main/CLAUDE.md` in your project root.

---

## Source & Thanks

> Created by [Drona Gangarapu](https://github.com/drona23). Licensed under MIT.
>
> [claude-token-efficient](https://github.com/drona23/claude-token-efficient) — ⭐ 3,100+

Thank you for helping developers save tokens and get more concise AI responses.

---

<!-- ZH -->


## Quick Use

Download and drop it into your project root:

```bash
curl -o CLAUDE.md https://raw.githubusercontent.com/drona23/claude-token-efficient/main/CLAUDE.md
```

---

## Intro

Claude Token Efficient is a drop-in CLAUDE.md file that cuts Claude Code's output verbosity by about 63% (from 465 words on average to 170). It has 3,100+ GitHub stars. It includes 5 specialized profiles — general, coding, benchmarking, agent, and analysis — each tuned for a different type of workflow. Independent benchmarks show 17.4% cost savings vs. the runner-up configuration. Zero code changes required — just drop it into your project root.

Best for heavy Claude Code users. Setup time: under 30 seconds.

---

## Available Profiles

- **General** (default) — 8 concise rules, fits any project
- **Coding** — Simplest solution first, no over-engineering
- **Benchmarking** — Tuned for passing tests
- **Agent** — Structured, machine-parseable output
- **Analysis** — Moderately verbose for data analysis scenarios

Benchmarks: 63% word-count reduction, 17.4% cost savings.

---

## Source & Thanks

> Created by [Drona Gangarapu](https://github.com/drona23). Licensed under MIT.
>
> [claude-token-efficient](https://github.com/drona23/claude-token-efficient) — ⭐ 3,100+



---
Source: https://tokrepo.com/en/workflows/claude-token-efficient-drop-claude-md-terse-output-5bfc4f12
Author: AI Open Source