Skip to main content
plugin

laconic — Claude Code plugin: what it does, how to install

A terse response mode for Claude Code that keeps technical meaning while dropping filler. Use it when long answers slow down code work.

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add anthropics/claude-plugins-community
/plugin install laconic@claude-community
Open on GitHub

What laconic does

laconic is a compact skill that changes how an AI coding agent writes its replies. It favors short, common words, relies on context, and skips explanations the reader can infer. The result is a concise technical response with only the code and reasoning needed for the task.

The README tests the mode on React rendering, JWT expiry, PostgreSQL, Docker, Git, and security review tasks. Its benchmark reports 90% average savings in output tokens, with results ranging from 75% to 96%. The skill itself is about 300 words.

You can start it with /laconic, “laconic mode,” or “be laconic.” laconic changes output only, so it does not reduce the context sent to the agent. That distinction matters when the main concern is prompt size rather than reply length.

What it helps with

  • trim a verbose debugging explanation
  • review a pull request with fewer words
  • explain a database race condition briefly
  • reduce filler in an architecture answer

Example prompts for the agent

  • Use /laconic and explain why this JWT expiry check fails.
  • Switch to laconic mode and review this pull request for security issues.
  • Be laconic: refactor this callback to async/await and show the required code.

How to install laconic

Plugin marketplace

/plugin marketplace add anthropics/claude-plugins-community
/plugin install laconic@claude-community

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about laconic

How do I install laconic in Claude Code?

Run /plugin marketplace add anthropics/claude-plugins-community, then run /plugin install laconic@claude-community.

What does laconic do?

It puts Claude Code into a terse response mode. The skill removes filler, trusts available context, and keeps the technical answer short.

Does laconic reduce input tokens?

No. It cuts output tokens only.

Source text

SKILL.md · MIT
<p align="center">
  <img src="https://raw.githubusercontent.com/GabrielBarberini/laconic/main/laconic.png" width="120" />
</p>

<h1 align="center">laconic</h1>

<p align="center">
  <strong>Philip II: "If I invade Laconia, I shall turn you out."<br/>Sparta: "If."</strong>
</p>

<p align="center">
  <a href="https://github.com/GabrielBarberini/laconic/stargazers"><img src="https://img.shields.io/github/stars/GabrielBarberini/laconic?style=flat&color=yellow" alt="Stars"></a>
  <a href="https://github.com/GabrielBarberini/laconic/commits/main"><img src="https://img.shields.io/github/last-commit/GabrielBarberini/laconic?style=flat" alt="Last Commit"></a>
  <a href="LICENSE"><img src="https://img.shields.io/github/license/GabrielBarberini/laconic?style=flat" alt="License"></a>
  <a href="https://gabrielbarberini.github.io/laconic/"><img src="https://img.shields.io/badge/web-gabrielbarberini.github.io%2Flaconic-blue?style=flat" alt="Website"></a>
</p>

<p align="center">
  <a href="#install">Install</a> &bull;
  <a href="#benchmarks">Benchmarks</a> &bull;
  <a href="#examples">Examples</a> &bull;
  <a href="#caveman-vs-laconic">Caveman vs Laconic</a>
</p>

---

**laconic** is a 300 word skill for AI coding agents inspired by [caveman](https://github.com/JuliusBrussee/caveman). 

It cuts filler.
It keeps meaning.
It trusts context.

Every word earns its place. 

## Benchmarks

### Caveman Benchmark
Claude Sonnet 4 via Langdock API. Each prompt: generic system prompt vs full laconic SKILL.md. Median of 3 runs per mode.

<!-- BENCHMARK-TABLE-START -->
| Task | Normal (tokens) | Laconic (tokens) | Saved | vs Caveman |
|------|---------------:|----------------:|------:|-----------:|
| Explain React re-render bug | 885 | 68 | 92% | +5pp |
| Fix auth middleware token expiry | 1059 | 39 | 96% | +13pp |
| Set up PostgreSQL connection pool | 2167 | 189 | 91% | +7pp |
| Explain git rebase vs merge | 996 | 95 | 90% | +32pp |
| Refactor callback to async/await | 494 | 62 | 87% | +65pp |
| Architecture: microservices vs monolith | 826 | 209 | 75% | +45pp |
| Review PR for security issues | 940 | 126 | 87% | +46pp |
| Docker multi-stage build | 2635 | 149 | 94% | +22pp |
| Debug PostgreSQL race condition | 1370 | 49 | 96% | +15pp |
| Implement React error boundary | 4096 | 400 | 90% | +3pp |
| **Average** | **1547** | **139** | **90%** | **+25pp** |

*Range: 75%–96% savings across prompts. [Caveman benchmarks](https://github.com/JuliusBrussee/caveman#benchmarks) averaged 64%.*
<!-- BENCHMARK-TABLE-END -->

> [!IMPORTANT]
> Laconic cuts output tokens only.

<details>
<summary>Run benchmarks yourself</summary>

```bash
cd benchmarks
pip install -r requirements.txt

echo "LANGDOCK_API_KEY=sk-your-key" > ../.env.local

python run.py --dry-run
python run.py
python run.py --update-readme
```

</details>

## Examples

**Prompt**: *"My Express auth middleware is letting expired JWT tokens through. The expiry check uses `Date.now()` compared to the token's `exp` field. What's wrong and how do I fix it?"*

<table>
<tr>
<td width="50%">

### 🗣️ Normal (~1,300 tokens)

Explains JWT spec, Unix timestamps vs JavaScript milliseconds, walks through middleware architecture, adds error handling, suggests libraries, and outputs a full refactored file (...)

</td>
<td width="50%">

### Λ Laconic (19 tokens)

> `exp` is in seconds. `Date.now()` is milliseconds.
>
> ```js
> if (Date.now() / 1000 > payload.exp) // expired
> ```

</td>
</tr>
</table>

## Caveman vs Laconic

| | Caveman | Laconic |
|--|---------|---------|
| Tone | Primitive | Terse |
| Explanation | Normal | Trusts context, skips what reader knows |
| Code | Normal | Just enough code |
| Token savings | ~65% | ~90% |

## Install

### Any agent (40+ supported)

```bash
npx skills add GabrielBarberini/laconic
```

`npx skills` supports Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, and [40+ more](https://github.com/vercel-labs/skills). To install for a specific agent:

```bash
npx skills add GabrielBarberini/laconic -a cursor
npx skills add GabrielBarberini/laconic -a copilot
npx skills add GabrielBarberini/laconic -a cline
npx skills add GabrielBarberini/laconic -a windsurf
```

### Pi

```bash
pi install https://github.com/GabrielBarberini/laconic
```

Or from npm:

```bash
pi install npm:tau-laconic
```

On pi you also get an extension: `/laconic [on|off]` (full laconic or off), natural-language triggers ("be laconic", "normal mode"), a `laconic` statusline, and per-project state in `.pi/laconic-mode.json`. It reads its rules from the same `SKILL.md`.

### Claude Code (plugin)

```bash
claude plugin marketplace add GabrielBarberini/laconic
claude plugin install laconic@laconic
```

### Codex

1. Clone repo
2. Open Codex in repo
3. Run `/plugins`
4. Search `Laconic`
5. Install plugin

Or copy the `plugins/laconic/` directory into your Codex plugins folder.

## Usage

Trigger with:
- `/laconic`
- "laconic mode"
- "be laconic"

## License

MIT — Sparta needed no walls. Neither does this license.

© GabrielBarberini · MIT · GabrielBarberini/laconic

Similar plugins

Plugins catalog →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor