Telling Claude to "be concise" barely works: it trims the sentences and keeps all the same waffle. What works is naming exactly what it should stop doing, no intro, no recap, just the answer, and saving that once in your settings so every chat obeys it. The rule to paste is below.
To stop Claude writing an essay for every question, paste a brevity rule into the Instructions for Claude box in your settings so it applies to every chat. The rule tells it to answer first, drop the intro and recap, keep the substance, and only go long when you ask. In Claude Code, set the Concise output style with /config.
Right now, tell it the shape you want
The quickest fix costs one line. Before or after your question, tell Claude the shape of the answer: Answer in 3 sentences. Start with the answer. Then stop., or "just the list, no intro". A hard shape lands far better than "be concise", which Claude reads as slightly shorter sentences while the padding stays.
As Robin at Prime Line puts it, ban a thing, do not request a quality: "be concise" competes with everything else you have asked for, while "no intro, answer first" is a rule it can actually follow. That sorts one message. The next move sorts every message.
Make it stick: one rule in your settings
The Instructions for Claude box applies to every conversation you start, so a rule written here is the version that truly sticks.
- Click your initials at the bottom-left, then open Settings.
- Find the Instructions for Claude section.
- Paste the rule below and save.
Answer first, in the fewest words that fully cover it. Never cut the meaning or the explanation to be short. Say the same thing with less padding. Cut the narration, keep the substance. Do not restate my question, announce your plan, or recap each step you took. Give me the outcome, the decision, and anything I have to act on. No warm-up like "Great question", "You're right" or "Let me help with that", and no summary at the end of what you just said. Short by default: a simple question gets one to three sentences of plain prose. Use a heading, a table or a bullet list only when it carries real structure, never as decoration. Say it plainly. Skip the hedging and the boilerplate. Mention a caveat only when it changes what I should do next. If a yes or no answers it, say yes or no first, then one line of why at most. Never trade being right for being short. Keep full error messages, warnings, and anything I need to act on safely. When I actually want the long version, I will say "full version" or "explain", and then you can go as deep as it needs.
This works because naming the exact habits to drop beats a vague "be concise". "Be concise" reads as a mood, while "no warm-up, answer first, no summary" is a set of rules it can actually follow. If replies still end with an offer to do more, add "no offers at the end" to the rule.
In Claude Code, use the Concise output style
If you work in Claude Code, the terminal tool, it has a built-in Concise output style that leads with the result and skips the preamble and narration, while still keeping full error reports and safety warnings. Run /config, choose Output style, and pick Concise.
It needs Claude Code v2.1.237 or later, and on current versions the change takes effect from your next message. Use /config for this, as the old /output-style command has been removed.
In the chat app, Anthropic's help page (read 22 September 2026) now points to Skills for changing how Claude formats its replies, and the old preset styles menu is no longer documented. The settings rule above is the part that reliably works.
If you use ChatGPT instead
Same idea, different menu. OpenAI's help page (read 22 September 2026) puts custom instructions under Settings, then Personalization, on the web and desktop, and under Customize ChatGPT on the phone. Paste the brevity rule above into that box, and it carries across your chats the same way.
The catch worth knowing
Short is not always better. Pushed too hard, a concise answer will quietly drop the caveat, the risk, or the reason behind a suggestion, and you feel finished sooner than you should.
That is exactly why the rule keeps an escape hatch, so when a decision or a piece of code actually matters, type "full version" and let it open back up. Brevity for the everyday, depth on demand.
The rule nudges, it does not lock, so in a very long chat it can drift back to its old habits, and a quick "shorter, answer first" pulls it straight back.
Questions people ask
How to get Claude to be more concise?
Name exactly what it should stop doing, such as no intro, no recap and answer first, and paste that rule into the Instructions for Claude box in Settings so every chat follows it. For a single message, give it a hard shape, like "Answer in 3 sentences. Start with the answer. Then stop."
How do I set Claude Code's output style to concise?
Run /config, choose Output style, and pick Concise. It needs Claude Code v2.1.237 or later, and the old /output-style command has been removed.
What is concise style in Claude?
In Claude Code, Concise is a built-in output style that leads with the result and skips the preamble and narration, while keeping full error reports and safety warnings. In the chat app, the old preset styles menu is no longer documented, so a brevity rule in your settings does the job.
Why is Claude so wordy in the first place?
It comes from how these models are trained: answers that ran longer tended to be rated better, so over-explaining became a habit. It is nothing you did, and you can turn it down.
Will making Claude concise make its answers worse?
It can, if you push too hard. A very short answer sometimes drops the caveat or the reason that actually mattered. That is why the rule above keeps an escape hatch: tell it "full version" when you want the depth back, and it opens up again.