Guide · Claude Code

How to change Claude Code's personality.

Output styles, CLAUDE.md, a launch flag, or a whole agent. One of them is built for this.

Quick answer: Save a Markdown file to ~/.claude/output-styles/ with name, description, and keep-coding-instructions: true in the YAML frontmatter, followed by your communication rules. Activate it with /output-style or /config. AgentTune provides all 43 personality tunings as ready-to-download output styles.
On this page

The twenty-second version.

Download a ready-made output style into ~/.claude/output-styles/ and select it:

tuning_dir=$(mktemp -d ./agenttune.XXXXXX) &&\ curl --fail --show-error --location https://agent-tune.com/output-styles/agenttune-mbti-intj.md \ --output "$tuning_dir/style.md" &&\ mkdir -p ~/.claude/output-styles &&\ (set -C; cat "$tuning_dir/style.md" > ~/.claude/output-styles/agenttune-mbti-intj.md)
  1. Restart Claude Code (custom style files are read at startup).
  2. Run /output-style and pick AgentTune INTJ (or set Output style inside /config).
  3. Run a real coding task to verify the new reporting style.

All 43 MIT-licensed styles are listed below and can be edited freely.

Four places to put it. They do different jobs.

Claude Code offers four ways to pass instructions, each with a different scope:

WhereWhat it doesLoadsUse it for
Output styleUpdates the system-level instructions Claude Code works fromEvery turnRole and communication tone (your personality file)
CLAUDE.mdArrives as a context message after the system promptEvery sessionProject build commands, test runners, and architecture
--append-system-promptAppends text to the system prompt at launchThat launchOne-off scripts or quick experiments
--agentRuns the session as a subagent with its own prompt, model, and toolsThat sessionReplacing who Claude Code is entirely

Because an output style is reinforced in the system prompt across turns, it holds up much better in long sessions than tone notes buried inside a repo CLAUDE.md.

Output styles, and the flag that matters.

Claude Code includes five built-in output styles: Default, Proactive, Concise, Explanatory, and Learning. You can also add custom Markdown files in ~/.claude/output-styles/ (global) or .claude/output-styles/ (per project).

Each custom style file takes four frontmatter keys:

  • name: Display name in the /output-style menu.
  • description: Short summary shown in the picker.
  • keep-coding-instructions: Defaults to false—always set this to true!
  • force-for-plugin: Used by plugins only.

Why keep-coding-instructions: true matters: By default, a custom output style drops Claude Code’s built-in software-engineering rules so people can repurpose the CLI for non-coding tasks. If you want the same coding agent with cleaner communication, include keep-coding-instructions: true:

--- name: Straight answers description: Conclusion first, no hedging, one recommendation. keep-coding-instructions: true --- How to talk to the person you are working with: - Lead with the answer or the recommendation. Reasoning comes after. - Drop hedges like "I think" and "it depends". If you don't know, say so in one line. - Give one recommendation, not a menu, unless asked for options. - Push back when they are wrong, and say why. - No openers, no recap of what they just said, no closing offers.

Every style in our 43-file pack sets keep-coding-instructions: true automatically. You can also set "outputStyle": "AgentTune INTJ" directly in .claude/settings.local.json.

The 43-style pack.

One output style per tuning. Each name links to the type's page, which shows the rules in plain English and a before-and-after. File is the download. The install command is the one at the top of this page with the file name swapped. A machine-readable list is at /output-styles/index.json.

Don't know your type? The free MBTI test takes about five minutes. Four other instruments are at /tests/ if MBTI is not your frame.

CLAUDE.md: right for the project, wrong for you.

CLAUDE.md still matters. It is just answering a different question. The docs give the load order: a managed policy file, then ~/.claude/CLAUDE.md, then ./CLAUDE.md or ./.claude/CLAUDE.md, then ./CLAUDE.local.md. The files are concatenated, none overrides another, and the docs suggest keeping each under 200 lines.

Three reasons your personality does not belong in the project's CLAUDE.md:

  • It is shared. The repo's CLAUDE.md is your team's file. "Talk to me like an ENFP" is not a team convention.
  • It is weaker. It arrives as a message, not as part of the system prompt.
  • It competes. Every line about your temperament is a line not spent on how to run the tests.

If you want it in a CLAUDE.md anyway, use ~/.claude/CLAUDE.md or CLAUDE.local.md, which are yours alone, and keep it to a few lines. /memory opens the files for editing, and /context shows what actually loaded. For what belongs in the project file, see CLAUDE.md examples.

Flags and agents: for one-offs and full replacements.

--append-system-prompt and --append-system-prompt-file add text to the system prompt and remove nothing. They work in interactive and non-interactive mode. Good for a script, or for trying a tuning once:

claude --append-system-prompt-file ~/.claude/output-styles/agenttune-mbti-intj.md

--system-prompt and --system-prompt-file replace the whole system prompt. That is almost never what you want for a personality. One catch from the docs: the prompt is recorded at a conversation's first request, so changing these flags on --resume or --continue only takes effect after compaction or in a new conversation.

claude --agent <name>, or "agent": "<name>" in .claude/settings.json, runs the entire session as one of your subagents. Its file body becomes the system prompt, replacing the default the way --system-prompt does. CLAUDE.md still loads. This is how you build a different character entirely. It is a bigger hammer than a personality needs.

For a team, a plugin can ship output styles in an output-styles/ folder at its root.

What a personality file should not touch.

Keep the two layers apart. The personality layer says how to talk to you: what to lead with, how to disagree, when to stop asking questions. The engineering layer says how to build: conventions, tests, what never to commit. When they blur you get a style that says "be decisive" being read as "skip the tests".

The line we put at the top of every file in the pack:

These rules change how you talk: what you lead with, how you frame decisions, how you disagree, when you stop asking questions. They do not change how you engineer.

The same separation applies to Cursor rules, AGENTS.md and Copilot instructions. That is covered in the layer your AGENTS.md is missing.

Questions people ask.

Does Claude Code have a personality setting?

Yes. It is called an output style. Claude Code ships five built-in styles (Default, Proactive, Concise, Explanatory and Learning), and you can add your own as Markdown files in ~/.claude/output-styles/. Switch with /output-style or under /config.

What is the difference between an output style and CLAUDE.md?

An output style changes the default instructions Claude Code works from and is sent on every turn. CLAUDE.md arrives as a message after the system prompt, and the docs say compliance is not guaranteed. Use an output style for role and tone, and CLAUDE.md for project conventions, commands and architecture.

Why did my custom output style make Claude Code worse at coding?

Custom styles drop Claude Code's built-in software-engineering instructions unless the file sets keep-coding-instructions: true. The default is false. Add that line to the front-matter and restart Claude Code.

Is /output-style deprecated?

It was deprecated in March 2026 and brought back in Claude Code 2.1.269 on September 11, 2026, according to the changelog. On older versions, set the style under /config, or put an outputStyle key in a settings file.

Do output styles apply to subagents?

A style reaches the main conversation and its forks. Other subagents do not receive it, and they do not get Claude Code's default system prompt either. A subagent's own file body is its system prompt.

Can I share an output style with my team?

Yes. Commit it to .claude/output-styles/ in the repo, or ship it in a plugin's output-styles folder. A personality style is usually personal, though, so most people keep it in ~/.claude/output-styles/.

Where do custom output styles live?

In ~/.claude/output-styles/ for every project, or .claude/output-styles/ inside one project. The nearest one wins. Restart Claude Code after adding or editing a file.

What changed.

  • Removed duplicate updated key and sharpened search title for /output-style and CLAUDE.md.
  • First published, with the 43-style pack. Checked against Claude Code 2.1.278.

Sources.

Keep going.