{"slug": "claude-has-a-concise-output-style", "title": "Claude has a \"Concise\" output style", "summary": "Anthropic's Claude Code introduced a 'Concise' output style that leads with results and skips preamble, requiring Claude Code v2.1.237 or later. The style is one of four built-in options, alongside Proactive, Explanatory, and Learning, and can be selected via the /config command or by setting the outputStyle field in settings files.", "body_md": "[CLAUDE.md](/docs/en/memory)instead.\n\n## Built-in output styles\n\nClaude Code’s**Default** output style is the existing system prompt, designed to help you complete software engineering tasks efficiently. There are four additional built-in output styles:\n\n-\n**Proactive**: Claude executes immediately, makes reasonable assumptions instead of pausing for routine decisions, and prefers action over planning. This is stronger autonomous-execution guidance than[auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)applies, and it works without changing your permission mode, so your permission mode still decides what runs without asking you. -\n**Concise**: Claude leads with the result, skips preamble and narration, and keeps responses short by default, while doing the engineering work as thoroughly as in the Default style. When you ask for an explanation or more detail, Claude answers in full. Claude always keeps the complete content of error reports, security warnings, and confirmations for destructive actions. Requires Claude Code v2.1.237 or later. -\n**Explanatory**: Provides educational “Insights” in between helping you complete software engineering tasks. Helps you understand implementation choices and codebase patterns. -\n**Learning**: Collaborative, learn-by-doing mode where Claude will not only share “Insights” while coding, but also ask you to contribute small, strategic pieces of code yourself. Claude Code will add`TODO(human)`\n\nmarkers in your code for you to implement.\n\n## Change your output style\n\nPick a style in one of these ways:**Terminal**: run`/config`\n\nand select**Output style** to pick a style from a menu. Claude Code saves your selection to`.claude/settings.local.json`\n\nat the[local project level](/docs/en/settings).**Desktop app**: set the`outputStyle`\n\nfield in a settings file, for example`.claude/settings.local.json`\n\n, the file the terminal menu writes. When you run`/config`\n\nthere, Claude Code[opens](/docs/en/desktop#what%E2%80%99s-not-available-in-desktop)rather than a menu.**Settings > Claude Code**\n\nThe standalone\n\n`/output-style`\n\ncommand was deprecated in v2.1.73 and removed in v2.1.91. Use `/config`\n\nor edit the `outputStyle`\n\nsetting directly.`outputStyle`\n\nfield directly in a settings file:\n`/clear`\n\nor a new session. See [How Claude Code uses prompt caching](/docs/en/prompt-caching#changing-output-style)for what an output style change does to the cache.\n\n## Create a custom output style\n\nA custom output style is a Markdown file: frontmatter for metadata, then the instructions to add to the system prompt.1\n\nCreate a Markdown file\n\nSave it at one of three levels. The file name becomes the style name unless you set\n\n`name`\n\nin the frontmatter.- User:\n`~/.claude/output-styles`\n\n- Project:\n`.claude/output-styles`\n\n- Managed policy:\n`.claude/output-styles`\n\ninside the[managed settings directory](/docs/en/settings#settings-files)\n\n`.claude/output-styles/`\n\nbetween the working directory and the repository root. When more than one of these nested directories defines a style with the same name, Claude Code uses the one closest to the working directory.2\n\nAdd frontmatter and instructions\n\nDecide whether to keep Claude Code’s software engineering instructions. Set\n\n`keep-coding-instructions: true`\n\nif you’re changing how Claude communicates but still want it coding the same way. Leave it out if Claude won’t be doing software engineering.This example leads every explanation with a diagram while keeping Claude’s coding behavior:3\n\nSwitch to your style\n\nRun\n\n`/config`\n\nin the terminal and select your style under **Output style**, or set`outputStyle`\n\nin a settings file to the style’s name. It takes effect after `/clear`\n\nor the next time you start a session.[Plugins](/docs/en/plugins-reference)can also ship output styles in an\n\n`output-styles/`\n\ndirectory.\n### Frontmatter\n\nOutput style files support these frontmatter fields:## How output styles work\n\nOutput styles directly modify Claude Code’s system prompt.- Claude Code adds each output style’s custom instructions to the end of the system prompt.\n- All output styles trigger reminders for Claude to adhere to the output style instructions during the conversation.\n- Custom output styles leave out Claude Code’s built-in software engineering instructions, such as how to scope changes, write comments, and verify work, unless\n`keep-coding-instructions`\n\nis set to`true`\n\n.\n\n[subagent runs its own system prompt](/docs/en/sub-agents#what-loads-at-startup), so styles don’t change how subagents respond. A\n\n[fork](/docs/en/sub-agents#fork-the-current-conversation)is the exception, because it inherits the parent’s full system prompt. Token usage depends on the style. Adding instructions to the system prompt increases input tokens, though prompt caching reduces this cost after the first request in a session. The built-in Explanatory and Learning styles produce longer responses than Default by design, which increases output tokens, and the Concise style does the opposite by instructing Claude to keep responses short by default. For custom styles, output token usage depends on what your instructions tell Claude to produce.\n\n## Comparisons to related features\n\nSeveral features customize how Claude Code behaves. Output styles modify the system prompt directly and apply to every response. The others add instructions without changing the default system prompt, or scope them to a specific task.## Related resources\n\n[Settings](/docs/en/settings): where the`outputStyle`\n\nfield lives and how settings precedence works[Permission modes](/docs/en/permission-modes): how the Proactive style compares to auto mode[Plugins](/docs/en/plugins): package and distribute output styles alongside skills, hooks, and agents[Debug your configuration](/docs/en/debug-your-config): diagnose why an output style isn’t taking effect", "url": "https://wpnews.pro/news/claude-has-a-concise-output-style", "canonical_source": "https://code.claude.com/docs/en/output-styles", "published_at": "2026-08-21 19:15:26+00:00", "updated_at": "2026-08-21 19:44:54.717081+00:00", "lang": "en", "topics": ["developer-tools", "ai-tools", "large-language-models"], "entities": ["Anthropic", "Claude Code"], "alternates": {"html": "https://wpnews.pro/news/claude-has-a-concise-output-style", "markdown": "https://wpnews.pro/news/claude-has-a-concise-output-style.md", "text": "https://wpnews.pro/news/claude-has-a-concise-output-style.txt", "jsonld": "https://wpnews.pro/news/claude-has-a-concise-output-style.jsonld"}}