SpyBara
Go Premium

output-styles.md 2025-10-28 18:02 UTC to 2025-10-29 21:02 UTC

119 added, 32 removed.

2025
Fri 31 00:04 Thu 30 18:02 Wed 29 21:02 Tue 28 18:02 Mon 27 18:02 Fri 24 21:01 Thu 23 21:02 Tue 21 00:04 Mon 20 21:02 Fri 17 18:01 Thu 16 18:02 Wed 15 18:02 Mon 13 21:01

Output styles

[DEPRECATED] Adapt Claude Code for uses beyond software engineering

Deprecation timeline

As of November 5, 2025, Claude Code will:

  • Automatically convert user-level output style files (~/.claude/output-styles) to plugins
  • Stop supporting the output styles feature
  • Remove the /output-style command and related functionality

What you need to do:

  • Migrate to plugins before November 5, 2025 for a smoother transition
  • Review the migration guide below to understand your options

Alternative: Use plugins instead

Plugins provide more powerful and flexible ways to customize Claude Code's behavior. The explanatory-output-style plugin recreates the deprecated Explanatory output style functionality.

Example: Explanatory Output Style Plugin

The explanatory-output-style plugin uses a SessionStart hook to inject additional context that encourages Claude to provide educational insights. Here's what it does:

  • Provides educational insights about implementation choices
  • Explains codebase patterns and decisions
  • Balances task completion with learning opportunities

Installing a plugin

To install a plugin like explanatory-output-style:

/plugin marketplace add anthropics/claude-code

/plugin install explanatory-output-style@claude-code-plugins

/exit

/plugin manage explanatory-output-style@claude-code-plugins

1. Press enter when you see claude-code-marketplace
2. Press space when you see explanatory-output-style to toggle enabled
3. Press down to "Apply changes", then press enter
    You should see "Disabled 1 plugin. Restart Claude Code to apply changes."

/exit

For more details on plugins, see the Plugins documentation.

Migration guide

Output styles directly modified Claude Code's system prompt. Here's how to achieve similar effects with hooks and subagents, both available through Claude Code plugins:

Use SessionStart hooks for context injection

If you used output styles to add context at the start of sessions, use SessionStart hooks instead.

The hook's output (stdout) is added to the conversation context. You can also:

  • Run scripts that dynamically generate context
  • Load project-specific information

Use Subagents for different system prompts

If you used output styles to change Claude's behavior for specific tasks, use Subagents instead.

Subagents are specialized AI assistants with:

  • Custom system prompts (must be in a separate context window from main loop)
  • Specific tool access permissions
  • Optional model to use, if not the main loop model

Reference: Original output styles documentation

Output styles allow you to use Claude Code as any type of agent while keeping its core capabilities, such as running local scripts, reading/writing files, and tracking TODOs.

Built-in output styles

Claude Code's Default output style is the existing system prompt, designed to help you complete software engineering tasks efficiently.

There are two additional built-in output styles focused on teaching you the codebase and how Claude operates:

  • Explanatory: Provides educational "Insights" in between helping you complete software engineering tasks. Helps you understand implementation choices and codebase patterns.

  • 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) markers in your code for you to implement.

How output styles work

Output styles directly modify Claude Code's system prompt.

  • Non-default output styles exclude instructions specific to code generation and efficient output normally built into Claude Code (such as responding concisely and verifying code with tests).
  • Instead, these output styles have their own custom instructions added to the system prompt.

Change your output style

You can either:

  • Run /output-style to access the menu and select your output style (this can also be accessed from the /config menu)

  • Run /output-style [style], such as /output-style explanatory, to directly switch to a style

These changes apply to the local project level and are saved in .claude/settings.local.json.

You can also create your own output style Markdown files and save them either at the user level (~/.claude/output-styles) or the project level (.claude/output-styles).

Output Styles vs. CLAUDE.md vs. --append-system-prompt

Output styles completely “turn off” the parts of Claude Code’s default system prompt specific to software engineering. Neither CLAUDE.md nor --append-system-prompt edit Claude Code’s default system prompt. CLAUDE.md adds the contents as a user message following Claude Code’s default system prompt. --append-system-prompt appends the content to the system prompt.

Output Styles vs. Agents

Output styles directly affect the main agent loop and only affect the system prompt. Agents are invoked to handle specific tasks and can include additional settings like the model to use, the tools they have available, and some context about when to use the agent.

Output Styles vs. Custom Slash Commands

You can think of output styles as “stored system prompts” and custom slash commands as “stored prompts”.