Skip to main content
A summary of customization tips shared by Boris Cherny (@bcherny), creator of Claude Code, on February 12, 2026.
Boris highlighted that customizability is one of the things engineers love most about Claude Code — hooks, plugins, LSPs, MCPs, skills, effort levels, custom agents, status lines, output styles, and more.Source: Tweet from February 12, 2026

​
1. Configure Your Terminal

Set up your terminal for the best Claude Code experience:
  • Theme: Run /config to set light/dark mode
  • Notifications: Enable notifications for iTerm2, or use a custom notification hook
  • Newlines: If using Claude Code in an IDE terminal, Apple Terminal, Warp, or Alacritty, run /terminal-setup to enable shift+enter for newlines (so you don’t need to type \)
  • Vim mode: Run /vim
Run /terminal-setup once to configure newline handling for your specific terminal emulator.

​
2. Adjust Effort Level

Run /model to pick your preferred effort level:
  • Low — fewer tokens, faster responses
  • Medium — balanced behavior
  • High — more tokens, more intelligence
Boris’s preference: High for everything.

​
3. Install Plugins, MCPs, and Skills

Plugins let you install LSPs (available for every major language), MCPs, skills, agents, and custom hooks.
Install from the official Anthropic plugin marketplace, or create your own marketplace for your company. Check the settings.json into your codebase to auto-add the marketplaces for your team.
Run /plugin to get started.
See Plugin Discovery for available marketplaces.

​
4. Create Custom Agents

Drop .md files in .claude/agents to create custom agents. Each agent can have:
  • Custom name and color
  • Custom tool set
  • Pre-allowed and pre-disallowed tools
  • Permission mode
  • Model selection
You can set the default agent for the main conversation using the "agent" field in settings.json or the --agent flag.
Run /agents to get started.

​
5. Pre-approve Common Permissions

Claude Code uses a permission system combining prompt injection detection, static analysis, sandboxing, and human oversight.
Out of the box, a small set of safe commands are pre-approved. To pre-approve more, run /permissions and add to the allow and block lists. Check these into your team’s settings.json.
Full wildcard syntax is supported:
  • Bash(bun run *)
  • Edit(/docs/**)

​
6. Enable Sandboxing

Opt into Claude Code’s open source sandbox runtime to improve safety while reducing permission prompts.
Run /sandbox to enable it. Sandboxing runs on your machine and supports both file and network isolation.

​
7. Add a Status Line

Custom status lines show up right below the composer, displaying model, directory, remaining context, cost, and anything else you want to see while you work.
Every team member can have a different status line. Use /statusline to have Claude generate one based on your .bashrc/.zshrc.
Example information displayed:
  • Current model and effort level
  • Working directory
  • Remaining context percentage
  • Session cost
  • Git branch

​
8. Customize Your Keybindings

Every key binding in Claude Code is customizable.
Run /keybindings to re-map any key. Settings live reload so you can see how it feels immediately.

​
9. Set Up Hooks

Hooks let you deterministically hook into Claude’s lifecycle:
  • Automatically route permission requests to Slack or Opus
  • Nudge Claude to keep going when it reaches the end of a turn (you can even kick off an agent or use a prompt to decide whether Claude should keep going)
  • Pre-process or post-process tool calls, e.g., to add your own logging
Ask Claude to add a hook to get started. Hooks are scripts that run outside the agentic loop on specific events.
See Hooks Documentation for available hook events and examples.

​
10. Customize Your Spinner Verbs

Customize your spinner verbs to add or replace the default list with your own verbs.
Check the settings.json into source control to share verbs with your team.
Example configuration: 
{
  "spinnerVerbs": [
    "architecting",
    "refactoring",
    "optimizing",
    "deploying"
  ]
}

​
11. Use Output Styles

Run /config and set an output style to have Claude respond using a different tone or format.
  • Explanatory — recommended when getting familiar with a new codebase, to have Claude explain frameworks and code patterns as it works
  • Learning — to have Claude coach you through making code changes
  • Custom — create custom output styles to adjust Claude’s voice
Use Explanatory mode when onboarding to a new codebase to learn as you work.

​
12. Customize All the Things!

Claude Code works great out of the box, but when you do customize, check your settings.json into git so your team can benefit too.
Configuration is supported at multiple levels:
  • For your codebase
  • For a sub-folder
  • For just yourself (.claude/settings.local.json)
  • Via enterprise-wide policies
With 37 settings and 84 environment variables (use the "env" field in your settings.json to avoid wrapper scripts), there’s a good chance any behavior you want is configurable.

​
Additional Resources

​
More from Boris Cherny

Build docs developers (and LLMs) love

Get started for freeTalk to us