- The AI Stack for devs
- Posts
- Mastering the latest Claude Code commands
Mastering the latest Claude Code commands
Guide to background processes, MCP configs, custom status lines, and output styles

Before you jump in, here’s something you’ll love.
I’ve put together a curated list of MCP servers and MCP registries to support your development workflows. When you subscribe to the newsletter, you’ll get instant access to this resource in your welcome email.
Bonus: I’m also working on a collection of free educational resources for building AI agents at every skill level. Coming soon for subscribers. Stay tuned!

Anthropic is cooking with Claude Code. They’re dominating every competitor in the CLI coding agent space, releasing a flood of powerful new features every week. Since I last covered the advanced Claude Code commands, they have outdone themselves. Today, we're diving into the latest commands and how to leverage them seamlessly in your daily workflows.
1. Background Commands
What it does:
Keeps long-running tasks like dev servers, build processes or test suites running independently without blocking your coding session. Claude monitors their output in real-time, spotting errors and offering fixes as they occur.
Why it’s useful:
You can maintain uninterrupted AI assistance while your environment stays live and responsive.
How to use:
- After typing your command (e.g. npm run dev), press Enter to run the bash command.
- Then press Ctrl + B to push it to the background.
- Press K to kill any background process you no longer need.
- Use /bashes to get the status of the background jobs

/bashes output
2. MCP with Multiple Configurations
What it does
Enables you to add and manage MCP servers separately by scope local, project shared, or user wide and load multiple configuration files as needed.
Why it’s useful:
Keeps your sessions lightweight, organized and focused by avoiding loading unnecessary MCP servers. Perfect for managing different environments or permissions. Instead of one massive JSON, you can load only the configs you need.
How to use:
// github_read.json
{
"mcpServers": {
"github-read": {
"url": "https://api.githubcopilot.com/mcp/",
"authorization_token": "GITHUB_READ_ONLY_TOKEN"
}
}
}
// github_write.json
{
"mcpServers": {
"github-write": {
"url": "https://api.githubcopilot.com/mcp/",
"authorization_token": "GITHUB_WRITE_TOKEN"
}
}
}
Loading both configs together in Claude Code, or whichever is required for the session.
claude --mcp-config github_read.json github_write.json
3. Custom Status Line
What it does:
Allows to put critical development context front and center in your terminal, including directory, Git branch status, active AI model and token usage metrics.
Why it’s useful:
Keeps you constantly aware of your current workspace state and token spend without interrupting your flow or switching windows.
How to use
- Generate a default status line config with claude status line
.This creates a config automatically styled for Bash or Zsh.
- Insert this config into your settings.json
file.
- For cleaner management, replace the inline config with a script call.

my current statusLine
My statusLine above displays:
- Current working directory
- Active Git branch with change indicators
- Active Claude model (Sonnet, Opus, etc.)
- Progress bar for current block’s remaining time
- Token and dollar usage metrics
- Burn rate tracking
4. Custom Output Styles
Claude Code can now adapt its response style to fit your specific workflow needs—whether you want concise answers, detailed explanations.
How to use:
- To switch output style interactively or directly, run:
/output-style explanatory
To create a new custom style, run:
/output-style:new I want an output style that is concise, test-driven, and no fluff
Claude will guide you through defining this style.
Example style file - myStyle.md stored locally at .claude/output-styles
---
name: My Custom Style
description: Concise and focused responses with minimal explanation
---
# Custom Style Instructions
You are an interactive CLI tool that helps users with software engineering tasks.
## Specific Behaviors
- Provide brief, actionable answers
- Use bullet points for lists
- Include essential code snippets with minimal comments

/output-style

Start learning AI in 2025
Keeping up with AI is hard – we get it!
That’s why over 1M professionals read Superhuman AI to stay ahead.
Get daily AI news, tools, and tutorials
Learn new AI skills you can use at work in 3 mins a day
Become 10X more productive

If you’re not a subscriber, here’s what you missed this month
Subscribe to get access to such posts every week in your email.

👀 Whats shipping (shipped) this week?
OpenAI debuts ChatGPT Go in India with upgraded features at a budget price.
Multiple Gemini CLI releases this week added better IDE integration, accessibility, emoji support, bug fixes and enhanced performance.

⭐️ Trending open source repos
ccpm - Claude Code PM, spec driven workflow
ccusage - Handy tool for monitoring claude code usage
context-engineering-intro - A comprehensive template for getting started with Context Engineering

🤓 Case Study
Small language models (SLMs) are now powerful, cost effective and flexible enough for most agentic AI tasks. Nvidea’s recent research paper

My Recommendations
Techpresso gives you a daily rundown of what's happening in tech and read by 300,000+ professionals.
The Deep View The go to daily newsletter for 250k+ founders and knowledge workers who want to stay up to date with artificial intelligence.
Looking for more such updates in your inbox? Discover other newsletters that our audience loves to read here
