Claude Code /status: Your Session at a Glance
Table of Contents
- What is /status
- How to Use It
- Basic Usage
- What It Tells You
- Account Information
- Current Model
- Working Directory
- Git Status
- Context Usage
- Tools and MCP Status
- Who Should Use /status
- Multi-Project Developers
- Claude Code Newcomers
- People Debugging Environment Issues
- Practical Tips
- Tip 1: Glance at /status Before Starting a New Task
- Tip 2: Pair with /compact for Context Management
- Tip 3: Use /status to Verify Configuration
- Tip 4: First Step in Troubleshooting
- /status vs /config vs /context
- Final Thoughts
What is /status
When using Claude Code, you might run into situations like:
- Forgetting which model you’re currently using — Opus or Sonnet?
- Not sure which Git branch you’re working on
- Wanting to know whether your account is API or subscription, without digging through settings
- After a long conversation, wondering how much context space is left
This information is scattered across different places. Having to check each one separately is annoying.
This is where the /status command comes in.
/status is a built-in Claude Code command that displays the complete status of your current session. Model, account, working directory, Git branch, context usage — all the session metadata you care about, presented in one command.
In short: a dashboard that shows Claude Code’s current “runtime state.”
How to Use It
Basic Usage
In Claude Code’s interactive mode, type:
/status
That’s it. Claude Code outputs a structured status summary covering all key information about your current session.
No arguments, no options. Type it and see.
What It Tells You
Account Information
/status first tells you about your account type and authentication method:
- Account type — whether you’re logged in with an API Key or OAuth (subscription account)
- Plan — if you’re a subscriber, it shows whether you’re on Pro or Max
Why does this matter? Because your account type directly determines your billing model and usage limits. API users pay per token; subscribers use quota. Different account types call for different optimization strategies.
Current Model
Shows the model you’re currently using:
- Claude Opus 4.6
- Claude Sonnet 4.6
- Claude Haiku 4.5
If you’ve specified a default model in CLAUDE.md or your settings but aren’t sure it took effect, /status gives you the answer instantly.
Working Directory
Shows Claude Code’s current working directory path.
This seems mundane, but it’s useful when:
- You have multiple terminal windows open with Claude Code in different projects and want to confirm “where am I right now”
- You’ve used
/add-dirto add extra directories and want to verify the working scope - In a monorepo, you need to confirm whether Claude Code is at the root or inside a specific package
Git Status
If the current directory is a Git repository, /status shows:
- Branch — which branch you’re on
- Dirty — whether there are uncommitted changes
You don’t need to exit Claude Code to run git status — one /status confirms your version control state. This is especially helpful during feature development involving multiple branches, quickly telling you “which line am I on.”
Context Usage
Shows how much of the context window has been used — how much is consumed and how much remains.
This is one of the most practical pieces of information in /status. The context window is Claude Code’s most critical resource, and knowing its usage helps you:
- Decide whether you need to
/compactthe conversation - Estimate how much more content can be processed
- Proactively clean up before the context fills up
Tools and MCP Status
/status also shows the number of available tools and information about connected MCP (Model Context Protocol) servers.
If you’ve configured MCP tools but aren’t sure whether they connected successfully, /status lets you verify quickly — no need to dig through config files or try calling tools to test.
Who Should Use /status
Multi-Project Developers
If you use Claude Code across multiple projects, /status helps you quickly confirm your current session context — which project, which branch, which model. Avoid developing on the wrong branch or wasting quota with Opus when you didn’t need to.
Claude Code Newcomers
If you’re just getting started with Claude Code, /status is the most direct way to understand “what’s happening right now.” No need to remember where each setting is configured — one command shows the full picture.
People Debugging Environment Issues
When Claude Code isn’t behaving as expected, the first step is often checking the environment:
- Is the model correct?
- Is the working directory correct?
- Is the MCP connection healthy?
- Is the context nearly full?
/status can rule out most environmental factors in 5 seconds.
Practical Tips
Tip 1: Glance at /status Before Starting a New Task
You don’t need to check it with every message, but spending 2 seconds on /status before starting an important task is a good habit. Confirm that the model, branch, and context are all as expected — avoid getting halfway through only to discover “I was on the wrong branch.”
Tip 2: Pair with /compact for Context Management
/status tells you how much context is used; /compact helps you free up space. Use them together:
/statusto check context usage- If usage is high,
/compactto compress /statusagain to confirm space was freed
This is much more proactive than waiting for Claude Code’s automatic compression, and yields better results.
Tip 3: Use /status to Verify Configuration
After changing model settings in CLAUDE.md, adding MCP tools, or adjusting permission settings, use /status to quickly verify they took effect. It’s more efficient and reliable than “trying something to see if it works.”
Tip 4: First Step in Troubleshooting
Claude Code acting weird? Don’t rush to restart the session. Check /status first:
- The model might not be what you think it is
- You might have accidentally switched to the wrong branch
- An MCP tool might have disconnected
- The context might be nearly full
More often than not, the root cause is the environment, not the model. /status helps you pinpoint it quickly.
/status vs /config vs /context
All three commands relate to “understanding the current state,” but they focus on different aspects:
| /status | /config | /context | |
|---|---|---|---|
| Focus | Overall session status overview | Configuration details and settings | Detailed context usage analysis |
| Depth | Broad and shallow — wide coverage | Deep into config specifics | Deep into context specifics |
| Primary use | Quick confirmation that “everything’s fine” | Reviewing and adjusting settings | Optimizing context management |
| Analogy | Car dashboard | Car settings menu | Detailed fuel report |
My recommendations:
- Want a quick overview of the current session →
/status - Want to view or modify specific configurations →
/config - Want to deeply analyze context usage and optimize →
/context
Final Thoughts
/status is one of the most “boring” commands in Claude Code — it doesn’t write code, fix bugs, or perform any actual operations. It does one thing: tells you the current state.
But it’s precisely this “boring” nature that makes it the most reliable diagnostic tool.
When something goes wrong, many people’s first instinct is to “start over” — open a new session, re-describe requirements, re-run everything. But most of the time, the problem isn’t the conversation itself — it’s the environment: wrong model, wrong branch, full context, disconnected tools.
Diagnose first, act second. This is the fundamental principle of any troubleshooting. /status is Claude Code’s “diagnostic command” — before you decide to start over, spend 2 seconds checking whether the environment is the issue.
Next time Claude Code isn’t performing as expected, resist the urge to complain that “the model got dumber.” Type /status — the answer might be right there on the dashboard.
Related Articles
Claude Code Agent Loop: Dissecting the Heart of an AI Coding Assistant
How does Claude Code understand your requests, invoke tools, and self-recover step by step? A source-code deep dive into the Agent Loop's core architecture — streaming responses, parallel tool execution, auto-compaction, and error recovery.
Claude Code settings.json Explained (1): Where Config Files Live and Who Wins
A complete guide to Claude Code's configuration file system — five config sources, their file paths, priority rules, array merging vs value overriding, and enterprise managed settings delivery.
Claude Code settings.json Deep Dive (Part 2): The Permissions System
A thorough breakdown of Claude Code's permissions configuration — allow/deny/ask rule arrays, wildcard syntax, MCP tool permissions, defaultMode options, and additionalDirectories.
Claude Code settings.json Deep Dive (Part 3): The Hooks System
A thorough breakdown of Claude Code's hooks configuration — four hook types, core events (PreToolUse/PostToolUse/Stop/Notification), stdin/stdout protocol, exit code semantics, and practical examples.
Claude Code settings.json Deep Dive (4): env, Models, Auth, and Other Useful Fields
A comprehensive guide to the remaining settings.json fields in Claude Code — env variable injection, model configuration, authentication helpers, Git attribution, session cleanup, language and UI, thinking depth, auto-updates, memory system, and more.