Claude Code Statusline: Show Live Session Info in Your Prompt
Engineering
Claude Code Statusline: Show Live Session Info in Your Prompt
Claude Code can render a custom status line — a persistent strip under the prompt showing whatever you want: the model, the working directory, the git branch, the running cost. It's a small touch that keeps you oriented, especially across several sessions. Here's how to wire one up.
How it works
You point Claude Code at a command. On each update it pipes the session context to that command as JSON on stdin, and the command prints one line to stdout — that line becomes your status line. Configure it in settings.json:
{
"statusLine": {
"type": "command",
"command": "~/.claude/statusline.sh"
}
}
A copy-paste status line
A script that shows the model and the current directory's basename:
#!/bin/bash
INPUT=$(cat)
MODEL=$(echo "$INPUT" | jq -r '.model.display_name')
DIR=$(echo "$INPUT" | jq -r '.workspace.current_dir' | xargs basename)
echo "[$MODEL] $DIR"
Make it executable (chmod +x), point settings.json at it, and you'll see something like [Opus] my-project under every prompt. Add the git branch, the running cost, an emoji — it's just a shell script printing a line.
What you get on stdin
The JSON includes the model, the workspace directories, the session id, and cost/usage info — so you can surface exactly what you care about: which model am I on, how much has this session cost, which repo is this. Pull the fields you want with jq.
One status line, one session
A status line is perfect for the session you're looking at. But it only describes the one terminal in front of you — and the whole point of agentic coding is running several at once. For the fleet, you want a status line for all of them at a glance.
That's Mwah: every live Claude Code session as a little robot on your desktop, each showing its own name, project, and live activity — a status line per agent, floating, always visible. Feed the ones that nailed it; retire the stuck ones.
Related: Run multiple Claude Code sessions · Claude Code hooks: the complete guide
Keep reading
View all dispatches →Shopify AI Agent Tools: What Your Agents Can Actually Do in Your Store
Clearly now ships Shopify store tools your AI agents can call — browse the catalog, read orders, roll up revenue, edit products, and attach generated images — over MCP and the beehaven CLI, with a dry-run preview on every write. Here are the tools, with example commands.
How to Manage Your Shopify Store with AI Agents
AI agents can now do the work of running a Shopify store — writing descriptions, generating product images, answering customers, updating the catalog. Here's how agent-run commerce works, and how to set it up.
Claude Code for Shopify: Run Your Store from Your Terminal
If you already run your codebase with Claude Code, the same agents can run your Shopify store — edit the catalog, generate product images, answer customers — with a connector and the right guardrails. Here's the setup.