starship

starship is a command for Claude Code from martinemde/starship-claude. It costs 12 tokens per session (2,088 once invoked), scanned D, original, MIT.

An interactive setup wizard for adding a Starship-based status line to Claude Code. Starship is a tool that customizes the command prompt in shells such as bash, zsh, and fish.

In plain words
What is it for?
Use it to install or configure the required Starship tool and set up the starship-claude status line. It is intended for developers who use Claude Code in a terminal.
Why use it?
It guides you through checking for Starship and configuring a prompt that can show project, context usage, model, and Git status. This keeps useful session information visible below the prompt.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the starship-claude plugin — 1 command shipped together

Good fit Use it to install or configure the required Starship tool and set up the starship-claude status line. It is intended for developers who use Claude Code in a terminal.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add martinemde/starship-claude
Claude Code
/plugin install starship-claude

Made for: Claude Code.

Or install starship-claude, the plugin that ships this one along with the rest of its 1 command.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for starship

README.md
[![agentmods](https://agentmods.dev/badge/commands/martinemde/starship-claude/starship/github.svg)](https://agentmods.dev/commands/martinemde/starship-claude/starship)
Your own site
<a href="https://agentmods.dev/commands/martinemde/starship-claude/starship"><img src="https://agentmods.dev/badge/commands/martinemde/starship-claude/starship/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for starship

Your own site · 80×15
<a href="https://agentmods.dev/commands/martinemde/starship-claude/starship"><img src="https://agentmods.dev/badge/commands/martinemde/starship-claude/starship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.02088
Opus 5 $0.00006 $0.01044
Sonnet 5 $0.00002 $0.00418
Haiku 4.5 $0.00001 $0.00209

Measured 11d ago against content hash bd68d74e3e7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade D, and why

starship scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sS https://starship.rs/install.sh | sh

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Read `~/.claude/settings.json` if it exists. Add or update the statusLine configuration:

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS https://starship.rs/install.sh | sh
plugin/commands/starship.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Starship-Claude Setup Wizard

You are running an interactive setup wizard to configure the starship-claude statusline for Claude Code. Follow these steps in order, using AskUserQuestion for each decision point.

Step 1: Check for Starship

Run this command to check if starship is installed:

command -v starship >/dev/null 2>&1 && echo "installed" || echo "not_installed"

If starship is NOT installed:

Display this start message:

Welcome to starship-claude setup! 🚀

With Claude's help, this will guide you through configuring a statusline to display useful information: project, context usage, model, and git status, right below your prompt.

Why Starship? Starship is a powerful and configurable prompt for shells like bash, zsh, and fish. I created starship-claude because I wanted the same thing in claude. Starship-claude doesn't have one built in style, you're free to create your own style to match your preferences.

You can read more about Starship here: https://starship.rs

Before we continue, starship-claude requires **Starship** (no surprise there). We need to install to continue. If you don't want to use Homebrew, you'll need to install yourself:

```bash
curl -sS https://starship.rs/install.sh | sh
```

Then ask:

  • Question: "Install starship?"
  • Header: "Starship"
  • Options:
    • "brew install starship" → Run: brew install starship
    • "I installed it myself" → Start over from Step 1 and re-check starship
    • "Exit wizard" → Tell them to visit https://starship.rs when they're ready and exit the wizard

If starship IS installed

Tell the user: "Looks like you already have starship installed, great!"

Then ask:

  • Question: "Ready to configure your Claude statusline?"
  • Header: "Ready"
  • Options:
    • "Launch it! 🚀" → Continue to the next step

Step 2: Check Existing Configuration

Check if configuration already exists:

test -f ~/.claude/starship.toml && echo "exists" || echo "not_found"

Read the full file on GitHub · 274 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 274 lines · 12 tokens per session scan D bd68d74e3e7c

Subscribe to this mod's changes

starship is a command published in the GitHub repository martinemde/starship-claude (149 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 2,088 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.