Skip to content

quick-start.md

Latest commit

 

History

History
91 lines (61 loc) · 3.17 KB

quick-start.md

File metadata and controls

91 lines (61 loc) · 3.17 KB
title Quick Start
description Get contextcrawler running in 5 minutes and see your first token savings
sidebar
order
2

Quick Start

This guide walks you through your first contextcrawler commands after installation.

Prerequisites

contextcrawler is installed and verified:

contextcrawler --version   # contextcrawler x.y.z
contextcrawler gain        # shows token savings dashboard

If not, see Installation.

Step 1: Initialize for your AI assistant

# For Claude Code (global — applies to all projects)
contextcrawler init --global

# For a single project only
cd /your/project && contextcrawler init

This installs the hook that automatically rewrites commands. Restart your AI assistant after this step.

Preview without writing: --dry-run

To see exactly what init would change before it touches anything, add --dry-run:

contextcrawler init --global --dry-run

Every would-be file create/update/patch is printed with a [dry-run] would ... prefix, then a [dry-run] Nothing written. footer. Nothing on disk is modified, no settings.json is patched, and the telemetry consent prompt is skipped. Combine with -v to also print the full content contextcrawler would write:

contextcrawler init --global --dry-run -v

--dry-run works for every init flavour (--agent cursor, --gemini, --codex, --copilot, --uninstall, ...). It cannot be combined with --show.

Step 2: Use your tools normally

Once the hook is installed, nothing changes in how you work. Your AI assistant runs commands as usual — the hook intercepts them transparently and rewrites them before execution.

For example, when Claude Code runs cargo test, the hook rewrites it to contextcrawler cargo test before it executes. The LLM receives filtered output with only the failures — not 500 lines of passing tests. You never see or type contextcrawler.

contextcrawler covers all major ecosystems — Git, Cargo/Rust, JavaScript, Python, Go, Ruby, .NET, Docker/Kubernetes, and more. See What contextcrawler optimises for the full list.

Step 3: Check your savings

After a few commands, see how much was saved:

contextcrawler gain
ContextCrawler Token Savings (Global Scope)
════════════════════════════════════════════════════════════

Total commands:    12
Input tokens:      45.2K
Output tokens:     4.9K
Tokens saved:      40.3K (89.2%)

Step 4: Unsupported commands

Commands contextcrawler doesn't recognise run through passthrough — output is unchanged, usage is tracked:

contextcrawler proxy make install

Next steps