Guides.
Beginner · practical · advanced · concept. Step-by-step writings on putting Claude Code to work.
All guides
14 entries · last updated 2026-05-16Getting Started with Claude Code
A beginner walkthrough for first-time Claude Code users. Covers installation across platforms, what you need to start, the first commands to learn, and where Claude Code runs beyond the terminal.
Skill vs Plugin vs MCP — how they differ
A concept guide that explains what Skills, MCPs, and Plugins each are and how they differ. Helps you decide which type to start with when picking your first tools.
Installing Your First Plugin
A step-by-step walkthrough for installing your first Claude Code plugin. Find one in the marketplace, install it, and confirm how to use it afterward.
Writing a Great CLAUDE.md
How to write an effective CLAUDE.md at your project root. Covers where to put it, what to include, and how to keep it tight enough for your token budget.
Using Plan Mode Well
A practical guide to when and how to use Claude's plan mode. Walks through what to review in a plan and how to handle changes mid-flight on high-impact work.
Upgrade Your Terminal with ccstatusline
Walks through customizing the Claude Code status line with ccstatusline — Powerline-style themes, model and token usage, and Git info on a single line.
Getting Started with the Memory Tool
How the Memory tool keeps context between sessions. Covers what gets saved automatically, where it's stored, and how to add or edit memories yourself.
Hidden Claude Code commands you actually want to use
Built-in slash commands that get buried even though they only need a single line to run — /radio, /btw, /teleport, /context, /copy, /loop and more, organized by when you'd reach for them.
Build Your Own Skill
A step-by-step guide to building your own Skill. Covers where files go, how to write the description that triggers it, and reference examples to study.
Automate Workflows with Hooks
How to wire automation into Claude Code with hooks. Covers which events are available, where to configure them, and how to debug when a hook doesn't fire.
Splitting Work with Subagents
How to split work with subagents to keep your main context clean and run tasks in parallel. Covers when subagents help and how to define your own.
Build Your Own MCP Server
How to build an MCP server that connects Claude to external services. Covers transport choices, OAuth handling, and how to wire it into Claude Code.
Agent Teams
How to coordinate multiple Claude Code instances as a team that shares a task list and communicates directly. Covers in-process mode, the iTerm2 + tmux split-pane setup, use cases, and known limitations.
Claude Code `/goal` — running auto-continuation safely
`/goal` sets a completion condition; after every turn a small fast model checks whether it holds and Claude keeps starting new turns until it does. The real lever is how the condition is written — most `/goal` problems are condition problems, not command problems.