@akshay_pachaar: How to setup your Claude code project? TL;DR Most developers skip the setup and just start prompting. That's the mistak…
Summary
A guide on setting up a Claude Code project using the .claude/ folder structure, including configuration for CLAUDE.md, rules, commands, skills, agents, and permissions.
View Cached Full Text
Cached at: 07/04/26, 02:50 PM
How to setup your Claude code project?
TL;DR
Most developers skip the setup and just start prompting. That’s the mistake.
A proper Claude Code project lives inside a .claude/ folder. Start with CLAUDE.md as Claude’s instruction manual. Split it into a rules/ folder as it grows. Add commands/ for repeatable workflows, skills/ for context-triggered automation, and agents/ for isolated subagents. Lock down permissions in settings.json.
There are two .claude/ folders: one committed with your repo, one global at ~/.claude/ for personal preferences and auto-memory across projects.
The .claude/ folder is infrastructure. Treat it like one.
The article below is something I wrote three months ago, and it is still very much relevant.
It is a complete guide to CLAUDE.md, custom commands, skills, agents, and permissions, along with how to set them up properly.
Similar Articles
@humzaakhalid: Most developers are using Claude Code wrong (100%) Claude Code fixes it in 90 seconds flat. Here is exactly how: 1. Get…
A detailed guide on using Claude Code effectively, including setup, CLAUDE.md configuration, four-layer architecture, hooks, and daily workflow patterns.
@vincemask: Many people use Claude Code but only have one CLAUDE.md in their project. A truly maintainable configuration is typically broken down into layers: 1. CLAUDE.md: Project-level context and conventions 2. settings.json: Permissions, model, and hooks 3. rules/: Split rules by topic 4. commands/: Settle repeatable workflows 5. skills/: Dynamically load based on task context 6. agents/: Define dedicated sub-agents 7. hooks/: Auto-validate before and after tool calls. When you have a lot of configurations, don't cram them all into one file. The clearer the layering, the more stable Claude Code becomes, and the easier it is to maintain and reuse. Here is a project structure diagram for your reference.
Recommended layered approach for Claude Code project configuration, splitting config into CLAUDE.md, settings.json, rules/, commands/, skills/, agents/, hooks/, etc., to improve maintainability and reusability.
@tom_doerr: Practical guide to Claude Code skills, hooks, and agents https://github.com/wesammustafa/Claude-Code-Everything-You-Nee…
A comprehensive practical guide to Claude Code covering setup, skills, hooks, MCP, agent teams, and prompt engineering for developers.
Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs
A comprehensive guide to using Claude Code as a programmable agent with memory, custom commands, and project configuration for advanced developers.
luongnv89/claude-howto
A comprehensive, structured guide for mastering Claude Code features, including slash commands, hooks, skills, MCP servers, and subagents, with visual tutorials, copy-paste templates, and a progressive learning path from beginner to power user.