$git clone https://github.com/wesammustafa/Claude-Code-Everything-You-Need-to-KnowFrom first prompt to agent teams — one guide.
| 1 | # Claude Code: Everything You Need to Know <img src="Images/claude-jumping.svg" width="44" height="40" alt="Animated Claude" align="right" /> |
| 2 | |
| 3 | **From first prompt to agent teams — one guide.** |
| 4 | |
| 5 | [](https://github.com/hesreallyhim/awesome-claude-code) |
| 6 | [](https://github.com/wesammustafa/Claude-Code-Everything-You-Need-to-Know/stargazers) |
| 7 | [](https://github.com/wesammustafa/Claude-Code-Everything-You-Need-to-Know/commits/main) |
| 8 | [](LICENSE) |
| 9 |  |
| 10 | |
| 11 | A practical guide to Claude Code — from your first prompt to multi-agent automation, hooks, MCP, and team workflows. Built around clear mental models and real examples, not marketing. |
| 12 | |
| 13 | ```bash |
| 14 | npm install -g @anthropic-ai/claude-code |
| 15 | ``` |
| 16 | |
| 17 | **Who this is for:** Developers using (or about to use) Claude Code. Beginners get a guided path; power users get depth on Skills, Hooks, MCP, and Agent Teams. |
| 18 | |
| 19 | --- |
| 20 | |
| 21 | ## 🧭 Choose your path |
| 22 | |
| 23 | | You are… | Start here | Time | |
| 24 | |---|---|---| |
| 25 | | 🚀 **New to Claude Code** | [Setup](#claude-code-setup) → [Prompt Engineering](#prompt-engineering-deep-dive) → [Your First Skill](#claude-skills) | ~15 min | |
| 26 | | ⚡ **Already using it, want depth** | [Skills](#claude-skills) · [Hooks](#hooks) · [MCP](#model-context-protocol-mcp) | ~30 min each | |
| 27 | | 🧠 **Building teams or automation** | [Agent Teams](#agent-teams-experimental) · [Workflows & automation](#beyond-one-terminal--the-2026-automation-surface) · [BMAD](#the-bmad-method--ai-agent-framework) | varies | |
| 28 | |
| 29 | --- |
| 30 | |
| 31 | ## 🧠 When to use what |
| 32 | |
| 33 | The four extension points in Claude Code, side by side: |
| 34 | |
| 35 | | Tool | Use when… | Skip if… | Lives in | |
| 36 | |---|---|---|---| |
| 37 | | **[Skills](#claude-skills)** *(slash commands)* | You repeat the same prompt or workflow ≥3 times | One-off task | `.claude/commands/*.md` | |
| 38 | | **[Hooks](#hooks)** | You want code to run *automatically* on tool use, session start, etc. | You only want manual triggers | `.claude/settings.json` | |
| 39 | | **[Subagents](#ai-agents)** | A subtask is big enough to need its own isolated context | The task fits in your main session | `.claude/agents/*.md` | |
| 40 | | **[MCP servers](#model-context-protocol-mcp)** | You need Claude to use *external* tools (browsers, DBs, APIs) | All your data is in local files | Configured per project | |
| 41 | |
| 42 | > 💡 These four compose. Most polished workflows combine 2–3. |
| 43 | |
| 44 | --- |
| 45 | |
| 46 | ## 📚 What's inside |
| 47 | |
| 48 | **Fundamentals** — [What is Claude Code?](#what-is-claude-code) · [Setup](#claude-code-setup) · [Prompt Engineering](#prompt-engineering-deep-dive) |
| 49 | |
| 50 | **Workflow extensions** — [Slash Commands](#claude-commands) · [Skills](#claude-skills) · [Hooks](#hooks) |
| 51 | |
| 52 | **Multi-agent & integration** — [Subagents](#ai-agents) · [Agent Teams](#agent-teams-experimental) · [Workflows & automation](#beyond-one-terminal--the-2026-automation-surface) · [MCP](#model-context-protocol-mcp) |
| 53 | |
| 54 | **Productivity & frameworks** — [Effort levels](#effort-levels) · [Fast Mode](#fast-mode) · [Super Claude](#super-claude-framework) · [BMAD Method](#the-bmad-method--ai-agent-framework) |
| 55 | |
| 56 | **Reference** — [Slash Command Cheatsheet](#built-in-slash-commands) · [Effort levels (full guide)](docs/reference/effort-levels.md) · [FAQ](#faq) · [Updates & Deprecations](#updates--deprecations) · [Further Reading](#references) |
| 57 | |
| 58 | <!-- Compatibility anchors for old inbound links --> |
| 59 | <a id="sdlc"></a> |
| 60 | <a id="what-are-llms-and-how-do-they-differ-from-ai-tools-like-claude-code"></a> |
| 61 | |
| 62 | ### What is Claude Code? |
| 63 | |
| 64 | Claude Code is Anthropic's official CLI for working with Claude from your terminal. You point it at a project; it reads t |