# Learn Claude Code by Tenzing

> A free learning path that takes people from complete beginner to professional with Claude Code (Anthropic's agentic coding tool), plus practice quizzes and timed mock exams for the Claude Certified Architect (Foundations) certification and a Claude Developer skills track. Published by Tenzing Digital. Independent; not affiliated with Anthropic.

Key facts:
- 19 lessons across 5 levels: Curious, Getting going, Daily driver, Power user, Pro.
- 120 Architect practice questions across 5 domains: Agentic Architecture & Orchestration (27%), Tool Design & MCP Integration (18%), Claude Code Configuration & Workflows (20%), Prompt Engineering & Structured Output (20%), Context Management & Reliability (15%).
- 100 Claude Code Skills practice questions across 5 domains: Claude Code Foundations & CLI (25%), Configuration & Memory (20%), Extending Claude Code (25%), Automation, CI & Agent SDK (15%), Claude API Fundamentals (15%).
- 90 Associate (Foundations) practice questions across 7 domains: Prompting and Task Execution (14%), Output Evaluation and Validation (21%), Product and Model Selection (12%), Workflow Integration and Solution Design (16%), Configuration and Knowledge Management (12%), Governance, Risk, and Responsible Use (15%), Troubleshooting and Optimization (10%).
- 80 Developer (Foundations) practice questions across 8 domains: Agents and Workflows (14.7%), Applications and Integration (33.1%), Claude Code (3.1%), Eval, Testing, and Debugging (2.6%), Model Selection and Optimization (16.8%), Prompt and Context Engineering (11%), Security and Safety (8.1%), Tools and MCPs (10.6%).
- Free, no account or sign-up.

## Learning path
- [What is Claude Code? Agentic coding explained](https://learn-claude-code.onrender.com/learn/what-is-claude-code/): Claude Code is Anthropic's agentic coding tool: it runs in your terminal (and in IDEs, desktop and web), reads your project, edits files and runs commands to complete tasks you describe in everyday language. Unlike a chatbot that only suggests code, it takes actions for you and checks its own work.
- [Every way to use Claude Code](https://learn-claude-code.onrender.com/learn/ways-to-use-claude-code/): Claude Code is one agent with many front doors. The terminal is the original and most flexible; the VS Code and JetBrains extensions put it beside your editor; the desktop and web apps add cloud sessions you can follow from your phone; GitHub, Slack and headless mode bring it into team workflows; and the Agent SDK lets you build your own agents on the same engine.
- [Install Claude Code and start a session](https://learn-claude-code.onrender.com/learn/install-claude-code-first-session/): Install Claude Code with the official installer script or npm, then type claude inside a project folder and log in with your Claude account or an Anthropic Console API key. Start by asking it to explain the project before asking it to change anything.
- [How to talk to Claude Code: better prompts](https://learn-claude-code.onrender.com/learn/how-to-prompt-claude-code/): The best Claude Code prompts state the goal, the context, the constraints and what "done" looks like. Be specific, point to relevant files, give examples, and ask Claude to plan or ask questions before it builds anything large.
- [How Claude Code works under the hood](https://learn-claude-code.onrender.com/learn/how-claude-code-works/): Claude Code sends your request, your project memory (CLAUDE.md) and a list of tools to a Claude model. The model replies with tool calls (read this file, run that command), Claude Code runs them, subject to your permissions, and feeds the results back. That loop repeats until the task is done. Everything lives in a context window, which is summarised automatically when it fills up.
- [Reading and editing files, plus @ mentions](https://learn-claude-code.onrender.com/learn/reading-editing-files-at-mentions/): Claude Code uses built-in tools to read, search (Grep, Glob) and edit files, showing you a diff before changes land. Type @ followed by a file or folder path to pull that exact content into the conversation and save Claude from searching.
- [Claude Code permissions and plan mode](https://learn-claude-code.onrender.com/learn/claude-code-permissions-plan-mode/): Claude Code asks permission before editing files or running commands. Press Shift+Tab to cycle between normal mode, auto-accept edits and plan mode, where Claude researches and proposes a plan without changing anything.
- [Git, undo and sessions: rewind and resume](https://learn-claude-code.onrender.com/learn/git-undo-rewind-resume-sessions/): Claude Code saves checkpoints so you can rewind conversation and code with Esc twice or /rewind, and git gives you a permanent safety net. Use claude -c to continue your last session and claude -r to pick an older one to resume.
- [What can you use Claude Code for? 12 everyday jobs](https://learn-claude-code.onrender.com/learn/claude-code-use-cases/): Claude Code is useful well beyond writing new code: it explains unfamiliar projects, fixes bugs from an error message, writes tests and documentation, refactors, reviews pull requests, handles git chores, builds small tools and scripts, and helps non-developers automate everyday tasks. Each job has a prompt pattern that works well.
- [CLAUDE.md explained: memory and /init](https://learn-claude-code.onrender.com/learn/claude-md-memory-init/): CLAUDE.md is a markdown file Claude Code loads automatically at the start of every session, acting as its long-term memory for your project. Run /init to generate one, keep team rules in the project-level file, and personal preferences in ~/.claude/CLAUDE.md.
- [Slash commands and context management](https://learn-claude-code.onrender.com/learn/slash-commands-context-management/): Claude Code has a context window: a limited working memory that fills up as you chat, read files and run tools. Use /clear to start fresh between unrelated tasks, /compact to summarise a long session, and /context to see what is using space.
- [Custom slash commands and settings.json](https://learn-claude-code.onrender.com/learn/custom-slash-commands-settings-json/): Save reusable prompts as markdown files in .claude/commands/ (shared with your team) or ~/.claude/commands/ (personal) to create your own slash commands. Use settings.json files to pre-approve safe commands, block risky ones and share configuration.
- [Claude Code skills and subagents](https://learn-claude-code.onrender.com/learn/claude-code-skills-subagents/): Skills are folders containing a SKILL.md file that Claude loads on demand when a task matches their description, perfect for repeatable workflows. Subagents are specialist helpers with their own context window, tools and instructions, used to delegate noisy or parallel work.
- [Claude Code hooks: automatic guardrails](https://learn-claude-code.onrender.com/learn/claude-code-hooks/): Hooks are shell commands Claude Code runs automatically at lifecycle events such as PreToolUse and PostToolUse. Unlike prompt instructions, which Claude usually follows, hooks run every time, making them ideal for formatting, logging and blocking risky actions.
- [Does Claude Code write bloated or insecure code?](https://learn-claude-code.onrender.com/learn/claude-code-bloat-security/): The criticisms have some truth: left to its defaults, an AI agent can add extra code, files and comments, and it can repeat insecure patterns it has seen. The fix is to treat Claude like a fast junior colleague: set house rules in CLAUDE.md, keep tasks small, enforce checks with hooks and linters, run a security review, and keep a person accountable for what ships, with human review for risky changes.
- [MCP servers and plugins for Claude Code](https://learn-claude-code.onrender.com/learn/mcp-servers-plugins/): The Model Context Protocol (MCP) is an open standard that lets Claude Code connect to external tools and data such as GitHub, databases, Figma or your CRM. Add servers with claude mcp add or a shared .mcp.json file, and use plugins to install bundles of commands, skills, agents, hooks and MCP servers in one go.
- [Headless Claude Code and CI/CD pipelines](https://learn-claude-code.onrender.com/learn/headless-claude-code-ci-cd-github-actions/): The -p (print) flag runs Claude Code non-interactively: it takes a prompt, does the work and prints the result, which is essential in scripts and CI where nobody can answer prompts. Combine it with --output-format json for machine-readable results, or use the official GitHub Action to let Claude respond to @claude in issues and PRs.
- [The Claude Agent SDK: build your own agents](https://learn-claude-code.onrender.com/learn/claude-agent-sdk-building-agents/): The Claude Agent SDK gives developers the same agent harness that powers Claude Code as a library for Python and TypeScript. It handles the agentic loop, tools, permissions, hooks, subagents and MCP so you can build custom agents for support, research, operations and more.
- [Architecting agentic systems](https://learn-claude-code.onrender.com/learn/architecting-agentic-systems/): Production agentic systems use a coordinator that decomposes work and delegates to focused subagents, passing explicit context, with deterministic guardrails for high-stakes actions and human checkpoints for irreversible ones. These principles form the core of the Claude Certified Architect exam.

## Certifications
- [Claude Certified Architect study guide](https://learn-claude-code.onrender.com/certifications/claude-certified-architect/): domains, weights, decision rules, sample questions.
- [Claude Code Skills study guide](https://learn-claude-code.onrender.com/certifications/claude-code-skills/): Claude Code CLI, configuration, extensions, automation and API basics.
- [Claude Certified Associate study guide](https://learn-claude-code.onrender.com/certifications/claude-certified-associate/): using Claude well at work, for business users.
- [Claude Certified Developer study guide](https://learn-claude-code.onrender.com/certifications/claude-certified-developer/): building on the Claude API, agents, models, prompts, tools and security.
- [Claude Certified Architect Professional study guide](https://learn-claude-code.onrender.com/certifications/claude-certified-architect-professional/): solution design, integration, evaluation, governance and stakeholders.
- [Practice arena](https://learn-claude-code.onrender.com/practice/): practice mode, timed mock exams, flashcards.

## Reference
- [Glossary](https://learn-claude-code.onrender.com/glossary/): simple definitions of Claude Code terms.
- [Cheat sheet](https://learn-claude-code.onrender.com/cheat-sheet/): Claude Code commands, shortcuts and file locations on one printable page.
- [Claude Code training for teams](https://learn-claude-code.onrender.com/teams/): hands-on team training from Tenzing Digital, remote or in person.
- [Arcade](https://learn-claude-code.onrender.com/arcade/): Bug Invaders and Quiz Blitz, retro browser games for revision breaks.
- [Memes](https://learn-claude-code.onrender.com/memes/): original Claude Code memes, each linked to the lesson that explains it.
- [Full text for LLMs](https://learn-claude-code.onrender.com/llms-full.txt)