Learn Claude Code, one guide at a time
Start here: install Claude Code and run your first task
Install Claude Code, sign in, make your first change, then set up CLAUDE.md with /init and learn when to use /clear.
The master setup prompt: one /goal that configures everything
Walk through our master setup prompt step by step so you know what each line changes before you paste it into Claude Code.
Write a CLAUDE.md that actually helps
Write a short CLAUDE.md with the commands, traps and decisions Claude cannot find in your code, and move the rest out.
Explore, plan, code, verify: the loop that works
Use plan mode, a written spec and a pass or fail check so Claude builds the right thing and proves it works.
Pick the right model and effort for each task
Choose between Opus, Sonnet, Haiku and Fable, set the effort level, and use ultrathink for one hard turn without wasting cache.
Your first skill in 10 minutes
Write a SKILL.md with frontmatter, run it with a slash command or let Claude load it, and split long material into supporting files.
Subagents: when to split the work
Learn when a subagent beats the main conversation, then build a test runner agent that keeps noisy output out of your context.
Let Claude run until it is done with /goal
Write a /goal condition with a measurable end state, a check and a turn bound, then let Claude work through it unattended.
Plugins and marketplaces: install the right packs
Find, vet and install Claude Code plugins from Anthropic's marketplaces, pick the right scope, and drop the ones that only cost you context.
Hooks for beginners
Add three hooks that always run, format files after every edit, trim test output to failures, and block a risky command.
Spend less without getting worse results
Cut Claude Code usage by keeping the prompt cache warm, changing effort instead of models, and clearing context at the right moments.
Claude Code this week: October 30 to November 4, 2026
The changes worth knowing from Claude Code 2.1.314 to 2.1.318, from a new write guard to subagent effort and sign-in expiry.
Big refactors with dynamic workflows
Run a repo-wide refactor as a rerunnable workflow script: inventory, pilot slice, isolated fan-out, adversarial checks, green build.
Code review that catches real bugs
Set up a REVIEW.md and two reviewer agents so Claude reports bugs that would hurt users, not style nits.
Build your first agent with the Claude API
Write a small TypeScript agent that calls tools in a loop, handles errors and stays inside a turn and token budget.
From idea to launched product in a weekend
Turn an idea into a live product in one weekend with a SPEC, a PLAN and one /goal per milestone.
Connect Claude Code to your tools with MCP
Add remote MCP servers safely, then build and connect your own TypeScript server so Claude can use your internal tools.
The multi-agent orchestration playbook
Split big Claude Code jobs across scouts, planners, worktree implementers and reviewers, with a config pack you can drop in.
Put Claude on a schedule: cloud scheduled tasks that run your chores
Set up cloud scheduled tasks that review PRs, check dependencies and triage CI while your laptop is closed, with 5 ready prompts.
Ship a full-stack app on Cloudflare with Claude Code
Use our own kickoff pack to take an Astro, D1, R2, KV and Workflows app from an empty folder to production, one /goal at a time.
Build a team skill library that stays sharp
Ship one shared skill library for your team, with descriptions that route, evals that prove it helps, and a review loop.
The token budget masterclass
Measure where your Claude Code tokens go, keep the prompt cache warm, and cut spend with settings, hooks and a weekly cost sheet.