Claude Code is Anthropic's autonomous coding agent. It runs in your terminal, reads your entire codebase, writes code, executes shell commands, and handles multi-step tasks without you supervising each step. An autonomous agent that does the work.
This guide covers how it works, what it costs, and where it fits in a business context.
What Claude Code Actually Is
Claude Code is a command-line tool you install via npm. You run it in a terminal. It reads your project files, understands the codebase, and then you tell it what to do in plain language. It plans the work, edits files, runs commands, checks its own output, and iterates until the task is done.
The key thing that separates it from every other AI coding tool: it doesn't need a GUI. No editor. No browser window. No tabs. It runs in a terminal, which means it can run on a remote computer, on a server with no screen, through Telegram bots, on a Mac Mini in your cupboard. You can text it an instruction from your phone and check the results later.
This matters more than it sounds. It's the entire reason Claude Code is different from tools like Cursor, GitHub Copilot, or Windsurf. Those tools need you sitting at a computer with an editor open. Claude Code doesn't.
How Claude Code Works
You install it globally:
npm install -g @anthropic-ai/claude-code
You navigate to a project directory and run claude. It reads your project structure. Then you talk to it.
A typical interaction isn't "write me a function." It's more like: "Add a contact form to this Astro site that stores submissions in Cloudflare D1 and sends me a Telegram notification. Include server-side validation and a success state." Claude Code will read your existing code, understand the project structure, create the necessary files, write the worker function, update the form component, and test the build. Multiple files. Multiple steps. One instruction.
It works because Claude Code has access to your entire local environment:
- File system - reads and writes any file in your project
- Terminal - runs shell commands, build tools, tests, git
- Context - reads CLAUDE.md files for project-specific instructions
- Network - full network access for connecting to services, deployments, package installs
The CLAUDE.md file is worth mentioning specifically. You put a markdown file in your project root that tells Claude Code how your project works - the tech stack, conventions, gotchas, what not to touch. It reads this every session. It's like giving a new developer onboarding notes, except this developer actually reads them.
Recent additions worth noting: Claude Code now has automatic memory - it records and recalls context as it works across sessions, so you don't have to re-explain your project every time. There's a research preview of agent teams - multiple Claude Code instances working on different parts of a problem at the same time. And it integrates directly into VS Code with session management and plan review, though the terminal remains the primary interface for autonomous work.
Which Model to Use
Claude Code runs on Anthropic's Claude models. The two that matter:
Opus 4.6 is the model you want for serious work. Complex reasoning, architectural decisions, multi-file refactors, anything where the agent needs to hold a lot of context and make judgment calls. It's slower and more expensive. It's worth it. When Claude Code is running your agent system - acting as the main brain that decides what to do and in what order - the smartest model available is the right choice. Right now that's Opus.
Sonnet 4.6 is faster and cheaper. Good for simpler tasks - quick edits, straightforward features, boilerplate. If you know exactly what you want and the task doesn't require much reasoning, Sonnet saves you money. But don't use it for complex work. The quality difference is real.
| Opus 4.6 | Sonnet 4.6 | |
|---|---|---|
| Best for | Complex reasoning, architecture, multi-file | Simple edits, boilerplate, quick tasks |
| Speed | Slower | Faster |
| Cost per task | $10-50 | $2-10 |
| Keeps track of the project | Excellent across long sessions | Good for shorter sessions |
| Judgment quality | Highest available | Good for most tasks, weaker on edge cases |
Opus vs Sonnet vs Codex in practice
Even with Codex 5.4 now available, Opus 4.6 remains the strongest main agent brain available. Opus is way better at front-end design than Codex. But the real difference is behaviour - Opus adapts to your instructions more precisely than ChatGPT's Codex. It follows your voice, your conventions, your preferences with fewer iterations. The depth of reasoning, the ability to hold complex project context across long sessions, the judgment calls on ambiguous problems - nothing else matches it right now. Sonnet 4.6 is faster but not as thorough. Sonnet is only worth using if you don't want to pay for the Max plan at $200 USD a month (roughly $300 AUD).
And if you're seeing people online recommending Qwen 3.5 as a main agent brain - don't. I tried it. Extremely slow, not smart, reminded me of ChatGPT 3.5 with its overuse of emojis. The real problem: my expectations were misaligned after sitting on Opus 4.6 constantly, then going back to Qwen expecting similar quality. There's a huge gap between what an open-source model scores on a benchmark test and how it actually performs when you need it to reason across a real codebase, make real architectural decisions, and recover from real errors. Qwen 3.5 couldn't do any of that competently. The benchmark scores don't translate to real autonomous work.
Model selection determines everything downstream. It's the worst place to cut costs.
One more thing: A pattern worth questioning is using a different AI app for everything. You can use Claude Code with Opus 4.6 as a single system that handles what all those $50/month apps do separately. It's very easy to consolidate right now. The personalisation factor with Claude Code is huge - it knows your entire business, your clients, your tools, your knowledge, your tone of voice. Stock standard ChatGPT on your phone is a completely different thing to Claude Code running actively on its own computer with full business context.
What Claude Code Is Good At
Full-stack development is where it's most impressive. Tell it to build a feature end-to-end and it writes the frontend component, the backend logic, the database changes, the type definitions. It understands how the pieces connect because it reads your whole codebase first. Refactoring is similarly strong - "rename this service and update every file that uses it" is a five-second instruction that handles what would be 20 minutes of find-and-replace. The real value is larger refactors: restructuring a module, changing an architectural pattern, migrating from one approach to another.
For debugging, paste an error and it reads the relevant files, traces the problem, and fixes it. Often it'll find the root cause was three files away from where the error surfaced. That kind of cross-file reasoning is where Claude Code shines.
It also handles multi-step workflows well. "Build the page, run the build, take a screenshot, check if it looks right, fix the responsive issues, rebuild." One instruction. Claude Code chains the steps together, checks its own work, and iterates. This is agentic AI - autonomous AI that does work independently - in practice. And it's surprisingly useful for codebase understanding - "How does authentication work in this project?" gives you an accurate explanation. Useful for onboarding into unfamiliar codebases or understanding code you wrote six months ago and forgot about.
What Claude Code Is Not Good At
Visual design is the biggest gap. It can write CSS but it can't see the result. It doesn't know if a page looks good. You need to review visual output yourself. Tools that can take screenshots and feed them back help, but Claude Code's native workflow is text-based. Similarly, tasks that need real-time human judgment - "use your taste" or "make it feel right" - lead to iteration loops. Claude Code is best when the success criteria are clear.
On extremely large codebases without guidance, it struggles. On a massive codebase with hundreds of thousands of lines, Claude Code needs your help navigating. The CLAUDE.md file and clear instructions about which parts of the codebase to focus on make a big difference. Without guidance, it can waste time and money reading files it doesn't need.
If you want to see each code change appear in real time and approve it visually, Cursor is better for that workflow. Claude Code shows you what it did after it's done - the trade-off of autonomous execution. Cursor's new Automations feature also now offers cloud-based unattended execution, so the headless advantage is narrowing.
Claude Code Pricing
Claude Code itself is free to install. You pay for what the AI model uses when it works on your tasks.
Pricing is based on usage - roughly, how much text the model reads and writes during a task. In practice:
- Simple task (quick edit, small fix): $2-5
- Medium task (new feature, multi-file changes): $10-25
- Complex task (architectural refactor, full-page build): $20-50
- Heavy day (continuous autonomous work): $50-100+
Claude Code Max is Anthropic's subscription option. $100/month gives you 5x the usage of the Pro plan. $200/month gives you 20x. Both include access to Claude Code and Cowork, which lets you hand off bigger tasks to run in the background. Usage limits reset weekly. If you're using Claude Code daily, Max gives you predictable costs instead of surprise API bills.
The way to think about cost: compare it to your time. If a $20 API bill replaces three hours of manual work, that's not expensive. If you're using it for five-second edits you could do faster by hand, that's waste.
Claude Code vs the Competition in 2026
AI coding tools have converged hard. Every major player now offers some form of autonomous agent. Here's where things actually stand as of March 2026:
| Claude Code | Cursor | OpenAI Codex | GitHub Copilot | |
|---|---|---|---|---|
| Type | Terminal agent | IDE + cloud agents | Terminal + cloud agent | IDE extension |
| Autonomous | Yes, fully headless | Yes, IDE + cloud | Yes, cloud-based | Limited |
| Runs unattended | Yes | Yes (Automations) | Yes (cloud) | No |
| Multi-file | Yes | Yes | Yes | Limited |
| Parallel tasks | One at a time | Multiple (Automations) | Multiple cloud agents | No |
| Model | Claude only | Multi-model | GPT-5.4 | Multi-model |
| Pricing | API or Max $100-200/mo | $20-40/mo | $20-200/mo | $10-19/mo |
What's changed recently: Cursor launched Automations in March 2026 - always-on cloud agents that trigger from Slack, GitHub, Linear, and webhooks. Each runs on its own cloud server and produces code changes ready to go live. This closes the gap with Codex on parallel and unattended work. OpenAI shipped GPT-5.4 with native computer-use capabilities and a much larger memory for holding project context. Claude Code added agent teams (research preview) for multiple agents working together and automatic memory across sessions.
For the detailed breakdowns: Claude Code vs Cursor and Claude Code vs ChatGPT/Codex.
The short version: Claude Code's advantage is full local system access and the deepest integration with Claude's reasoning. Cursor now has both IDE-based and cloud-based agent execution. Codex has parallel cloud execution powered by GPT-5.4. None of them is universally better. It depends on how you work and which model's reasoning you trust most.
Claude Code as a Business Operating System
Claude Code runs on a Mac Mini that stays on all day. A Telegram bot pipes messages to Claude Code sessions. Instructions go in from a phone. The agent does the work. Results get reviewed when convenient.
Example: "audit the SEO on the advisory page and fix anything you find." Claude Code loads the SEO expert instructions from a markdown file, runs the audit, identifies issues, fixes them, rebuilds the site, and sends back a summary. No terminal opened. No browser opened. Summary reviewed on a phone, deploy approved.
A business agent operating system. Claude Code is the execution engine. The structure around it - specialist instruction files, client workspaces, a Telegram bot, persistent memory via markdown files - turns a single tool into a system. The system is deliberately simple. Folders, files, and a bot. No framework.
The real unlock with Claude Code isn't writing code faster. It's removing yourself from the execution loop entirely and focusing on judgment and direction instead. The person who runs this kind of system is an agent operator - and it's a role every business running AI will need.
Making AI tool decisions for your business?
AI advisory for founders and business owners who need direct answers on AI tools and implementation.
AI advisory services →Getting Started with Claude Code
If you want to try Claude Code, here's the honest path:
1. Get an Anthropic API account. Go to console.anthropic.com, create an account, add credits. Start with $20. That's enough for a solid day of experimentation.
2. Install Claude Code. npm install -g @anthropic-ai/claude-code. You need Node.js installed.
3. Start with a real project. Don't test it on toy examples. Open a real codebase you're working on. Navigate to the directory. Run claude.
4. Start with clear, concrete tasks. "Add a 404 page to this project" is better than "make the site better." Claude Code excels when the success criteria are unambiguous. As you get comfortable, you can give it broader instructions.
5. Create a CLAUDE.md file. Tell it about your project. The tech stack, the conventions, what matters. This is the single best thing you can do to improve Claude Code's output quality.
6. Use Opus for anything complex. Don't try to save money by using a weaker model for hard tasks. The cost difference between Opus and Sonnet is small compared to the time you waste fixing bad output from a model that wasn't smart enough for the job.
Common misconceptions about Claude Code
The most common misconception is that it's just for developers. Claude Code writes code, but the person using it doesn't have to be a developer. Business owners use it to build landing pages, set up automations, and manage their web presence. This is part of why static sites built with Claude Code are replacing WordPress for many businesses - Claude Code can build a faster, cheaper static site in an afternoon. You need to be comfortable in a terminal, but you don't need to be a programmer. What you need is the ability to describe what you want clearly - a communication skill.
On the other end, people assume it replaces developers entirely. It doesn't. It replaces a lot of the work developers do. The judgment, architecture, and taste still come from a human. Claude Code handles the execution. If anything, it makes good developers far more productive and widens the gap between good and mediocre developers.
The cost objection usually comes from comparing it to free tools instead of to the time it saves. If a $30 API bill replaces half a day of manual work, that's the cheapest employee you'll ever hire. And waiting for it to get better means your competitors learn it first. It's already good enough to be useful today.