Claude Code: questions and answers

CLAUDE.md, auto memory, hooks and sharing context across a development team.

  • How much does Claude Code cost, and which plan do I need?

    Claude Code is available through paid Claude plans or pay-as-you-go API access; the Free plan does not include it. As of November 2026, Pro costs $20 a month ($17 billed yearly), Max $100 and Ultra $200. Team Standard seats cost $25 a month or $20 billed yearly; API spending depends on usage.

  • How do I install Claude Code, and how do I keep it updated?

    Run the native installer: curl -fsSL https://claude.ai/install.sh | bash on macOS, Linux and WSL, or irm https://claude.ai/install.ps1 | iex in Windows PowerShell. Then run claude in your project and log in with a paid Claude plan or a Console account. Native installs update themselves, npm installs too when the npm folder is writable; Homebrew and WinGet need manual upgrades by default.

  • What are Claude Code skills and how do you write one?

    A skill is a folder with a SKILL.md file: a short YAML header with a name and description, then instructions in Markdown. Claude sees only the name and description in every session and reads the full file when a task fits, or when you type /skill-name. Personal skills live in ~/.claude/skills/, project skills in .claude/skills/ in the repo, and plugins can ship their own.

  • Claude Code desktop, CLI, web or mobile: what is the difference?

    All four use the same Claude Code engine, but cloud sessions load only part of your configuration. The terminal CLI runs on your machine and is the most complete. The desktop app wraps it in a visual interface with diff review and parallel sessions. Claude Code on the web runs sessions on Anthropic-managed cloud machines. The mobile app runs nothing itself: it steers cloud or local sessions.

  • How do I use Claude Code well? A first workflow that works

    Write a specific prompt, give Claude a check it can run (a test, a build, a linter) and ask for the output as evidence. Keep CLAUDE.md short and only for what the code cannot tell Claude. Put rules that may never be broken in deny rules or hooks, not in prose. Press Esc when it drifts, and after two failed corrections run /clear and write a better prompt.

  • How do I use Claude Code with GitHub, and @claude in pull requests?

    Claude Code GitHub Actions is a GitHub Action, anthropics/claude-code-action@v1, that runs Claude Code inside your repository's workflows. The quick setup is /install-github-app in Claude Code, which needs admin access to the repo. After that, anyone with write access can mention @claude in an issue or PR to get code analyzed, changed and pushed. Each run uses GitHub Actions minutes plus API tokens or your Claude subscription.

  • Claude Code vs Cursor: which should my dev team choose?

    Choose Claude Code for a Claude-centered workflow across the editors your developers already use, priced through Claude plans from $20 a month or Team seats from $25. Choose Cursor when your team wants its editor workflow and a broader choice of models; as of November 2026 it is sold inside The X Subscription, with Teams seats at $30, $100 or $200 and Claude models billed at API prices. They also combine: Claude Code runs inside Cursor.

  • What is Everything Claude Code (ECC) and should your team install it?

    Everything Claude Code, renamed ECC (github.com/affaan-m/ECC), is an open source, MIT-licensed collection that turns Claude Code into a fuller engineering setup: 72 agents, 327 skills, hooks, rules, session memory and the AgentShield security scanner. It installs as the Claude Code plugin ecc@ecc and also has paths for Codex, Cursor, OpenCode and others. It is a community project, not from Anthropic.

  • What is Claude Code Remote Control and how do I use it?

    Remote Control connects claude.ai/code or the Claude mobile app to a Claude Code session that keeps running on your own computer, with your files, tools and MCP servers. Start it with claude remote-control, claude --remote-control or /remote-control. It works on Pro, Max, Ultra, Team and Enterprise plans, not with API keys, and your machine has to stay on.

  • How do Claude Code usage limits work, and how do I check my usage?

    On Pro and Max, Claude Code shares a rolling 5-hour limit and a weekly limit with Claude chat; Team and seat-based Enterprise seats work the same way per seat. With an API key there is no plan limit: you pay per token. Type /usage in Claude Code (/cost and /stats are aliases) to see plan usage bars, session cost and what eats your allowance.

  • OpenCode vs Claude Code: which coding agent should I use?

    Pick Claude Code if you work with Claude models and want to use your Claude subscription: Anthropic's terms reserve subscription sign-in for its own apps. Pick OpenCode if you want an open source (MIT) agent that switches between many providers, including local models, ChatGPT Plus or Pro, and GitHub Copilot. Claude models in OpenCode run on API billing.

  • Can Claude Code review pull requests, and what does Code Review cost?

    Yes, in several ways. Code Review is Anthropic's managed service: several agents review each GitHub pull request on Anthropic's infrastructure, verify their findings and post inline comments. It is for Team and Enterprise plans and is billed on token usage through usage credits, with no flat price per review. On any plan, /code-review (alias /review) reviews your branch inside your own Claude Code session.

  • What are agent teams in Claude Code and how do you turn them on?

    Agent teams let one Claude Code session act as team lead and start teammates: full, separate Claude Code sessions that share a task list and message each other directly. The feature is experimental and disabled by default; you turn it on with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Each teammate has its own context window, so token use grows with the size of the team.

  • What is auto mode in Claude Code, and is it safe to use?

    Auto mode is a Claude Code permission mode in which Claude acts without asking, while a separate classifier model reviews what rules and auto-approval do not settle and blocks what goes beyond your request, such as a force push or a production deploy. Since v2.1.283 it is the starting mode for interactive terminal and VS Code sessions. The docs state that it reduces prompts but does not guarantee safety.

  • What does plan mode do in Claude Code and how do you turn it on?

    Plan mode is a Claude Code permission mode in which Claude reads files, runs commands to explore and writes a plan, but normally does not edit your source until you approve. You enter it with Shift+Tab, by starting a single prompt with /plan, or with claude --permission-mode plan. When the plan is ready you choose how to continue, or keep planning.

  • What is Claude Code Router and should a team use it?

    Claude Code Router (CCR) is an open source, MIT-licensed project by musistudio, not by Anthropic. It runs a local gateway on your machine (port 3456 by default) that sits between coding agents such as Claude Code, Codex, OpenCode or Grok CLI and the model providers you configure, with routing rules, fallbacks and request logs. Anthropic does not support routing Claude Code to non-Claude models.

  • What is the Claude Code SDK, now the Claude Agent SDK?

    The Claude Code SDK was renamed the Claude Agent SDK. It gives you the same tools, agent loop and context management that power Claude Code, as a library in Python (claude-agent-sdk) and TypeScript (@anthropic-ai/claude-agent-sdk). Use it to embed an agent in your own application. For scripts and CI in any language, claude -p is the same SDK through the command line.

  • Is Claude Code safe to use on company code?

    Claude Code runs on your machine and sends your prompts, the code it reads and its output to Anthropic over TLS. Under commercial terms (Team, Enterprise, API) Anthropic does not train on that data and keeps it 30 days by default. On Free, Pro, Max and Ultra, training depends on a privacy setting. Safety on the machine itself comes from permissions, deny rules, the sandbox and managed settings.

  • How do I use Claude Code in VS Code and JetBrains?

    In VS Code (1.94 or later), Cursor and other forks, install the Claude Code extension: it bundles its own copy of Claude Code and adds a chat panel with inline diffs, @-mentions and plan review. In IntelliJ, PyCharm, WebStorm and other JetBrains IDEs, install the Claude Code plugin and the CLI separately; the plugin runs claude in the IDE terminal and opens diffs in the IDE's diff viewer.

  • What are subagents in Claude Code and when should you use them?

    A subagent is a separate Claude worker that Claude Code starts for one task. It has its own context window, its own system prompt and its own tool permissions, and it returns only a result, so long search output or logs stay out of your main conversation. Claude Code ships built-in subagents such as Explore and Plan, and you define your own as Markdown files in .claude/agents/.

  • Does Claude Code have memory across sessions?

    You can resume an earlier session with claude --continue or claude --resume; a new session starts with an empty context window. Two mechanisms carry knowledge into it: CLAUDE.md files, which you write and can share through git, and auto memory, notes Claude Code writes itself in ~/.claude/projects/<project>/memory/ with MEMORY.md as the index. Auto memory is on by default and stays on your machine.

  • How much does Claude Code cost per developer per month in tokens?

    Anthropic's Claude Code docs give an average of about $13 per developer per active day and $150 to $250 per developer per month across enterprise deployments, with 90% of users staying under $30 per active day. On a Pro, Max or Team seat you pay a fixed price and hit usage limits instead; with an API key you pay per token.

  • What are Claude Code hooks and how do I set them up?

    Hooks are handlers Claude Code runs automatically at fixed moments in a session: before a tool call (PreToolUse), after it (PostToolUse), when a prompt is submitted, when Claude stops, and more. You configure them in a settings.json file. Unlike CLAUDE.md, which Claude reads as advice, a PreToolUse hook that exits with code 2 actually blocks the action.

  • How do Claude Code plugins work, and can a plugin add shared memory?

    A Claude Code plugin is a folder that bundles skills, subagents, hooks and MCP servers, described in .claude-plugin/plugin.json, and installed as one unit from a marketplace with /plugin. Claude Code's built-in memory is local files. A plugin can add memory that lives elsewhere: an MCP server gives Claude tools to read and write it, and hooks load it at the right moment.

All topics →

The first half hour · free

What does your AI forget?

  1. 01You tell us which AI you use and where it keeps starting over.
  2. 02We show what a shared memory changes there, on your own examples.
  3. 03You keep the plan, with or without Bombos.
Piet Baudoin
Piet BaudoinYou talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe
We reply the same working day.