Question 1

How do I find the Claude Code session linked to a pull request?

Accepted Answer

When you create a PR using `gh pr create`, the session is automatically linked to that PR. Run `claude --from-pr 1234` with your PR number to open the session picker filtered to sessions linked to that PR, or paste the PR URL into the /resume picker search.

Question 2

Will Claude Code match my project's existing test style?

Accepted Answer

Yes. According to the docs, Claude examines your existing test files to match the style, frameworks, and assertion patterns already in use. Being specific about what behavior you want to verify helps it generate more useful tests.

Question 3

What should I tell Claude Code when reporting a bug?

Accepted Answer

The docs recommend telling Claude the command to reproduce the issue so it can get a stack trace, mentioning any steps to reproduce the error, and letting it know whether the error is intermittent or consistent.

Question 4

What's the best way to start exploring an unfamiliar codebase with Claude Code?

Accepted Answer

Navigate to the project root, run `claude`, and ask for a high-level overview with a prompt like "give me an overview of this codebase." Start with broad questions, then narrow down to specific areas like architecture patterns, key data models, or how authentication is handled.

Question 5

Does Claude Code work differently for Next.js, Vite, or Create React App?

Accepted Answer

Not at the tool level — there's no per-framework mode. The real differences are in the commands and conventions you document in CLAUDE.md (dev server command, build command, file structure), not in how Claude Code itself behaves.

Question 6

Do I need TypeScript configured for Claude Code to work with JSX/TSX files?

Accepted Answer

No — Claude Code reads and edits these files like any other source file. If your project uses TypeScript or ESLint, Claude Code works with whatever errors or conventions that tooling already surfaces; it doesn't require extra setup beyond what your project has.

Question 7

Can Claude Code run my test suite automatically?

Accepted Answer

It can run any command you've approved via its permission settings, including your project's real test script — see the Claude Code permissions guide for how allow/ask/deny rules work.

Question 8

Is a CLAUDE.md file required to use Claude Code on a React project?

Accepted Answer

No, but it meaningfully reduces how much context Claude Code has to re-infer each session — see the CLAUDE.md and auto memory guide for what it does and how to generate a starting one with /init.

Question 9

What's the difference between a plugin and putting skills in the .claude directory?

Accepted Answer

Standalone configuration in the .claude/ directory gives you skill names like /hello and is best for personal workflows, project-specific customizations, and quick experiments. Plugins are self-contained directories (optionally with a .claude-plugin/plugin.json manifest) that namespace skills like /plugin-name:hello, and are better for sharing with teammates, distributing to the community, versioned releases, and reuse across projects.

Question 10

How do I test a Claude Code plugin locally before publishing it?

Accepted Answer

Run Claude Code with the --plugin-dir flag pointing at your plugin directory, for example: claude --plugin-dir ./my-first-plugin. Then invoke the skill with its namespaced name, like /my-first-plugin:hello. You can also run /help and check the Custom commands tab to see the skill listed.

Question 11

Why are plugin skill names prefixed like /my-plugin:hello?

Accepted Answer

Plugin skills are always namespaced to prevent conflicts when multiple plugins have skills with the same name. The prefix comes from the name field in plugin.json, so you can change the namespace by updating that field.

Question 12

Why does /reload-plugins report 0 skills after I edit a skill?

Accepted Answer

The skills count in the reload summary only covers commands/ directories, so it can report 0 skills even though the skill you edited actually reloaded. Your updated skill will still work when you invoke it.

Question 13

Why does Claude Code say my MCP server has a "url" but no "type"?

Accepted Answer

A JSON entry with a url but no type is a configuration error: Claude Code reads an entry with no type as a stdio server, skips it, and reports the error telling you to add "type": "http" (or "sse" / "ws"). Before v2.1.202, the same misconfiguration was reported as `command: expected string, received undefined`.

Question 14

Should I use HTTP or SSE transport for remote MCP servers in Claude Code?

Accepted Answer

Use HTTP where available — it's the recommended option and the most widely supported transport for cloud-based services. SSE is deprecated, but some services still expose only an SSE endpoint; for those, use the same claude mcp add command with --transport sse.

Question 15

Can I use "streamable-http" as the type in my .mcp.json?

Accepted Answer

Yes. When configuring servers via JSON in .mcp.json, ~/.claude.json, or claude mcp add-json, the type field accepts streamable-http as an alias for http. The MCP specification uses that name, so configurations copied from server documentation work without modification.

Question 16

How does an MCP stdio server find the project root in Claude Code?

Accepted Answer

Claude Code sets CLAUDE_PROJECT_DIR in the spawned server's environment to the project root — read it from inside the server process, e.g. process.env.CLAUDE_PROJECT_DIR in Node or os.environ["CLAUDE_PROJECT_DIR"] in Python. It's stable and doesn't change mid-session; servers that need the current set of allowed directories should implement the MCP roots/list request instead.

Question 17

How do I add an MCP server to Claude Code from the command line?

Accepted Answer

Run `claude mcp add --transport http ` in your terminal (not inside a claude session). For example: `claude mcp add --transport http claude-code-docs https://code.claude.com/docs/mcp`. The name is one you make up, `--transport http` indicates a hosted server at a URL, and the command confirms which configuration file it wrote.

Question 18

How do I check if an MCP server is connected in Claude Code?

Accepted Answer

Run `claude mcp list` in your terminal. Each server appears with a status indicator such as `✔ Connected` (ready to use), `! Needs authentication`, or `✘ Failed to connect`. If a server connected but couldn't list its tools, run `claude mcp get <name>` for the error detail. Inside a claude session, you can use the `/mcp` command to check and manage servers you've already added.

Question 19

What does 'local config' mean when adding an MCP server?

Accepted Answer

By default, `claude mcp add` registers the server at local scope: private to you and active only in the current project. If you start Claude Code in a different project, the server isn't active there. Pass `--scope user` to register it once for all your projects, or `--scope project` to share it with teammates.

Question 20

Why should I remove MCP servers I'm not using?

Accepted Answer

Each connected server takes some space in Claude's context window because its tool names and server instructions load into every session. Removing servers you no longer use with `claude mcp remove <name>` keeps that space free.

Question 21

What is the difference between CLAUDE.md and auto memory in Claude Code?

Accepted Answer

CLAUDE.md files are instructions you write yourself — coding standards, workflows, and project architecture — scoped to a project, user, or organization. Auto memory is written by Claude itself, capturing learnings and patterns from your corrections, and is scoped per repository (shared across worktrees). Both are loaded at the start of every session, though auto memory is limited to the first 200 lines or 25KB.

Question 22

Where should I put my CLAUDE.md file?

Accepted Answer

It depends on scope. Project instructions go in ./CLAUDE.md or ./.claude/CLAUDE.md and are shared with your team via source control. Personal preferences for all projects go in ~/.claude/CLAUDE.md. Personal project-specific preferences go in ./CLAUDE.local.md (add it to .gitignore). Organization-wide managed policy files live in system locations like /Library/Application Support/ClaudeCode/CLAUDE.md on macOS or /etc/claude-code/CLAUDE.md on Linux and WSL.

Question 23

Does /init overwrite an existing CLAUDE.md?

Accepted Answer

No. If a CLAUDE.md already exists, /init suggests improvements rather than overwriting it. When no file exists, /init analyzes your codebase and creates one with build commands, test instructions, and project conventions it discovers.

Question 24

How do I check that my CLAUDE.md file was actually loaded?

Accepted Answer

Run /context in a session and check the list under "Memory files". Files in the directory hierarchy above the working directory load in full at launch, while CLAUDE.md files in subdirectories load on demand when Claude reads files in those directories.

Question 25

Is Claude's memory on by default?

Accepted Answer

It depends on your plan. Memory is on by default for Free, Pro, and Max plans, and off by default for Team and Enterprise organizations.

Question 26

How do I see or delete what Claude remembers about me?

Accepted Answer

Go to Settings > Memory. Everything Claude remembers is listed under Topics there, and you can edit or delete any individual item.

Question 27

Does Claude remember sensitive information like health details?

Accepted Answer

Not by default. Topics such as health or beliefs stay out of memory unless you turn on the 'Include sensitive topics in memory' setting.

Question 28

Does Claude's memory work in Cowork?

Accepted Answer

Yes. As of this update, memory works across both chat and Cowork in the cloud, so remembered context carries over between the two.

Question 29

Which Claude plans have project sharing?

Accepted Answer

According to Anthropic's release notes dated August 1, 2025, project permissions and sharing were enabled for Team and Enterprise plans. The release notes don't mention availability on other plans.

Question 30

Can Claude projects be shared across a whole organization?

Accepted Answer

Anthropic's release notes point to its "Organization-wide sharing" documentation, indicating the sharing model works at the organization level on Team and Enterprise plans, with permission controls rather than open access.

Question 31

Where do I find instructions for setting up Claude project sharing?

Accepted Answer

The release notes don't include setup steps themselves — they direct readers to Anthropic's Organization-wide sharing documentation, which is the authoritative place for configuration details.

Question 32

How do I get Claude to search my past conversations?

Accepted Answer

According to Anthropic's release notes, you prompt Claude directly — ask it in plain language to search your past chats for a previous conversation or topic. The announcement doesn't describe a separate button or settings toggle; the feature is described as something you invoke by prompting.

Question 33

Which Claude plans can search past chats?

Accepted Answer

Anthropic's August 11, 2025 release notes list the Max, Team, and Enterprise plans. Free and Pro plans are not mentioned in the announcement.

Question 34

Does this mean Claude automatically remembers all my previous chats?

Accepted Answer

The release notes describe this as prompt-driven: users can prompt Claude to search over past chats. It's framed as a search capability you invoke, not as Claude automatically carrying memory into every conversation. Anthropic's support article on personalization features covers the details beyond the announcement.

Question 35

Can Claude combine information from more than one past conversation?

Accepted Answer

Yes — Anthropic's release notes specifically mention 'synthesizing across topics' as one of the two uses, alongside continuing context from a previous chat. That means Claude can draw on multiple past conversations when prompted, not just resume a single one.

Question 36

Is Claude's health data feature available on the free plan?

Accepted Answer

No. According to Anthropic's release notes, health features are available on Pro and Max plans only.

Question 37

What do I need on Android to use Claude's health and fitness features?

Accepted Answer

Android users need Health Connect and Android 14 or later. Without both, the feature won't work on your device.

Question 38

Can I use Claude's health features outside the US?

Accepted Answer

Not currently. Anthropic's release notes state the health features are limited to users in the US. The word 'currently' suggests this may change, but no expansion timeline has been announced.

Question 39

What kind of health data can Claude analyze?

Accepted Answer

Anthropic's release notes specifically mention activity patterns, workout trends, and sleep quality, and note that Claude provides insights and visualizations using native charts. The notes say 'and more,' but don't list additional data types.

Question 40

Can Claude manage reminders on Android?

Accepted Answer

No. According to Anthropic's September 3, 2025 release notes, reminder management is available on iOS only. Android users get the calendar event drafting and location-finding capabilities, but not reminders.

Question 41

What can Claude do with my phone's apps now?

Accepted Answer

Per Anthropic's release notes, Claude's iOS and Android apps can now connect with apps on your device to draft calendar events, help you find locations, and — on iOS only — manage reminders.

Question 42

Do I need a specific Claude plan to use calendar and location access on mobile?

Accepted Answer

Anthropic's release note doesn't mention any plan requirement for this feature. It describes the capabilities as part of the Claude iOS and Android apps and points to two updated support articles for further details.

Question 43

What can the Claude in Chrome extension actually do?

Accepted Answer

According to Anthropic's release notes, the extension allows Claude to read, click, and navigate websites alongside you — meaning it can see page content and take actions in your browser rather than only responding in a chat window.

Question 44

Is Claude in Chrome a finished, stable feature?

Accepted Answer

No. Anthropic explicitly describes it as experimental, which signals an early-stage feature whose behavior and availability may change. It's reasonable to try it, but not to depend on it for critical workflows yet.

Question 45

Does Claude in Chrome work in other browsers like Safari or Edge?

Accepted Answer

The announcement describes it specifically as a Chrome browser extension. No other browsers are mentioned in the release notes.

Question 46

How do I install and set up Claude in Chrome?

Accepted Answer

Anthropic's release notes point to their own "Getting Started with Claude in Chrome" support article for setup. The announcement itself doesn't include installation steps, so that guide is the place to go for current instructions and availability.

Frequently Asked Questions

Guides

Updates

Frequently Asked Questions

Guides

Updates