Documentation 2026-03-05 06:12 UTC to 2026-03-06 06:10 UTC

28 </Step>28 </Step>

29 29 

30 <Step title="Ask for a high-level overview">30 <Step title="Ask for a high-level overview">

31 ```31 ```text theme={null}

32 > give me an overview of this codebase 32 give me an overview of this codebase

33 ```33 ```

34 </Step>34 </Step>

35 35 

36 <Step title="Dive deeper into specific components">36 <Step title="Dive deeper into specific components">

37 ```37 ```text theme={null}

38 > explain the main architecture patterns used here 38 explain the main architecture patterns used here

39 ```39 ```

40 40 

41 ```41 ```text theme={null}

42 > what are the key data models?42 what are the key data models?

43 ```43 ```

44 44 

45 ```45 ```text theme={null}

46 > how is authentication handled?46 how is authentication handled?

47 ```47 ```

48 </Step>48 </Step>

49</Steps>49</Steps>

62 62 

63<Steps>63<Steps>

64 <Step title="Ask Claude to find relevant files">64 <Step title="Ask Claude to find relevant files">

65 ```65 ```text theme={null}

66 > find the files that handle user authentication 66 find the files that handle user authentication

67 ```67 ```

68 </Step>68 </Step>

69 69 

70 <Step title="Get context on how components interact">70 <Step title="Get context on how components interact">

71 ```71 ```text theme={null}

72 > how do these authentication files work together? 72 how do these authentication files work together?

73 ```73 ```

74 </Step>74 </Step>

75 75 

76 <Step title="Understand the execution flow">76 <Step title="Understand the execution flow">

77 ```77 ```text theme={null}

78 > trace the login process from front-end to database 78 trace the login process from front-end to database

79 ```79 ```

80 </Step>80 </Step>

81</Steps>81</Steps>

96 96 

97<Steps>97<Steps>

98 <Step title="Share the error with Claude">98 <Step title="Share the error with Claude">

99 ```99 ```text theme={null}

100 > I'm seeing an error when I run npm test 100 I'm seeing an error when I run npm test

101 ```101 ```

102 </Step>102 </Step>

103 103 

104 <Step title="Ask for fix recommendations">104 <Step title="Ask for fix recommendations">

105 ```105 ```text theme={null}

106 > suggest a few ways to fix the @ts-ignore in user.ts 106 suggest a few ways to fix the @ts-ignore in user.ts

107 ```107 ```

108 </Step>108 </Step>

109 109 

110 <Step title="Apply the fix">110 <Step title="Apply the fix">

111 ```111 ```text theme={null}

112 > update user.ts to add the null check you suggested 112 update user.ts to add the null check you suggested

113 ```113 ```

114 </Step>114 </Step>

115</Steps>115</Steps>

130 130 

131<Steps>131<Steps>

132 <Step title="Identify legacy code for refactoring">132 <Step title="Identify legacy code for refactoring">

133 ```133 ```text theme={null}

134 > find deprecated API usage in our codebase 134 find deprecated API usage in our codebase

135 ```135 ```

136 </Step>136 </Step>

137 137 

138 <Step title="Get refactoring recommendations">138 <Step title="Get refactoring recommendations">

139 ```139 ```text theme={null}

140 > suggest how to refactor utils.js to use modern JavaScript features 140 suggest how to refactor utils.js to use modern JavaScript features

141 ```141 ```

142 </Step>142 </Step>

143 143 

144 <Step title="Apply the changes safely">144 <Step title="Apply the changes safely">

145 ```145 ```text theme={null}

146 > refactor utils.js to use ES2024 features while maintaining the same behavior 146 refactor utils.js to use ES2024 features while maintaining the same behavior

147 ```147 ```

148 </Step>148 </Step>

149 149 

150 <Step title="Verify the refactoring">150 <Step title="Verify the refactoring">

151 ```151 ```text theme={null}

152 > run tests for the refactored code 152 run tests for the refactored code

153 ```153 ```

154 </Step>154 </Step>

155</Steps>155</Steps>

170 170 

171<Steps>171<Steps>

172 <Step title="View available subagents">172 <Step title="View available subagents">

173 ```173 ```text theme={null}

174 > /agents174 /agents

175 ```175 ```

176 176 

177 This shows all available subagents and lets you create new ones.177 This shows all available subagents and lets you create new ones.

180 <Step title="Use subagents automatically">180 <Step title="Use subagents automatically">

181 Claude Code automatically delegates appropriate tasks to specialized subagents:181 Claude Code automatically delegates appropriate tasks to specialized subagents:

182 182 

183 ```183 ```text theme={null}

184 > review my recent code changes for security issues184 review my recent code changes for security issues

185 ```185 ```

186 186 

187 ```187 ```text theme={null}

188 > run all tests and fix any failures188 run all tests and fix any failures

189 ```189 ```

190 </Step>190 </Step>

191 191 

192 <Step title="Explicitly request specific subagents">192 <Step title="Explicitly request specific subagents">

193 ```193 ```text theme={null}

194 > use the code-reviewer subagent to check the auth module194 use the code-reviewer subagent to check the auth module

195 ```195 ```

196 196 

197 ```197 ```text theme={null}

198 > have the debugger subagent investigate why users can't log in198 have the debugger subagent investigate why users can't log in

199 ```199 ```

200 </Step>200 </Step>

201 201 

202 <Step title="Create custom subagents for your workflow">202 <Step title="Create custom subagents for your workflow">

203 ```203 ```text theme={null}

204 > /agents204 /agents

205 ```205 ```

206 206 

207 Then select "Create New subagent" and follow the prompts to define:207 Then select "Create New subagent" and follow the prompts to define:

264claude --permission-mode plan264claude --permission-mode plan

265```265```

266 266 

267```267```text theme={null}

268> I need to refactor our authentication system to use OAuth2. Create a detailed migration plan.268I need to refactor our authentication system to use OAuth2. Create a detailed migration plan.

269```269```

270 270 

271Claude analyzes the current implementation and create a comprehensive plan. Refine with follow-ups:271Claude analyzes the current implementation and create a comprehensive plan. Refine with follow-ups:

272 272 

273```text theme={null}

274What about backward compatibility?

273```275```

274> What about backward compatibility?276 

275> How should we handle database migration?277```text theme={null}

278How should we handle database migration?

276```279```

277 280 

278<Tip>Press `Ctrl+G` to open the plan in your default text editor, where you can edit it directly before Claude proceeds.</Tip>281<Tip>Press `Ctrl+G` to open the plan in your default text editor, where you can edit it directly before Claude proceeds.</Tip>

298 301 

299<Steps>302<Steps>

300 <Step title="Identify untested code">303 <Step title="Identify untested code">

301 ```304 ```text theme={null}

302 > find functions in NotificationsService.swift that are not covered by tests 305 find functions in NotificationsService.swift that are not covered by tests

303 ```306 ```

304 </Step>307 </Step>

305 308 

306 <Step title="Generate test scaffolding">309 <Step title="Generate test scaffolding">

307 ```310 ```text theme={null}

308 > add tests for the notification service 311 add tests for the notification service

309 ```312 ```

310 </Step>313 </Step>

311 314 

312 <Step title="Add meaningful test cases">315 <Step title="Add meaningful test cases">

313 ```316 ```text theme={null}

314 > add test cases for edge conditions in the notification service 317 add test cases for edge conditions in the notification service

315 ```318 ```

316 </Step>319 </Step>

317 320 

318 <Step title="Run and verify tests">321 <Step title="Run and verify tests">

319 ```322 ```text theme={null}

320 > run the new tests and fix any failures 323 run the new tests and fix any failures

321 ```324 ```

322 </Step>325 </Step>

323</Steps>326</Steps>

334 337 

335<Steps>338<Steps>

336 <Step title="Summarize your changes">339 <Step title="Summarize your changes">

337 ```340 ```text theme={null}

338 > summarize the changes I've made to the authentication module341 summarize the changes I've made to the authentication module

339 ```342 ```

340 </Step>343 </Step>

341 344 

342 <Step title="Generate a pull request">345 <Step title="Generate a pull request">

343 ```346 ```text theme={null}

344 > create a pr347 create a pr

345 ```348 ```

346 </Step>349 </Step>

347 350 

348 <Step title="Review and refine">351 <Step title="Review and refine">

349 ```352 ```text theme={null}

350 > enhance the PR description with more context about the security improvements353 enhance the PR description with more context about the security improvements

351 ```354 ```

352 </Step>355 </Step>

353</Steps>356</Steps>

364 367 

365<Steps>368<Steps>

366 <Step title="Identify undocumented code">369 <Step title="Identify undocumented code">

367 ```370 ```text theme={null}

368 > find functions without proper JSDoc comments in the auth module 371 find functions without proper JSDoc comments in the auth module

369 ```372 ```

370 </Step>373 </Step>

371 374 

372 <Step title="Generate documentation">375 <Step title="Generate documentation">

373 ```376 ```text theme={null}

374 > add JSDoc comments to the undocumented functions in auth.js 377 add JSDoc comments to the undocumented functions in auth.js

375 ```378 ```

376 </Step>379 </Step>

377 380 

378 <Step title="Review and enhance">381 <Step title="Review and enhance">

379 ```382 ```text theme={null}

380 > improve the generated documentation with more context and examples 383 improve the generated documentation with more context and examples

381 ```384 ```

382 </Step>385 </Step>

383 386 

384 <Step title="Verify documentation">387 <Step title="Verify documentation">

385 ```388 ```text theme={null}

386 > check if the documentation follows our project standards 389 check if the documentation follows our project standards

387 ```390 ```

388 </Step>391 </Step>

389</Steps>392</Steps>

412 </Step>415 </Step>

413 416 

414 <Step title="Ask Claude to analyze the image">417 <Step title="Ask Claude to analyze the image">

415 ```418 ```text theme={null}

416 > What does this image show?419 What does this image show?

417 ```420 ```

418 421 

419 ```422 ```text theme={null}

420 > Describe the UI elements in this screenshot423 Describe the UI elements in this screenshot

421 ```424 ```

422 425 

423 ```426 ```text theme={null}

424 > Are there any problematic elements in this diagram?427 Are there any problematic elements in this diagram?

425 ```428 ```

426 </Step>429 </Step>

427 430 

428 <Step title="Use images for context">431 <Step title="Use images for context">

429 ```432 ```text theme={null}

430 > Here's a screenshot of the error. What's causing it?433 Here's a screenshot of the error. What's causing it?

431 ```434 ```

432 435 

433 ```436 ```text theme={null}

434 > This is our current database schema. How should we modify it for the new feature?437 This is our current database schema. How should we modify it for the new feature?

435 ```438 ```

436 </Step>439 </Step>

437 440 

438 <Step title="Get code suggestions from visual content">441 <Step title="Get code suggestions from visual content">

439 ```442 ```text theme={null}

440 > Generate CSS to match this design mockup443 Generate CSS to match this design mockup

441 ```444 ```

442 445 

443 ```446 ```text theme={null}

444 > What HTML structure would recreate this component?447 What HTML structure would recreate this component?

445 ```448 ```

446 </Step>449 </Step>

447</Steps>450</Steps>

464 467 

465<Steps>468<Steps>

466 <Step title="Reference a single file">469 <Step title="Reference a single file">

467 ```470 ```text theme={null}

468 > Explain the logic in @src/utils/auth.js471 Explain the logic in @src/utils/auth.js

469 ```472 ```

470 473 

471 This includes the full content of the file in the conversation.474 This includes the full content of the file in the conversation.

472 </Step>475 </Step>

473 476 

474 <Step title="Reference a directory">477 <Step title="Reference a directory">

475 ```478 ```text theme={null}

476 > What's the structure of @src/components?479 What's the structure of @src/components?

477 ```480 ```

478 481 

479 This provides a directory listing with file information.482 This provides a directory listing with file information.

480 </Step>483 </Step>

481 484 

482 <Step title="Reference MCP resources">485 <Step title="Reference MCP resources">

483 ```486 ```text theme={null}

484 > Show me the data from @github:repos/owner/repo/issues487 Show me the data from @github:repos/owner/repo/issues

485 ```488 ```

486 489 

487 This fetches data from connected MCP servers using the format @server:resource. See [MCP resources](/en/mcp#use-mcp-resources) for details.490 This fetches data from connected MCP servers using the format @server:resource. See [MCP resources](/en/mcp#use-mcp-resources) for details.

561 <Step title="Name the current session">564 <Step title="Name the current session">

562 Use `/rename` during a session to give it a memorable name:565 Use `/rename` during a session to give it a memorable name:

563 566 

564 ```567 ```text theme={null}

565 > /rename auth-refactor568 /rename auth-refactor

566 ```569 ```

567 570 

568 You can also rename any session from the picker: run `/resume`, navigate to a session, and press `R`.571 You can also rename any session from the picker: run `/resume`, navigate to a session, and press `R`.

577 580 

578 Or from inside an active session:581 Or from inside an active session:

579 582 

580 ```583 ```text theme={null}

581 > /resume auth-refactor584 /resume auth-refactor

582 ```585 ```

583 </Step>586 </Step>

584</Steps>587</Steps>

859 862 

860### Example questions863### Example questions

861 864 

862```865```text theme={null}

863> can Claude Code create pull requests?866can Claude Code create pull requests?

864```867```

865 868 

866```869```text theme={null}

867> how does Claude Code handle permissions?870how does Claude Code handle permissions?

868```871```

869 872 

870```873```text theme={null}

871> what skills are available?874what skills are available?

872```875```

873 876 

874```877```text theme={null}

875> how do I use MCP with Claude Code?878how do I use MCP with Claude Code?

876```879```

877 880 

878```881```text theme={null}

879> how do I configure Claude Code for Amazon Bedrock?882how do I configure Claude Code for Amazon Bedrock?

880```883```

881 884 

882```885```text theme={null}

883> what are the limitations of Claude Code?886what are the limitations of Claude Code?

884```887```

885 888 

886<Note>889<Note>

184 184 

185Claude Code is conversational. You don't need perfect prompts. Start with what you want, then refine:185Claude Code is conversational. You don't need perfect prompts. Start with what you want, then refine:

186 186 

187```text theme={null}

188Fix the login bug

187```189```

188> Fix the login bug

189 190 

190[Claude investigates, tries something]191\[Claude investigates, tries something]

191 192 

192> That's not quite right. The issue is in the session handling.193```text theme={null}

193 194That's not quite right. The issue is in the session handling.

194[Claude adjusts approach]

195```195```

196 196 

197\[Claude adjusts approach]

198 

197When the first attempt isn't right, you don't start over. You iterate.199When the first attempt isn't right, you don't start over. You iterate.

198 200 

199#### Interrupt and steer201#### Interrupt and steer

204 206 

205The more precise your initial prompt, the fewer corrections you'll need. Reference specific files, mention constraints, and point to example patterns.207The more precise your initial prompt, the fewer corrections you'll need. Reference specific files, mention constraints, and point to example patterns.

206 208 

207```209```text theme={null}

208> The checkout flow is broken for users with expired cards.210The checkout flow is broken for users with expired cards.

209> Check src/payments/ for the issue, especially token refresh.211Check src/payments/ for the issue, especially token refresh.

210> Write a failing test first, then fix it.212Write a failing test first, then fix it.

211```213```

212 214 

213Vague prompts like "fix the login bug" work, but you'll spend more time steering. Specific prompts like the above often succeed on the first attempt.215Vague prompts work, but you'll spend more time steering. Specific prompts like the one above often succeed on the first attempt.

214 216 

215### Give Claude something to verify against217### Give Claude something to verify against

216 218 

217Claude performs better when it can check its own work. Include test cases, paste screenshots of expected UI, or define the output you want.219Claude performs better when it can check its own work. Include test cases, paste screenshots of expected UI, or define the output you want.

218 220 

219```221```text theme={null}

220> Implement validateEmail. Test cases: 'user@example.com' → true,222Implement validateEmail. Test cases: 'user@example.com' → true,

221> 'invalid' → false, 'user@.com' → false. Run the tests after.223'invalid' → false, 'user@.com' → false. Run the tests after.

222```224```

223 225 

224For visual work, paste a screenshot of the design and ask Claude to compare its implementation against it.226For visual work, paste a screenshot of the design and ask Claude to compare its implementation against it.

227 229 

228For complex problems, separate research from coding. Use plan mode (`Shift+Tab` twice) to analyze the codebase first:230For complex problems, separate research from coding. Use plan mode (`Shift+Tab` twice) to analyze the codebase first:

229 231 

230```232```text theme={null}

231> Read src/auth/ and understand how we handle sessions.233Read src/auth/ and understand how we handle sessions.

232> Then create a plan for adding OAuth support.234Then create a plan for adding OAuth support.

233```235```

234 236 

235Review the plan, refine it through conversation, then let Claude implement. This two-phase approach produces better results than jumping straight to code.237Review the plan, refine it through conversation, then let Claude implement. This two-phase approach produces better results than jumping straight to code.

238 240 

239Think of delegating to a capable colleague. Give context and direction, then trust Claude to figure out the details:241Think of delegating to a capable colleague. Give context and direction, then trust Claude to figure out the details:

240 242 

241```243```text theme={null}

242> The checkout flow is broken for users with expired cards.244The checkout flow is broken for users with expired cards.

243> The relevant code is in src/payments/. Can you investigate and fix it?245The relevant code is in src/payments/. Can you investigate and fix it?

244```246```

245 247 

246You don't need to specify which files to read or what commands to run. Claude figures that out.248You don't need to specify which files to read or what commands to run. Claude figures that out.

51 51 

52```bash theme={null}52```bash theme={null}

53claude53claude

54> /ide54```

55 

56```text theme={null}

57/ide

55```58```

56 59 

57If you want Claude to have access to the same files as your IDE, start Claude Code from the same directory as your IDE project root.60If you want Claude to have access to the same files as your IDE, start Claude Code from the same directory as your IDE project root.

532{/* ### Example: Automate browser testing with Playwright532{/* ### Example: Automate browser testing with Playwright

533 533 

534 ```bash534 ```bash

535 # 1. Add the Playwright MCP server

536 claude mcp add --transport stdio playwright -- npx -y @playwright/mcp@latest535 claude mcp add --transport stdio playwright -- npx -y @playwright/mcp@latest

536 ```

537 

538 Then write and run browser tests:

537 539 

538 # 2. Write and run browser tests540 ```text

539 > "Test if the login flow works with test@example.com"541 Test if the login flow works with test@example.com

540 > "Take a screenshot of the checkout page on mobile"542 ```

541 > "Verify that the search feature returns results"543 ```text

544 Take a screenshot of the checkout page on mobile

545 ```

546 ```text

547 Verify that the search feature returns results

542 ``` */}548 ``` */}

543 549 

544### Example: Monitor errors with Sentry550### Example: Monitor errors with Sentry

545 551 

546```bash theme={null}552```bash theme={null}

547# 1. Add the Sentry MCP server

548claude mcp add --transport http sentry https://mcp.sentry.dev/mcp553claude mcp add --transport http sentry https://mcp.sentry.dev/mcp

554```

555 

556Authenticate with your Sentry account:

557 

558```text theme={null}

559/mcp

560```

549 561 

550# 2. Use /mcp to authenticate with your Sentry account562Then debug production issues:

551> /mcp

552 563 

553# 3. Debug production issues564```text theme={null}

554> "What are the most common errors in the last 24 hours?"565What are the most common errors in the last 24 hours?

555> "Show me the stack trace for error ID abc123"566```

556> "Which deployment introduced these new errors?"567 

568```text theme={null}

569Show me the stack trace for error ID abc123

570```

571 

572```text theme={null}

573Which deployment introduced these new errors?

557```574```

558 575 

559### Example: Connect to GitHub for code reviews576### Example: Connect to GitHub for code reviews

560 577 

561```bash theme={null}578```bash theme={null}

562# 1. Add the GitHub MCP server

563claude mcp add --transport http github https://api.githubcopilot.com/mcp/579claude mcp add --transport http github https://api.githubcopilot.com/mcp/

580```

581 

582Authenticate if needed by selecting "Authenticate" for GitHub:

583 

584```text theme={null}

585/mcp

586```

564 587 

565# 2. In Claude Code, authenticate if needed588Then work with GitHub:

566> /mcp

567# Select "Authenticate" for GitHub

568 589 

569# 3. Now you can ask Claude to work with GitHub590```text theme={null}

570> "Review PR #456 and suggest improvements"591Review PR #456 and suggest improvements

571> "Create a new issue for the bug we just found"592```

572> "Show me all open PRs assigned to me"593 

594```text theme={null}

595Create a new issue for the bug we just found

596```

597 

598```text theme={null}

599Show me all open PRs assigned to me

573```600```

574 601 

575### Example: Query your PostgreSQL database602### Example: Query your PostgreSQL database

576 603 

577```bash theme={null}604```bash theme={null}

578# 1. Add the database server with your connection string

579claude mcp add --transport stdio db -- npx -y @bytebase/dbhub \605claude mcp add --transport stdio db -- npx -y @bytebase/dbhub \

580 --dsn "postgresql://readonly:pass@prod.db.com:5432/analytics"606 --dsn "postgresql://readonly:pass@prod.db.com:5432/analytics"

607```

608 

609Then query your database naturally:

610 

611```text theme={null}

612What's our total revenue this month?

613```

614 

615```text theme={null}

616Show me the schema for the orders table

617```

581 618 

582# 2. Query your database naturally619```text theme={null}

583> "What's our total revenue this month?"620Find customers who haven't made a purchase in 90 days

584> "Show me the schema for the orders table"

585> "Find customers who haven't made a purchase in 90 days"

586```621```

587 622 

588## Authenticate with remote MCP servers623## Authenticate with remote MCP servers

601 <Step title="Use the /mcp command within Claude Code">636 <Step title="Use the /mcp command within Claude Code">

602 In Claude code, use the command:637 In Claude code, use the command:

603 638 

604 ```639 ```text theme={null}

605 > /mcp640 /mcp

606 ```641 ```

607 642 

608 Then follow the steps in your browser to login.643 Then follow the steps in your browser to login.

810 <Step title="View and manage servers in Claude Code">845 <Step title="View and manage servers in Claude Code">

811 In Claude Code, use the command:846 In Claude Code, use the command:

812 847 

813 ```848 ```text theme={null}

814 # Within Claude Code, see all MCP servers including Claude.ai ones849 /mcp

815 > /mcp

816 ```850 ```

817 851 

818 Claude.ai servers appear in the list with indicators showing they come from Claude.ai.852 Claude.ai servers appear in the list with indicators showing they come from Claude.ai.

924 <Step title="Reference a specific resource">958 <Step title="Reference a specific resource">

925 Use the format `@server:protocol://resource/path` to reference a resource:959 Use the format `@server:protocol://resource/path` to reference a resource:

926 960 

927 ```961 ```text theme={null}

928 > Can you analyze @github:issue://123 and suggest a fix?962 Can you analyze @github:issue://123 and suggest a fix?

929 ```963 ```

930 964 

931 ```965 ```text theme={null}

932 > Please review the API documentation at @docs:file://api/authentication966 Please review the API documentation at @docs:file://api/authentication

933 ```967 ```

934 </Step>968 </Step>

935 969 

936 <Step title="Multiple resource references">970 <Step title="Multiple resource references">

937 You can reference multiple resources in a single prompt:971 You can reference multiple resources in a single prompt:

938 972 

939 ```973 ```text theme={null}

940 > Compare @postgres:schema://users with @docs:file://database/user-model974 Compare @postgres:schema://users with @docs:file://database/user-model

941 ```975 ```

942 </Step>976 </Step>

943</Steps>977</Steps>

1019 </Step>1053 </Step>

1020 1054 

1021 <Step title="Execute a prompt without arguments">1055 <Step title="Execute a prompt without arguments">

1022 ```1056 ```text theme={null}

1023 > /mcp__github__list_prs1057 /mcp__github__list_prs

1024 ```1058 ```

1025 </Step>1059 </Step>

1026 1060 

1027 <Step title="Execute a prompt with arguments">1061 <Step title="Execute a prompt with arguments">

1028 Many prompts accept arguments. Pass them space-separated after the command:1062 Many prompts accept arguments. Pass them space-separated after the command:

1029 1063 

1030 ```1064 ```text theme={null}

1031 > /mcp__github__pr_review 4561065 /mcp__github__pr_review 456

1032 ```1066 ```

1033 1067 

1034 ```1068 ```text theme={null}

1035 > /mcp__jira__create_issue "Bug in login flow" high1069 /mcp__jira__create_issue "Bug in login flow" high

1036 ```1070 ```

1037 </Step>1071 </Step>

1038</Steps>1072</Steps>

7> Continue a local Claude Code session from your phone, tablet, or any browser using Remote Control. Works with claude.ai/code and the Claude mobile app.7> Continue a local Claude Code session from your phone, tablet, or any browser using Remote Control. Works with claude.ai/code and the Claude mobile app.

8 8 

9<Note>9<Note>

10 Remote Control is available as a research preview on Max and Pro plans. It is not available on Team or Enterprise plans.10 Remote Control is available on all plans. Team and Enterprise admins must first enable Claude Code in [admin settings](https://claude.ai/admin-settings/claude-code).

11</Note>11</Note>

12 12 

13Remote Control connects [claude.ai/code](https://claude.ai/code) or the Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) to a Claude Code session running on your machine. Start a task at your desk, then pick it up from your phone on the couch or a browser on another computer.13Remote Control connects [claude.ai/code](https://claude.ai/code) or the Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) to a Claude Code session running on your machine. Start a task at your desk, then pick it up from your phone on the couch or a browser on another computer.

26 26 

27Before using Remote Control, confirm that your environment meets these conditions:27Before using Remote Control, confirm that your environment meets these conditions:

28 28 

29* **Subscription**: requires a Max plan. Pro plan support is coming soon. API keys are not supported.29* **Subscription**: available on Pro, Max, Team, and Enterprise plans. Team and Enterprise admins must first enable Claude Code in [admin settings](https://claude.ai/admin-settings/claude-code). API keys are not supported.

30* **Authentication**: run `claude` and use `/login` to sign in through claude.ai if you haven't already.30* **Authentication**: run `claude` and use `/login` to sign in through claude.ai if you haven't already.

31* **Workspace trust**: run `claude` in your project directory at least once to accept the workspace trust dialog.31* **Workspace trust**: run `claude` in your project directory at least once to accept the workspace trust dialog.

32 32 

54 <Tab title="From an existing session">54 <Tab title="From an existing session">

55 If you're already in a Claude Code session and want to continue it remotely, use the `/remote-control` (or `/rc`) command:55 If you're already in a Claude Code session and want to continue it remotely, use the `/remote-control` (or `/rc`) command:

56 56 

57 ```57 ```text theme={null}

58 /remote-control58 /remote-control

59 ```59 ```

60 60 

61 Pass a name as an argument to set a custom session title:61 Pass a name as an argument to set a custom session title:

62 62 

63 ```63 ```text theme={null}

64 /remote-control My Project64 /remote-control My Project

65 ```65 ```

66 66 

92You can enable sandboxing by running the `/sandbox` command:92You can enable sandboxing by running the `/sandbox` command:

93 93 

94```text theme={null}94```text theme={null}

95> /sandbox95/sandbox

96```96```

97 97 

98This opens a menu where you can choose between sandbox modes. If required dependencies are missing (such as `bubblewrap` or `socat` on Linux), the menu displays installation instructions for your platform.98This opens a menu where you can choose between sandbox modes. If required dependencies are missing (such as `bubblewrap` or `socat` on Linux), the menu displays installation instructions for your platform.

224 224 

225When running the install command, you may see one of these errors:225When running the install command, you may see one of these errors:

226 226 

227```227```text theme={null}

228bash: line 1: syntax error near unexpected token `<'228bash: line 1: syntax error near unexpected token `<'

229bash: line 1: `<!DOCTYPE html>'229bash: line 1: `<!DOCTYPE html>'

230```230```

231 231 

232On PowerShell, the same problem appears as:232On PowerShell, the same problem appears as:

233 233 

234```234```text theme={null}

235Invoke-Expression: Missing argument in parameter list.235Invoke-Expression: Missing argument in parameter list.

236```236```

237 237 

386 386 

387If you see `Killed` during installation on a VPS or cloud instance:387If you see `Killed` during installation on a VPS or cloud instance:

388 388 

389```389```text theme={null}

390Setting up Claude Code...390Setting up Claude Code...

391Installing Claude Code native build latest...391Installing Claude Code native build latest...

392bash: line 142: 34803 Killed "$binary_path" install ${TARGET:+"$TARGET"}392bash: line 142: 34803 Killed "$binary_path" install ${TARGET:+"$TARGET"}

462 462 

463If you see errors about missing shared libraries like `libstdc++.so.6` or `libgcc_s.so.1` after installation, the installer may have downloaded the wrong binary variant for your system.463If you see errors about missing shared libraries like `libstdc++.so.6` or `libgcc_s.so.1` after installation, the installer may have downloaded the wrong binary variant for your system.

464 464 

465```465```text theme={null}

466Error loading shared library libstdc++.so.6: No such file or directory466Error loading shared library libstdc++.so.6: No such file or directory

467```467```

468 468 

487 487 

488If the installer prints `Illegal instruction` instead of the OOM `Killed` message, the downloaded binary doesn't match your CPU architecture. This commonly happens on ARM servers that receive an x86 binary, or on older CPUs that lack required instruction sets.488If the installer prints `Illegal instruction` instead of the OOM `Killed` message, the downloaded binary doesn't match your CPU architecture. This commonly happens on ARM servers that receive an x86 binary, or on older CPUs that lack required instruction sets.

489 489 

490```490```text theme={null}

491bash: line 142: 2238232 Illegal instruction "$binary_path" install ${TARGET:+"$TARGET"}491bash: line 142: 2238232 Illegal instruction "$binary_path" install ${TARGET:+"$TARGET"}

492```492```

493 493 

508 508 

509If you see `dyld: cannot load` or `Abort trap: 6` during installation, the binary is incompatible with your macOS version or hardware.509If you see `dyld: cannot load` or `Abort trap: 6` during installation, the binary is incompatible with your macOS version or hardware.

510 510 

511```511```text theme={null}

512dyld: cannot load 'claude-2.1.42-darwin-x64' (load command 0x80000034 is unknown)512dyld: cannot load 'claude-2.1.42-darwin-x64' (load command 0x80000034 is unknown)

513Abort trap: 6513Abort trap: 6

514```514```

48 48 

49 Other ways to open Claude Code:49 Other ways to open Claude Code:

50 50 

51 * **Activity Bar**: click the Spark icon in the left sidebar to open the sessions list. Click any session to open it as a full editor tab, or start a new one. This icon is always visible in the Activity Bar.

51 * **Command Palette**: `Cmd+Shift+P` (Mac) or `Ctrl+Shift+P` (Windows/Linux), type "Claude Code", and select an option like "Open in New Tab"52 * **Command Palette**: `Cmd+Shift+P` (Mac) or `Ctrl+Shift+P` (Windows/Linux), type "Claude Code", and select an option like "Open in New Tab"

52 * **Status Bar**: click **✱ Claude Code** in the bottom-right corner of the window. This works even when no file is open.53 * **Status Bar**: click **✱ Claude Code** in the bottom-right corner of the window. This works even when no file is open.

53 54 

83 84 

84The prompt box supports several features:85The prompt box supports several features:

85 86 

86* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch modes. In normal mode, Claude asks permission before each action. In Plan mode, Claude describes what it will do and waits for approval before making changes. In auto-accept mode, Claude makes edits without asking. Set the default in VS Code settings under `claudeCode.initialPermissionMode`.87* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch modes. In normal mode, Claude asks permission before each action. In Plan mode, Claude describes what it will do and waits for approval before making changes. VS Code automatically opens the plan as a full markdown document where you can add inline comments to give feedback before Claude begins. In auto-accept mode, Claude makes edits without asking. Set the default in VS Code settings under `claudeCode.initialPermissionMode`.

87* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, toggling extended thinking, and viewing plan usage (`/usage`). The Customize section provides access to MCP servers, hooks, memory, permissions, and plugins. Items with a terminal icon open in the integrated terminal.88* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, toggling extended thinking, and viewing plan usage (`/usage`). The Customize section provides access to MCP servers, hooks, memory, permissions, and plugins. Items with a terminal icon open in the integrated terminal.

88* **Context indicator**: the prompt box shows how much of Claude's context window you're using. Claude automatically compacts when needed, or you can run `/compact` manually.89* **Context indicator**: the prompt box shows how much of Claude's context window you're using. Claude automatically compacts when needed, or you can run `/compact` manually.

89* **Extended thinking**: lets Claude spend more time reasoning through complex problems. Toggle it on via the command menu (`/`). See [Extended thinking](/en/common-workflows#use-extended-thinking-thinking-mode) for details.90* **Extended thinking**: lets Claude spend more time reasoning through complex problems. Toggle it on via the command menu (`/`). See [Extended thinking](/en/common-workflows#use-extended-thinking-thinking-mode) for details.

143* **Editor area**: opens Claude as a tab alongside your files. Useful for side tasks.144* **Editor area**: opens Claude as a tab alongside your files. Useful for side tasks.

144 145 

145<Tip>146<Tip>

146 Use the sidebar for your main Claude session and open additional tabs for side tasks. Claude remembers your preferred location. Note that the Spark icon only appears in the Activity Bar when the Claude panel is docked to the left. Since Claude defaults to the right side, use the Editor Toolbar icon to open Claude.147 Use the sidebar for your main Claude session and open additional tabs for side tasks. Claude remembers your preferred location. The Activity Bar sessions list icon is separate from the Claude panel: the sessions list is always visible in the Activity Bar, while the Claude panel icon only appears there when the panel is docked to the left sidebar.

147</Tip>148</Tip>

148 149 

149### Run multiple conversations150### Run multiple conversations

267Claude Code is available as both a VS Code extension (graphical panel) and a CLI (command-line interface in the terminal). Some features are only available in the CLI. If you need a CLI-only feature, run `claude` in VS Code's integrated terminal.268Claude Code is available as both a VS Code extension (graphical panel) and a CLI (command-line interface in the terminal). Some features are only available in the CLI. If you need a CLI-only feature, run `claude` in VS Code's integrated terminal.

268 269 

269| Feature | CLI | VS Code Extension |270| Feature | CLI | VS Code Extension |

270| ------------------- | --------------------------------------------- | ---------------------------------------- |271| ------------------- | --------------------------------------------- | ------------------------------------------------------------------------------------ |

271| Commands and skills | [All](/en/interactive-mode#built-in-commands) | Subset (type `/` to see available) |272| Commands and skills | [All](/en/interactive-mode#built-in-commands) | Subset (type `/` to see available) |

272| MCP server config | Yes | No (configure via CLI, use in extension) |273| MCP server config | Yes | Partial (add servers via CLI; manage existing servers with `/mcp` in the chat panel) |

273| Checkpoints | Yes | Yes |274| Checkpoints | Yes | Yes |

274| `!` bash shortcut | Yes | No |275| `!` bash shortcut | Yes | No |

275| Tab completion | Yes | No |276| Tab completion | Yes | No |

304 305 

305### Connect to external tools with MCP306### Connect to external tools with MCP

306 307 

307MCP (Model Context Protocol) servers give Claude access to external tools, databases, and APIs. Configure them via CLI, then use them in both extension and CLI.308MCP (Model Context Protocol) servers give Claude access to external tools, databases, and APIs.

308 309 

309To add an MCP server, open the integrated terminal (`` Ctrl+` `` or `` Cmd+` ``) and run:310To add an MCP server, open the integrated terminal (`` Ctrl+` `` or `` Cmd+` ``) and run:

310 311 

312claude mcp add --transport http github https://api.githubcopilot.com/mcp/313claude mcp add --transport http github https://api.githubcopilot.com/mcp/

313```314```

314 315 

315Once configured, ask Claude to use the tools (e.g., "Review PR #456"). Some servers require authentication: run `claude` in the terminal, then type `/mcp` to authenticate. See the [MCP documentation](/en/mcp) for available servers.316Once configured, ask Claude to use the tools (e.g., "Review PR #456").

317 

318To manage MCP servers without leaving VS Code, type `/mcp` in the chat panel. The MCP management dialog lets you enable or disable servers, reconnect to a server, and manage OAuth authentication. See the [MCP documentation](/en/mcp) for available servers.

316 319 

317## Work with git320## Work with git

318 321 

423Now that you have Claude Code set up in VS Code:426Now that you have Claude Code set up in VS Code:

424 427 

425* [Explore common workflows](/en/common-workflows) to get the most out of Claude Code428* [Explore common workflows](/en/common-workflows) to get the most out of Claude Code

426* [Set up MCP servers](/en/mcp) to extend Claude's capabilities with external tools. Configure servers using the CLI, then use them in the extension.429* [Set up MCP servers](/en/mcp) to extend Claude's capabilities with external tools. Add servers using the CLI, then manage them with `/mcp` in the chat panel.

427* [Configure Claude Code settings](/en/settings) to customize allowed commands, hooks, and more. These settings are shared between the extension and CLI.430* [Configure Claude Code settings](/en/settings) to customize allowed commands, hooks, and more. These settings are shared between the extension and CLI.