SpyBara
Go Premium

Documentation 2026-07-10 17:00 UTC to 2026-07-11 19:03 UTC

20 files changed +231 −30. View all changes and history on the product overview
2026
Sat 11 19:03 Fri 10 17:00 Thu 9 23:58 Wed 8 16:02 Tue 7 16:02 Mon 6 23:57 Sat 4 03:01 Fri 3 23:00 Thu 2 23:59 Wed 1 21:01
Details

783 783 

784* **[Custom tools guide](/en/agent-sdk/custom-tools)**: Build your own MCP server that runs in-process with your SDK application784* **[Custom tools guide](/en/agent-sdk/custom-tools)**: Build your own MCP server that runs in-process with your SDK application

785* **[Permissions](/en/agent-sdk/permissions)**: Control which MCP tools your agent can use with `allowedTools` and `disallowedTools`785* **[Permissions](/en/agent-sdk/permissions)**: Control which MCP tools your agent can use with `allowedTools` and `disallowedTools`

786* **[MCP output limits and warnings](/en/mcp#mcp-output-limits-and-warnings)**: How the SDK handles tool results that exceed `MAX_MCP_OUTPUT_TOKENS`, including the persist-to-disk fallback and the `anthropic/maxResultSizeChars` per-tool annotation

786* **[TypeScript SDK reference](/en/agent-sdk/typescript)**: Full API reference including MCP configuration options787* **[TypeScript SDK reference](/en/agent-sdk/typescript)**: Full API reference including MCP configuration options

787* **[Python SDK reference](/en/agent-sdk/python)**: Full API reference including MCP configuration options788* **[Python SDK reference](/en/agent-sdk/python)**: Full API reference including MCP configuration options

788* **[MCP server directory](https://github.com/modelcontextprotocol/servers)**: Browse available MCP servers for databases, APIs, and more789* **[MCP server directory](https://github.com/modelcontextprotocol/servers)**: Browse available MCP servers for databases, APIs, and more

Details

247 247 

248Set these environment variables to specific Amazon Bedrock model IDs.248Set these environment variables to specific Amazon Bedrock model IDs.

249 249 

250Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Amazon Bedrock resolves to Opus 4.6. Set it to the Opus 4.8 ID to use the latest model:250Without these variables, the `opus` alias on Amazon Bedrock resolves to Opus 4.8 and the `sonnet` alias resolves to Sonnet 4.5. Set each variable to pin its alias to a specific version:

251 251 

252```bash theme={null}252```bash theme={null}

253export ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'253export ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'


260Claude Code uses these default models when no pinning variables are set:260Claude Code uses these default models when no pinning variables are set:

261 261 

262| Model type | Default value |262| Model type | Default value |

263| :--------------- | :--------------------------------------------- |263| :--------------- | :----------------------------- |

264| Primary model | `us.anthropic.claude-sonnet-4-5-20250929-v1:0` |264| Primary model | `us.anthropic.claude-opus-4-8` |

265| Small/fast model | Same as primary model |265| Small/fast model | Same as primary model |

266 266 

267Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Amazon Bedrock, Claude Code defaults this to the primary model because Haiku may not be enabled in every account or region. To use Haiku for background tasks, set `ANTHROPIC_DEFAULT_HAIKU_MODEL` to a model ID that is available in your account.267Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Amazon Bedrock, Claude Code defaults this to the primary model because Haiku may not be enabled in every account or region. To use Haiku for background tasks, set `ANTHROPIC_DEFAULT_HAIKU_MODEL` to a model ID that is available in your account.

Details

266 266 

267### 3. Pin model versions267### 3. Pin model versions

268 268 

269Claude Platform on AWS uses the same model IDs as the direct Claude API. The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias resolves to Opus 4.7.269Claude Platform on AWS uses the same model IDs as the direct Claude API. The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias resolves to Opus 4.8.

270 270 

271If you deploy Claude Code to a team, pin the model IDs explicitly so a new release doesn't move everyone at once:271If you deploy Claude Code to a team, pin the model IDs explicitly so a new release doesn't move everyone at once:

272 272 

273```bash theme={null}273```bash theme={null}

274export ANTHROPIC_DEFAULT_FABLE_MODEL=claude-fable-5274export ANTHROPIC_DEFAULT_FABLE_MODEL=claude-fable-5

275export ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-4-7275export ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-4-8

276export ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-5276export ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-5

277export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-haiku-4-5277export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-haiku-4-5

278```278```

Details

303it to ship. You shouldn't have to pick one forever.303it to ship. You shouldn't have to pick one forever.

304 304 

305*Shift+Tab* cycles through how much Claude can do without asking: *Manual* (the305*Shift+Tab* cycles through how much Claude can do without asking: *Manual* (the

306`default` setting value) asks before each action, *acceptEdits* lets file306`default` setting value) asks before file edits and most shell commands, *acceptEdits* lets file

307edits and common filesystem commands307edits and common filesystem commands

308flow through while still checking before other shell commands, and *plan*308flow through while still checking before other shell commands, and *plan*

309proposes changes for your approval before anything is touched. Plan mode is309proposes changes for your approval before anything is touched. Plan mode is


502One-line replies for the questions you will be asked most.502One-line replies for the questions you will be asked most.

503 503 

504| Question | Response |504| Question | Response |

505| ---------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |505| ---------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

506| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/en/vs-code) |506| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/en/vs-code) |

507| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/en/quickstart) |507| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/en/quickstart) |

508| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. Under your Enterprise plan, your code and prompts are not used to train models. [Data usage →](/en/data-usage) |508| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. Under your Enterprise plan, your code and prompts are not used to train models. [Data usage →](/en/data-usage) |

509| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt; permission prompts gate edits, shell commands, and anything outside that directory. [Permissions →](/en/permissions) |509| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt; permission prompts gate edits, non-read-only shell commands, and file-tool reads outside that directory. A built-in set of read-only shell commands such as `ls` and `cat` runs without prompting; restrict it with [sandbox `denyRead` rules](/en/sandboxing#filesystem-isolation). [Permissions →](/en/permissions) |

510| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/en/overview) |510| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/en/overview) |

511| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/en/quickstart) |511| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/en/quickstart) |

512 512 

desktop.md +1 −1

Details

84 84 

85<span id="auto-mode-availability" />85<span id="auto-mode-availability" />

86 86 

87Auto mode is a research preview available to all users on the Anthropic API and requires Claude Opus 4.6 or later, or Sonnet 4.6 or later. In Enterprise deployments that route Desktop to Google Cloud's Agent Platform, auto mode is off until you [set `CLAUDE_CODE_ENABLE_AUTO_MODE`](/en/permission-modes#enable-auto-mode-on-bedrock-agent-platform-or-foundry), and only Claude Sonnet 5, Opus 4.7, and Opus 4.8 are supported there.87Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, or Sonnet 4.6 or later. In Enterprise deployments that route Desktop to Google Cloud's Agent Platform, auto mode is off until you [set `CLAUDE_CODE_ENABLE_AUTO_MODE`](/en/permission-modes#enable-auto-mode-on-bedrock-agent-platform-or-foundry), and only Claude Sonnet 5, Opus 4.7, and Opus 4.8 are supported there.

88 88 

89<Tip title="Best practice">89<Tip title="Best practice">

90 Start complex tasks in Plan so Claude maps out an approach before making changes. Once you approve the plan, switch to Accept edits or Manual to execute it. See [explore first, then plan, then code](/en/best-practices#explore-first-then-plan-then-code) for more on this workflow.90 Start complex tasks in Plan so Claude maps out an approach before making changes. Once you approve the plan, switch to Accept edits or Manual to execute it. See [explore first, then plan, then code](/en/best-practices#explore-first-then-plan-then-code) for more on this workflow.

desktop-linux.md +10 −2

Details

69 69 

70### Install from a downloaded file70### Install from a downloaded file

71 71 

72If you can't use the apt repository, first download the `.deb` package for your architecture, x64 or arm64, from [claude.com/download](https://claude.com/download). Then open the downloaded file with your software installer, or install it with apt from the directory that contains the downloaded file:72If you can't install through the apt repository, download the `.deb` package directly from the repository's package pool. This command looks up the newest package for your architecture in the repository index, then downloads it to the current directory:

73 

74```bash theme={null}

75curl -fLO "https://downloads.claude.ai/claude-desktop/apt/stable/$(curl -s "https://downloads.claude.ai/claude-desktop/apt/stable/dists/stable/main/binary-$(dpkg --print-architecture)/Packages" | grep '^Filename: pool/main/c/claude-desktop/claude-desktop_' | sort -V | tail -n 1 | cut -d' ' -f2)"

76```

77 

78If the command fails with `Remote file name has no length`, the lookup returned no package path. This can mean the repository index couldn't be fetched, for example when your network blocks `downloads.claude.ai`, or that no package exists for your architecture. Confirm that your network can reach `downloads.claude.ai` and that `dpkg --print-architecture` prints `amd64` or `arm64`; the repository doesn't publish packages for other architectures.

79 

80Then open the downloaded file with your software installer, such as GNOME Software, or install it with apt from the directory that contains the downloaded file:

73 81 

74```bash theme={null}82```bash theme={null}

75sudo apt install ./claude-desktop_*.deb83sudo apt install ./claude-desktop_*.deb


77 85 

78If apt reports `E: Unsupported file ./claude-desktop_*.deb given on commandline`, the pattern didn't match a `.deb` file in the current directory. Confirm the download completed, then run the command again from the directory that contains the file.86If apt reports `E: Unsupported file ./claude-desktop_*.deb given on commandline`, the pattern didn't match a `.deb` file in the current directory. Confirm the download completed, then run the command again from the directory that contains the file.

79 87 

80A `.deb` installed this way doesn't receive updates. To get updates through apt, add the repository as shown above, or uncomment the `deb` line in the placeholder entry the package writes to `/etc/apt/sources.list.d/claude-desktop.list`.88A `.deb` installed this way doesn't receive updates. To get updates through apt, register the repository from the [Add Anthropic's apt repository](#install) step. The package also writes a commented-out repository entry to `/etc/apt/sources.list.d/claude-desktop.list`; uncommenting its `deb` line is equivalent.

81 89 

82## Update90## Update

83 91 

glossary.md +1 −1

Details

48 48 

49### Auto mode49### Auto mode

50 50 

51A [permission mode](#permission-mode) where a separate classifier model reviews actions in the background, so most run without approval prompts; explicit ask rules still prompt. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). It never sees tool results, so injected instructions cannot influence its decisions. Auto mode is a research preview.51A [permission mode](#permission-mode) where a separate classifier model reviews actions in the background, so most run without approval prompts; explicit ask rules still prompt. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). It never sees tool results, so injected instructions cannot influence its decisions.

52 52 

53Learn more: [Eliminate prompts with auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode)53Learn more: [Eliminate prompts with auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode)

54 54 

Details

212 212 

213Set these environment variables to specific Google Cloud's Agent Platform model IDs.213Set these environment variables to specific Google Cloud's Agent Platform model IDs.

214 214 

215Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Google Cloud's Agent Platform resolves to Opus 4.6. Set it to the Opus 4.8 ID to use the latest model:215Without these variables, the `opus` alias on Google Cloud's Agent Platform resolves to Opus 4.8 and the `sonnet` alias resolves to Sonnet 4.5. Set each variable to pin its alias to a specific version:

216 216 

217```bash theme={null}217```bash theme={null}

218export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'218export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'


225Claude Code uses these default models when no pinning variables are set:225Claude Code uses these default models when no pinning variables are set:

226 226 

227| Model type | Default value |227| Model type | Default value |

228| :--------------- | :--------------------------- |228| :--------------- | :-------------------- |

229| Primary model | `claude-sonnet-4-5@20250929` |229| Primary model | `claude-opus-4-8` |

230| Small/fast model | Same as primary model |230| Small/fast model | Same as primary model |

231 231 

232Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Google Cloud's Agent Platform, Claude Code defaults this to the primary model because Haiku may not be enabled in every project or region. To use Haiku for background tasks, set `ANTHROPIC_DEFAULT_HAIKU_MODEL` to a model ID that is available in your project.232Background tasks such as session title generation use the small/fast model, normally a Haiku-class model. On Google Cloud's Agent Platform, Claude Code defaults this to the primary model because Haiku may not be enabled in every project or region. To use Haiku for background tasks, set `ANTHROPIC_DEFAULT_HAIKU_MODEL` to a model ID that is available in your project.

Details

157* **Manual**: Claude asks before file edits and shell commands157* **Manual**: Claude asks before file edits and shell commands

158* **Accept edits**: Claude edits files and runs common filesystem commands like `mkdir` and `mv` without asking, still asks for other commands158* **Accept edits**: Claude edits files and runs common filesystem commands like `mkdir` and `mv` without asking, still asks for other commands

159* **Plan**: Claude explores and proposes a plan without editing your source files; permission prompts still apply as in Manual mode159* **Plan**: Claude explores and proposes a plan without editing your source files; permission prompts still apply as in Manual mode

160* **Auto**: Claude evaluates all actions with background safety checks. Currently a research preview160* **Auto**: Claude evaluates all actions with background safety checks

161 161 

162You can also allow specific commands in `.claude/settings.json` so Claude doesn't ask each time. This is useful for trusted commands like `npm test` or `git status`. Settings can be scoped from organization-wide policies down to personal preferences. See [Permissions](/en/permissions) for details.162You can also allow specific commands in `.claude/settings.json` so Claude doesn't ask each time. This is useful for trusted commands like `npm test` or `git status`. Settings can be scoped from organization-wide policies down to personal preferences. See [Permissions](/en/permissions) for details.

163 163 

model-config.md +12 −4

Details

38| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions |38| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions |

39| **`opusplan`** | Special mode that uses `opus` during plan mode, then switches to `sonnet` for execution |39| **`opusplan`** | Special mode that uses `opus` during plan mode, then switches to `sonnet` for execution |

40 40 

41On the Anthropic API, `opus` resolves to Opus 4.8 and `sonnet` resolves to Sonnet 5. On [Claude Platform on AWS](/en/claude-platform-on-aws), `opus` resolves to Opus 4.7 and `sonnet` resolves to Sonnet 4.6. On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, `opus` resolves to Opus 4.6 and `sonnet` resolves to Sonnet 4.5; newer models are available on those providers by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.41What each alias resolves to depends on the provider:

42 

43* **Anthropic API**: `opus` resolves to Opus 4.8 and `sonnet` resolves to Sonnet 5.

44* **[Claude Platform on AWS](/en/claude-platform-on-aws)**: `opus` resolves to Opus 4.8 and `sonnet` resolves to Sonnet 4.6.

45* **Amazon Bedrock and Google Cloud's Agent Platform**: `opus` resolves to Opus 4.8 and `sonnet` resolves to Sonnet 4.5.

46* **Microsoft Foundry**: `opus` resolves to Opus 4.6 and `sonnet` resolves to Sonnet 4.5.

47 

48Where an alias resolves to an older model, newer models are available by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.

42 49 

43Aliases point to the recommended version for your provider and update over time. To pin to a specific version, use the full model name, for example `claude-opus-4-8`, or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.50Aliases point to the recommended version for your provider and update over time. To pin to a specific version, use the full model name, for example `claude-opus-4-8`, or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.

44 51 


307The behavior of `default` depends on your account type:314The behavior of `default` depends on your account type:

308 315 

309* **Max, Team Premium, Enterprise pay-as-you-go, and Anthropic API**: defaults to Opus 4.8316* **Max, Team Premium, Enterprise pay-as-you-go, and Anthropic API**: defaults to Opus 4.8

310* **Claude Platform on AWS**: defaults to Opus 4.7317* **Claude Platform on AWS**: defaults to Opus 4.8

311* **Pro, Team Standard, and Enterprise subscription seats**: defaults to Sonnet 5318* **Pro, Team Standard, and Enterprise subscription seats**: defaults to Sonnet 5

312* **Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry**: defaults to Sonnet 4.5319* **Amazon Bedrock and Google Cloud's Agent Platform**: defaults to Opus 4.8

320* **Microsoft Foundry**: defaults to Sonnet 4.5

313 321 

314Enterprise pay-as-you-go means an Enterprise organization billed by usage rather than by subscription seat.322Enterprise pay-as-you-go means an Enterprise organization billed by usage rather than by subscription seat.

315 323 


367 375 

368This section covers content-based fallback from Fable 5. For availability-based fallback when a model is overloaded or unavailable, see [Fallback model chains](#fallback-model-chains).376This section covers content-based fallback from Fable 5. For availability-based fallback when a model is overloaded or unavailable, see [Fallback model chains](#fallback-model-chains).

369 377 

370Fable 5 runs with safety classifiers for cybersecurity and biology content. When a classifier flags a request, Claude Code re-runs that request on the default Opus model and shows a notice in the transcript: Opus 4.8 on the Anthropic API and [LLM gateway](/en/llm-gateway) deployments, or Opus 4.7 on [Claude Platform on AWS](/en/claude-platform-on-aws).378Fable 5 runs with safety classifiers for cybersecurity and biology content. When a classifier flags a request, Claude Code re-runs that request on Opus 4.8 and shows a notice in the transcript.

371 379 

372The session then continues on that Opus model. To return to Fable 5, run `/model fable`.380The session then continues on that Opus model. To return to Fable 5, run `/model fable`.

373 381 

Details

177Auto mode also nudges Claude to keep working without stopping for clarifying questions, though Claude still asks when your prompt or a skill explicitly relies on it. For stronger autonomous behavior while keeping permission prompts, set the [Proactive output style](/en/output-styles) instead.177Auto mode also nudges Claude to keep working without stopping for clarifying questions, though Claude still asks when your prompt or a skill explicitly relies on it. For stronger autonomous behavior while keeping permission prompts, set the [Proactive output style](/en/output-styles) instead.

178 178 

179<Warning>179<Warning>

180 Auto mode is a research preview. It reduces permission prompts but does not guarantee safety. Use it for tasks where you trust the general direction, not as a replacement for review on sensitive operations.180 Auto mode reduces permission prompts but does not guarantee safety. Use it for tasks where you trust the general direction, not as a replacement for review on sensitive operations.

181</Warning>181</Warning>

182 182 

183Auto mode is available only when your account meets all of these requirements:183Auto mode is available only when your account meets all of these requirements:

permissions.md +4 −4

Details

13Claude Code uses a tiered permission system to balance power and safety:13Claude Code uses a tiered permission system to balance power and safety:

14 14 

15| Tool type | Example | Approval required | "Yes, don't ask again" behavior |15| Tool type | Example | Approval required | "Yes, don't ask again" behavior |

16| :---------------- | :--------------- | :---------------- | :-------------------------------------------- |16| :---------------- | :--------------- | :---------------------------------------------------------------------------------- | :-------------------------------------------- |

17| Read-only | File reads, Grep | No | N/A |17| Read-only | File reads, Grep | No, within the [working directory and additional directories](#working-directories) | N/A |

18| Bash commands | Shell execution | Yes | Permanently per project directory and command |18| Bash commands | Shell execution | Yes, except a built-in set of [read-only commands](#read-only-commands) | Permanently per project directory and command |

19| File modification | Edit/write files | Yes | Until session end |19| File modification | Edit/write files | Yes | Until session end |

20 20 

21## Manage permissions21## Manage permissions


45| `default` | Standard behavior: prompts for permission on first use of each tool. {/* min-version: 2.1.200 */}Labeled Manual in the CLI and the VS Code and JetBrains extensions, and Claude Code accepts `manual` as an alias. The label and alias require Claude Code v2.1.200 or later |45| `default` | Standard behavior: prompts for permission on first use of each tool. {/* min-version: 2.1.200 */}Labeled Manual in the CLI and the VS Code and JetBrains extensions, and Claude Code accepts `manual` as an alias. The label and alias require Claude Code v2.1.200 or later |

46| `acceptEdits` | Automatically accepts file edits and common filesystem commands such as `mkdir`, `touch`, `mv`, and `cp` for paths in the working directory or `additionalDirectories` |46| `acceptEdits` | Automatically accepts file edits and common filesystem commands such as `mkdir`, `touch`, `mv`, and `cp` for paths in the working directory or `additionalDirectories` |

47| `plan` | Claude reads files and runs read-only shell commands to explore but doesn't edit your source files. Labeled Plan in the CLI and the VS Code extension |47| `plan` | Claude reads files and runs read-only shell commands to explore but doesn't edit your source files. Labeled Plan in the CLI and the VS Code extension |

48| `auto` | Auto-approves tool calls with background safety checks that verify actions align with your request. Currently a research preview |48| `auto` | Auto-approves tool calls with background safety checks that verify actions align with your request |

49| `dontAsk` | Auto-denies tools unless pre-approved via `/permissions` or `permissions.allow` rules |49| `dontAsk` | Auto-denies tools unless pre-approved via `/permissions` or `permissions.allow` rules |

50| `bypassPermissions` | Skips permission prompts, except those forced by explicit `ask` rules. Root and home directory removals such as `rm -rf /` also still prompt as a circuit breaker |50| `bypassPermissions` | Skips permission prompts, except those forced by explicit `ask` rules. Root and home directory removals such as `rm -rf /` also still prompt as a circuit breaker |

51 51 

security.md +2 −2

Details

16 16 

17Claude Code uses strict read-only permissions by default. When additional actions are needed (editing files, running tests, executing commands), Claude Code requests explicit permission. Users control whether to approve actions once or allow them automatically.17Claude Code uses strict read-only permissions by default. When additional actions are needed (editing files, running tests, executing commands), Claude Code requests explicit permission. Users control whether to approve actions once or allow them automatically.

18 18 

19Claude Code requires approval before running Bash commands that can modify your system. A built-in set of read-only commands such as `ls`, `cat`, and `git status` runs without a prompt. This approach lets users and organizations configure permissions directly.19Claude Code requires approval before running Bash commands that can modify your system. A built-in set of [read-only commands](/en/permissions#read-only-commands) such as `ls`, `cat`, and `git status` runs without a prompt. This approach lets users and organizations configure permissions directly.

20 20 

21For detailed permission configuration, see [Permissions](/en/permissions).21For detailed permission configuration, see [Permissions](/en/permissions).

22 22 


25To mitigate risks in agentic systems:25To mitigate risks in agentic systems:

26 26 

27* **Sandboxed bash tool**: [Sandbox](/en/sandboxing) bash commands with filesystem and network isolation, reducing permission prompts while maintaining security. Enable with `/sandbox` to define boundaries where Claude Code can work autonomously27* **Sandboxed bash tool**: [Sandbox](/en/sandboxing) bash commands with filesystem and network isolation, reducing permission prompts while maintaining security. Enable with `/sandbox` to define boundaries where Claude Code can work autonomously

28* **Write access restriction**: Claude Code can only write to the folder where it was started and its subfolders—it cannot modify files in parent directories without explicit permission. While Claude Code can read files outside the working directory (useful for accessing system libraries and dependencies), write operations are strictly confined to the project scope, creating a clear security boundary28* **Working directory boundary**: Claude Code can only write to the folder where it was started and its subfolders, and cannot modify files in parent directories without explicit permission. Reading paths outside this boundary with the Read, Grep, and Glob tools is possible after an approval prompt. Extend the boundary with [additional directories](/en/permissions#working-directories) to skip the prompt, or restrict the broader read access available to read-only Bash commands with [sandbox `denyRead` rules](/en/sandboxing#filesystem-isolation), which apply only when sandboxing is enabled

29* **Prompt fatigue mitigation**: Support for allowlisting frequently used safe commands per-user, per-codebase, or per-organization29* **Prompt fatigue mitigation**: Support for allowlisting frequently used safe commands per-user, per-codebase, or per-organization

30* **Accept Edits mode**: Auto-approves file edits and a fixed set of filesystem Bash commands like `mkdir`, `touch`, `rm`, `mv`, `cp`, and `sed` for paths in the working directory. Other Bash commands and out-of-scope paths still prompt30* **Accept Edits mode**: Auto-approves file edits and a fixed set of filesystem Bash commands like `mkdir`, `touch`, `rm`, `mv`, `cp`, and `sed` for paths in the working directory. Other Bash commands and out-of-scope paths still prompt

31 31 

setup.md +1 −1

Details

30## Install Claude Code30## Install Claude Code

31 31 

32<Tip>32<Tip>

33 Prefer a graphical interface? The [Desktop app](/en/desktop-quickstart) lets you use Claude Code without the terminal. Download it for [macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code\&utm_medium=docs), [Windows](https://claude.com/download?utm_source=claude_code\&utm_medium=docs), or [Linux](https://claude.com/download?utm_source=claude_code\&utm_medium=docs).33 Prefer a graphical interface? The [Desktop app](/en/desktop-quickstart) lets you use Claude Code without the terminal. Download it for [macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code\&utm_medium=docs), [Windows](https://claude.com/download?utm_source=claude_code\&utm_medium=docs), or [Linux](/en/desktop-linux).

34 34 

35 New to the terminal? See the [terminal guide](/en/terminal-guide) for step-by-step instructions.35 New to the terminal? See the [terminal guide](/en/terminal-guide) for step-by-step instructions.

36</Tip>36</Tip>

Details

10 10 

11To add custom tools, connect an [MCP server](/en/mcp). To extend Claude with reusable prompt-based workflows, write a [skill](/en/skills), which runs through the existing `Skill` tool rather than adding a new tool entry.11To add custom tools, connect an [MCP server](/en/mcp). To extend Claude with reusable prompt-based workflows, write a [skill](/en/skills), which runs through the existing `Skill` tool rather than adding a new tool entry.

12 12 

13The Permission required column shows whether the tool prompts in the default permission mode for paths inside the working directory. File-access tools marked No, including `Read`, `Grep`, and `Glob`, still prompt for paths outside the [working directory and additional directories](/en/permissions#working-directories). `Bash` is marked Yes but runs a built-in set of [read-only commands](/en/permissions#read-only-commands) without prompting.

14 

13| Tool | Description | Permission required |15| Tool | Description | Permission required |

14| :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ |16| :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ |

15| `Agent` | Spawns a [subagent](/en/sub-agents) with its own context window to handle a task. See [Agent tool behavior](#agent-tool-behavior) | No |17| `Agent` | Spawns a [subagent](/en/sub-agents) with its own context window to handle a task. See [Agent tool behavior](#agent-tool-behavior) | No |

Details

44If your issue isn't listed, work through the diagnostic checks below to narrow down the cause.44If your issue isn't listed, work through the diagnostic checks below to narrow down the cause.

45 45 

46<Tip>46<Tip>

47 If you'd rather skip the terminal entirely, the [Claude Code Desktop app](/en/desktop-quickstart) lets you install and use Claude Code through a graphical interface. Download it for [macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code\&utm_medium=docs), [Windows](https://claude.com/download?utm_source=claude_code\&utm_medium=docs), or [Linux](https://claude.com/download?utm_source=claude_code\&utm_medium=docs) and start coding without any command-line setup.47 If you'd rather skip the terminal entirely, the [Claude Code Desktop app](/en/desktop-quickstart) lets you install and use Claude Code through a graphical interface. Download it for [macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code\&utm_medium=docs) or [Windows](https://claude.com/download?utm_source=claude_code\&utm_medium=docs) and start coding without any command-line setup. On Linux, install the app with apt by following the [Linux install instructions](/en/desktop-linux).

48</Tip>48</Tip>

49 49 

50## Run diagnostic checks50## Run diagnostic checks

vs-code.md +1 −1

Details

95The prompt box supports several features:95The prompt box supports several features:

96 96 

97* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch modes, or set the default in VS Code settings under `claudeCode.initialPermissionMode`. See [permission modes](/en/permission-modes#switch-permission-modes) for every mode the indicator offers.97* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch modes, or set the default in VS Code settings under `claudeCode.initialPermissionMode`. See [permission modes](/en/permission-modes#switch-permission-modes) for every mode the indicator offers.

98 * **Manual**: Claude asks permission before each action.98 * **Manual**: Claude asks permission before file edits and most shell commands.

99 * **Plan**: 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.99 * **Plan**: 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.

100 * **Edit automatically**: Claude makes edits without asking.100 * **Edit automatically**: Claude makes edits without asking.

101* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, toggling extended thinking, viewing plan usage (`/usage`), and starting a [Remote Control](/en/remote-control) session (`/remote-control`). The Customize section provides access to MCP servers, hooks, memory, permissions, and plugins. Items with a terminal icon open in the integrated terminal.101* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, toggling extended thinking, viewing plan usage (`/usage`), and starting a [Remote Control](/en/remote-control) session (`/remote-control`). The Customize section provides access to MCP servers, hooks, memory, permissions, and plugins. Items with a terminal icon open in the integrated terminal.

whats-new.md +16 −0

Details

8 8 

9The weekly dev digest highlights the features most likely to change how you work. Each entry includes runnable code, a short demo, and a link to the full docs. For every bug fix and minor improvement, see the [changelog](/en/changelog).9The weekly dev digest highlights the features most likely to change how you work. Each entry includes runnable code, a short demo, and a link to the full docs. For every bug fix and minor improvement, see the [changelog](/en/changelog).

10 10 

11<Update label="Week 28" description="July 6–10, 2026" tags={["v2.1.202–v2.1.206"]}>

12 **In-app browser on Desktop**: Claude Code on desktop gets a built-in browser, so Claude can pull up docs, designs, or any other site and interact with pages the same way it does with your local dev server previews.

13 

14 Also this week: **`/doctor`** is a full setup checkup that diagnoses issues and can fix them, with `/checkup` as its alias; **auto mode** blocks transcript tampering and asks before `rm -rf` on unresolved variables; and **agent view rows** show a colored state word and a classifier-written headline.

15 

16 [Read the Week 28 digest →](/en/whats-new/2026-w28)

17</Update>

18 

19<Update label="Week 27" description="June 29 – July 3, 2026" tags={["v2.1.195–v2.1.201"]}>

20 **Claude Sonnet 5**: the new default model for Pro, Team Standard, and Enterprise subscription seats, with top-tier coding and tool use at Sonnet pricing, a native 1M-token context window, and adaptive thinking on by default.

21 

22 Also this week: **Claude in Chrome** is generally available on all direct Anthropic plans; **subagents run in the background by default** so Claude keeps working while they run; **Claude Desktop on Linux** lands in beta on Ubuntu and Debian; and **`/radio`** tunes into Claude FM lo-fi radio.

23 

24 [Read the Week 27 digest →](/en/whats-new/2026-w27)

25</Update>

26 

11<Update label="Week 26" description="June 22–26, 2026" tags={["v2.1.185–v2.1.193"]}>27<Update label="Week 26" description="June 22–26, 2026" tags={["v2.1.185–v2.1.193"]}>

12 **`claude mcp login`**: authenticate a configured MCP server from your shell instead of the interactive `/mcp` menu, and clear its stored credentials later with `claude mcp logout`.28 **`claude mcp login`**: authenticate a configured MCP server from your shell instead of the interactive `/mcp` menu, and clear its stored credentials later with `claude mcp logout`.

13 29 

whats-new/2026-w27.md +103 −0 created

Details

1> ## Documentation Index

2> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt

3> Use this file to discover all available pages before exploring further.

4 

5# Week 27 · June 29 – July 3, 2026

6 

7> Claude Sonnet 5 becomes the default model, Claude in Chrome reaches general availability, subagents run in the background by default, Claude Desktop arrives on Linux in beta, and /radio tunes into Claude FM.

8 

9<div className="digest-meta">

10 <span>Releases <a href="/docs/en/changelog#2-1-195">v2.1.195 → v2.1.201</a></span>

11 <span>5 features · June 29 – July 3</span>

12</div>

13 

14<div className="digest-feature">

15 <div className="digest-feature-header">

16 <span className="digest-feature-title">Claude Sonnet 5</span>

17 <span className="digest-feature-pill">new model</span>

18 </div>

19 

20 <p className="digest-feature-lede">Sonnet 5 is the new default model for Pro, Team Standard, and Enterprise subscription seats: top-tier coding and tool use at Sonnet pricing, with a native 1M-token context window and adaptive thinking on by default. API pricing is promotional at \$2/\$10 per MTok through August 31. Requires v2.1.197 or later.</p>

21 

22 <p className="digest-feature-try">Switch to Sonnet 5 by name, or pick it from the model picker:</p>

23 

24 ```text Claude Code theme={null}

25 > /model claude-sonnet-5

26 ```

27 

28 <a className="digest-feature-link" href="/docs/en/model-config#available-models">Model configuration</a>

29</div>

30 

31<div className="digest-feature">

32 <div className="digest-feature-header">

33 <span className="digest-feature-title">Claude in Chrome is generally available</span>

34 <span className="digest-feature-pill">v2.1.198</span>

35 </div>

36 

37 <p className="digest-feature-lede">The Chrome integration is out of preview for everyone on a direct Anthropic plan. Claude Code drives your browser through the Claude in Chrome extension: it opens tabs, clicks through pages, fills forms, reads console logs, and shares your login state, so it can test the app it builds without you switching contexts.</p>

38 

39 <a className="digest-feature-link" href="/docs/en/chrome">Use Claude Code with Chrome</a>

40</div>

41 

42<div className="digest-feature">

43 <div className="digest-feature-header">

44 <span className="digest-feature-title">Subagents run in the background by default</span>

45 <span className="digest-feature-pill">v2.1.198</span>

46 </div>

47 

48 <p className="digest-feature-lede">Claude now keeps working while subagents run and picks up their results when they finish, instead of pausing the conversation to wait. Claude still runs a subagent in the foreground when it needs the result before continuing, and background subagents surface every permission prompt in your main session. Pin a subagent's behavior with the <code>background</code> frontmatter field.</p>

49 

50 <a className="digest-feature-link" href="/docs/en/sub-agents#run-subagents-in-foreground-or-background">Run subagents in foreground or background</a>

51</div>

52 

53<div className="digest-feature">

54 <div className="digest-feature-header">

55 <span className="digest-feature-title">Claude Desktop on Linux</span>

56 <span className="digest-feature-pill">Desktop</span>

57 </div>

58 

59 <p className="digest-feature-lede">The Claude desktop app is now available on Ubuntu 22.04+ and Debian 12+ in beta, on x86\_64 and arm64. You get the same Chat, Cowork, and Claude Code experience as macOS and Windows: parallel sessions, visual diff review, an integrated terminal and editor, and live app preview. Installs from Anthropic's apt repository, so updates arrive through regular package updates.</p>

60 

61 <a className="digest-feature-link" href="/docs/en/desktop-linux">Claude Desktop on Linux</a>

62</div>

63 

64<div className="digest-feature">

65 <div className="digest-feature-header">

66 <span className="digest-feature-title">/radio</span>

67 <span className="digest-feature-pill">CLI</span>

68 </div>

69 

70 <p className="digest-feature-lede">Claude FM is on the air. <code>/radio</code> opens the lo-fi radio stream in your browser for something to code to, and prints the stream URL when no browser is available. Not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry.</p>

71 

72 <Frame>

73 <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/x358isu_VzLnyTEN/images/whats-new/radio.mp4?fit=max&auto=format&n=x358isu_VzLnyTEN&q=85&s=36a0c33859cef119c7192dceea8bcbd3" data-path="images/whats-new/radio.mp4" />

74 </Frame>

75 

76 <p className="digest-feature-try">Tune in from any session:</p>

77 

78 ```text Claude Code theme={null}

79 > /radio

80 ```

81 

82 <a className="digest-feature-link" href="/docs/en/commands#all-commands">All commands</a>

83</div>

84 

85<div className="digest-wins">

86 <p className="digest-wins-title">Other wins</p>

87 

88 <div className="digest-wins-grid">

89 <div><a href="/docs/en/artifacts">Artifacts</a> are now generally available and included on Pro and Max plans, joining Team and Enterprise</div>

90 <div>Admins can set an <a href="/docs/en/model-config#organization-default-model">organization default model</a> in the org console; it shows as "Org default" in <code>/model</code> when you haven't picked a model yourself</div>

91 <div>Stacked skill invocations like <code>/skill-a /skill-b do XYZ</code> now load all leading skills (up to 5), not only the first</div>

92 <div><code>AskUserQuestion</code> dialogs no longer auto-continue by default; opt into an idle timeout via <code>/config</code></div>

93 <div>The "default" permission mode is now named "Manual" across the CLI, `--help`, VS Code, and JetBrains; `--permission-mode manual` is accepted alongside `default`</div>

94 <div>New <code>/dataviz</code> skill gives chart and dashboard design guidance, with a runnable color-palette validator</div>

95 <div>The built-in Explore agent now inherits the main session's model (capped at Opus) instead of running on Haiku</div>

96 <div>Background agents launched from <code>claude agents</code> now commit, push, and open a draft PR when they finish code work in a worktree, instead of stopping to ask</div>

97 <div>Hook matchers with hyphenated identifiers like <code>code-reviewer</code> now exact-match instead of substring-matching; use <code>mcp\_\_brave-search\_\_.\*</code> to match all tools from a hyphenated MCP server</div>

98 <div>Transient server rate-limit errors unrelated to your usage limit are now retried automatically with backoff for subscribers instead of failing the turn</div>

99 <div>The streaming idle watchdog is now on by default for all providers: it aborts and retries when a response stream produces no events for 5 minutes (<code>CLAUDE\_ENABLE\_STREAM\_WATCHDOG=0</code> to disable)</div>

100 </div>

101</div>

102 

103[Full changelog for v2.1.195–v2.1.201 →](/en/changelog#2-1-195)

whats-new/2026-w28.md +63 −0 created

Details

1> ## Documentation Index

2> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt

3> Use this file to discover all available pages before exploring further.

4 

5# Week 28 · July 6–10, 2026

6 

7> Browse external sites from the Desktop app's built-in browser, run a full setup checkup with /doctor, and pick up auto mode transcript protections and agent view upgrades.

8 

9<div className="digest-meta">

10 <span>Releases <a href="/docs/en/changelog#2-1-202">v2.1.202 → v2.1.206</a></span>

11 <span>2 features · July 6–10</span>

12</div>

13 

14<div className="digest-feature">

15 <div className="digest-feature-header">

16 <span className="digest-feature-title">In-app browser on Desktop</span>

17 <span className="digest-feature-pill">Desktop</span>

18 </div>

19 

20 <p className="digest-feature-lede">Claude Code on desktop now has a built-in browser. Claude can pull up docs, designs, or any other site, and read, click through, and interact with pages the same way it does with your local dev server previews. The browser is sandboxed and configurable: you choose whether browsing sessions persist, and safety classifiers review actions on external sites.</p>

21 

22 <Frame>

23 <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/x358isu_VzLnyTEN/images/whats-new/desktop-browser.mp4?fit=max&auto=format&n=x358isu_VzLnyTEN&q=85&s=8033e85a1cb0a37870a79e702c18f4e4" data-path="images/whats-new/desktop-browser.mp4" />

24 </Frame>

25 

26 <a className="digest-feature-link" href="/docs/en/desktop#browse-external-sites">Browse external sites</a>

27</div>

28 

29<div className="digest-feature">

30 <div className="digest-feature-header">

31 <span className="digest-feature-title">/doctor is a full setup checkup</span>

32 <span className="digest-feature-pill">v2.1.205</span>

33 </div>

34 

35 <p className="digest-feature-lede"><code>/doctor</code> now diagnoses issues and can fix them, instead of printing a read-only report. It checks installation health, finds unused skills, MCP servers, and plugins versus their context cost, deduplicates local <code>CLAUDE.md</code> files against checked-in ones, proposes trimming <code>CLAUDE.md</code> content Claude could derive from the codebase, and flags slow hooks. It reports findings first and asks for confirmation before changing anything. <code>/checkup</code> is its alias.</p>

36 

37 <p className="digest-feature-try">Run a checkup from any session:</p>

38 

39 ```text Claude Code theme={null}

40 > /doctor

41 ```

42 

43 <a className="digest-feature-link" href="/docs/en/commands#all-commands">All commands</a>

44</div>

45 

46<div className="digest-wins">

47 <p className="digest-wins-title">Other wins</p>

48 

49 <div className="digest-wins-grid">

50 <div>Auto mode now blocks tampering with session transcript files, and asks before running <code>rm -rf</code> on a variable it can't resolve from context</div>

51 <div><code>/cd</code> now suggests directory paths as you type, matching <code>/add-dir</code></div>

52 <div><code>/commit-push-pr</code> auto-allows <code>git push</code> to the repo's configured push remote in addition to <code>origin</code></div>

53 <div>Gateway: <code>/login</code> now supports Anthropic-operated public gateway endpoints</div>

54 <div><code>EnterWorktree</code> asks for confirmation before entering a git worktree outside the project's <code>.claude/worktrees/</code> directory</div>

55 <div>Background agents upgrade to a new version in the background right after a Claude Code update, instead of paying a slow stale-session upgrade when you attach</div>

56 <div>Agent view rows now show a colored state word and a classifier-written headline instead of raw tool call text, and sessions that edit, merge, comment on, or push to an existing PR link it in <code>claude agents</code></div>

57 <div>Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB</div>

58 <div>Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on</div>

59 <div>Improved <code>/code-review</code> findings quality on Opus 4.8 across all effort levels</div>

60 </div>

61</div>

62 

63[Full changelog for v2.1.202–v2.1.206 →](/en/changelog#2-1-202)