SpyBara
Go Premium

Documentation 2025-10-21 00:04 UTC to 2025-10-23 21:02 UTC

6 files changed +35 −19. View all changes and history on the product overview
2025
Fri 31 00:04 Thu 30 18:02 Wed 29 21:02 Tue 28 18:02 Mon 27 18:02 Fri 24 21:01 Thu 23 21:02 Tue 21 00:04 Mon 20 21:02 Fri 17 18:01 Thu 16 18:02 Wed 15 18:02 Mon 13 21:01
Details

445 445 

446* **Isolated virtual machines**: Each session runs in an isolated, Anthropic-managed VM446* **Isolated virtual machines**: Each session runs in an isolated, Anthropic-managed VM

447* **Network access controls**: Network access is limited by default, and can be disabled447* **Network access controls**: Network access is limited by default, and can be disabled

448 

449<Note>

450 When running with network access disabled, Claude Code is allowed to communicate with the Anthropic API which may still allow data to exit the isolated Claude Code VM.

451</Note>

452 

448* **Credential protection**: Sensitive credentials (such as git credentials or signing keys) are never inside the sandbox with Claude Code. Authentication is handled through a secure proxy using scoped credentials453* **Credential protection**: Sensitive credentials (such as git credentials or signing keys) are never inside the sandbox with Claude Code. Authentication is handled through a secure proxy using scoped credentials

449* **Secure analysis**: Code is analyzed and modified within isolated VMs before creating PRs454* **Secure analysis**: Code is analyzed and modified within isolated VMs before creating PRs

450 455 

plugins.md +2 −2

Details

1# Plugins1# Plugins

2 2 

3> Extend Claude Code with custom commands, agents, hooks, and MCP servers through the plugin system.3> Extend Claude Code with custom commands, agents, hooks, Skills, and MCP servers through the plugin system.

4 4 

5<Tip>5<Tip>

6 For complete technical specifications and schemas, see [Plugins reference](/en/docs/claude-code/plugins-reference). For marketplace management, see [Plugin marketplaces](/en/docs/claude-code/plugin-marketplaces).6 For complete technical specifications and schemas, see [Plugins reference](/en/docs/claude-code/plugins-reference). For marketplace management, see [Plugin marketplaces](/en/docs/claude-code/plugin-marketplaces).

7</Tip>7</Tip>

8 8 

9Plugins let you extend Claude Code with custom functionality that can be shared across projects and teams. Install plugins from [marketplaces](/en/docs/claude-code/plugin-marketplaces) to add pre-built commands, agents, hooks, and MCP servers, or create your own to automate your workflows.9Plugins let you extend Claude Code with custom functionality that can be shared across projects and teams. Install plugins from [marketplaces](/en/docs/claude-code/plugin-marketplaces) to add pre-built commands, agents, hooks, Skills, and MCP servers, or create your own to automate your workflows.

10 10 

11## Quickstart11## Quickstart

12 12 

sandboxing.md +8 −3

Details

73Customize sandbox behavior through your `settings.json` file. See [Settings](/en/docs/claude-code/settings#sandbox-settings) for complete configuration reference.73Customize sandbox behavior through your `settings.json` file. See [Settings](/en/docs/claude-code/settings#sandbox-settings) for complete configuration reference.

74 74 

75<Tip>75<Tip>

76 **Pattern support:**76 Not all commands are compatible with sandboxing out of the box. Some notes that may help you make the most out of the sandbox:

77 77 

78 * Paths support absolute (`/home/user`), relative (`./src`), home directory (`~`), and wildcards (`**/*.json`)78 * Many CLI tools require accessing certain hosts. As you use these tools, they will request permission to access certain hosts. Granting permission will allow them to access these hosts now and in the future, enabling them to safely execute inside the sandbox.

79 * Domains support exact matches (`github.com`), wildcards (`*.npmjs.org`), and subdomains79 * `watchman` is incompatible with running in the sandbox. If you're running `jest`, consider using `jest --no-watchman`

80 * `docker` is incompatible with running in the sandbox. Consider specifying `docker` in `excludedCommands` to force it to run outside of the sandbox.

80</Tip>81</Tip>

81 82 

83<Note>

84 Claude Code includes an intentional escape hatch mechanism that allows commands to run outside the sandbox when necessary. When a command fails due to sandbox restrictions (such as network connectivity issues or incompatible tools), Claude is prompted to analyze the failure and may retry the command with the `dangerouslyDisableSandbox` parameter. Commands that use this parameter go through the normal Claude Code permissions flow requiring user permission to execute. This allows Claude Code to handle edge cases where certain tools or network operations cannot function within sandbox constraints.

85</Note>

86 

82## Security benefits87## Security benefits

83 88 

84### Protection against prompt injection89### Protection against prompt injection

security.md +4 −0

Details

61* **Natural language descriptions**: Complex bash commands include explanations for user understanding61* **Natural language descriptions**: Complex bash commands include explanations for user understanding

62* **Secure credential storage**: API keys and tokens are encrypted. See [Credential Management](/en/docs/claude-code/iam#credential-management)62* **Secure credential storage**: API keys and tokens are encrypted. See [Credential Management](/en/docs/claude-code/iam#credential-management)

63 63 

64<Warning>

65 **Windows WebDAV security risk**: We recommend against enabling WebDAV when running Claude Code on Windows. [WebDAV has been deprecated by Microsoft](https://learn.microsoft.com/en-us/windows/whats-new/deprecated-features#:~:text=The%20Webclient%20\(WebDAV\)%20service%20is%20deprecated) due to security risks. Enabling WebDAV may allow Claude Code to trigger network requests to remote hosts, bypassing the permission system.

66</Warning>

67 

64**Best practices for working with untrusted content**:68**Best practices for working with untrusted content**:

65 69 

661. Review suggested commands before approval701. Review suggested commands before approval

skills.md +15 −6

Details

72 72 

73```yaml theme={null}73```yaml theme={null}

74---74---

75name: Your Skill Name75name: your-skill-name

76description: Brief description of what this Skill does and when to use it76description: Brief description of what this Skill does and when to use it

77---77---

78 78 


85Show concrete examples of using this Skill.85Show concrete examples of using this Skill.

86```86```

87 87 

88**Field requirements**:

89 

90* `name`: Must use lowercase letters, numbers, and hyphens only (max 64 characters)

91* `description`: Brief description of what the Skill does and when to use it (max 1024 characters)

92 

88The `description` field is critical for Claude to discover when to use your Skill. It should include both what the Skill does and when Claude should use it.93The `description` field is critical for Claude to discover when to use your Skill. It should include both what the Skill does and when Claude should use it.

89 94 

90See the [best practices guide](/en/docs/agents-and-tools/agent-skills/best-practices) for complete authoring guidance.95See the [best practices guide](/en/docs/agents-and-tools/agent-skills/best-practices) for complete authoring guidance including validation rules.

91 96 

92## Add supporting files97## Add supporting files

93 98 


123 128 

124```yaml theme={null}129```yaml theme={null}

125---130---

126name: Safe File Reader131name: safe-file-reader

127description: Read files without making changes. Use when you need read-only file access.132description: Read files without making changes. Use when you need read-only file access.

128allowed-tools: Read, Grep, Glob133allowed-tools: Read, Grep, Glob

129---134---


481 486 

482```yaml theme={null}487```yaml theme={null}

483---488---

484name: Generating Commit Messages489name: generating-commit-messages

485description: Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.490description: Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.

486---491---

487 492 


510 515 

511```yaml theme={null}516```yaml theme={null}

512---517---

513name: Code Reviewer518name: code-reviewer

514description: Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.519description: Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality.

515allowed-tools: Read, Grep, Glob520allowed-tools: Read, Grep, Glob

516---521---


549 554 

550````yaml theme={null}555````yaml theme={null}

551---556---

552name: PDF Processing557name: pdf-processing

553description: Extract text, fill forms, merge PDFs. Use when working with PDF files, forms, or document extraction. Requires pypdf and pdfplumber packages.558description: Extract text, fill forms, merge PDFs. Use when working with PDF files, forms, or document extraction. Requires pypdf and pdfplumber packages.

554---559---

555 560 


592 Learn how Skills work across Claude products597 Learn how Skills work across Claude products

593 </Card>598 </Card>

594 599 

600 <Card title="Use Skills in the Agent SDK" icon="cube" href="/en/api/agent-sdk/skills">

601 Use Skills programmatically with TypeScript and Python

602 </Card>

603 

595 <Card title="Get started with Agent Skills" icon="rocket" href="/en/docs/agents-and-tools/agent-skills/quickstart">604 <Card title="Get started with Agent Skills" icon="rocket" href="/en/docs/agents-and-tools/agent-skills/quickstart">

596 Create your first Skill605 Create your first Skill

597 </Card>606 </Card>

vs-code.md +1 −8

Details

30 30 

31Download and install the extension from the [Visual Studio Code Extension Marketplace](https://marketplace.visualstudio.com/items?itemName=anthropic.claude-code).31Download and install the extension from the [Visual Studio Code Extension Marketplace](https://marketplace.visualstudio.com/items?itemName=anthropic.claude-code).

32 32 

33### Updating

34 

35To update the VS Code extension:

36 

371. Open the VS Code command palette with `Cmd+Shift+P` (Mac) or `Ctrl+Shift+P` (Windows/Linux)

382. Search for "Claude Code: Update"

393. Select the command to update to the latest version

40 

41### How It Works33### How It Works

42 34 

43Once installed, you can start using Claude Code through the VS Code interface:35Once installed, you can start using Claude Code through the VS Code interface:


69| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI | | `"your-project-id"` |61| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI | | `"your-project-id"` |

70| `ANTHROPIC_MODEL` | Override primary model | Override model ID | `"us.anthropic.claude-3-7-sonnet-20250219-v1:0"` |62| `ANTHROPIC_MODEL` | Override primary model | Override model ID | `"us.anthropic.claude-3-7-sonnet-20250219-v1:0"` |

71| `ANTHROPIC_SMALL_FAST_MODEL` | Override small/fast model | Optional | `"us.anthropic.claude-3-5-haiku-20241022-v1:0"` |63| `ANTHROPIC_SMALL_FAST_MODEL` | Override small/fast model | Optional | `"us.anthropic.claude-3-5-haiku-20241022-v1:0"` |

64| `CLAUDE_CODE_SKIP_AUTH_LOGIN` | Disable all prompts to login | Optional | `"1"` or `"true"` |

72 65 

73For detailed setup instructions and additional configuration options, see:66For detailed setup instructions and additional configuration options, see:

74 67