SpyBara
Go Premium

Documentation 2026-09-22 23:59 UTC to 2026-09-23 23:57 UTC

16 files changed +84 −44. View all changes and history on the product overview
2026
Mon 28 02:59 Sun 27 23:59 Sat 26 23:59 Fri 25 23:58 Thu 24 22:57 Wed 23 23:57 Tue 22 23:59 Mon 21 22:59 Sun 20 23:59 Sat 19 23:57 Fri 18 23:58 Thu 17 05:00 Wed 16 22:58 Tue 15 23:58 Mon 14 22:58 Sun 13 21:00 Sat 12 03:02 Fri 11 23:01 Thu 10 23:00 Wed 9 22:58 Tue 8 20:00 Sat 5 14:59 Fri 4 23:59 Thu 3 16:59 Wed 2 04:58 Tue 1 21:02

artifacts.md +4 −0

Details

306| Organization policy | Customer-managed encryption keys (CMEK), HIPAA, and [Zero Data Retention](/docs/en/zero-data-retention) are not enabled for the organization. |306| Organization policy | Customer-managed encryption keys (CMEK), HIPAA, and [Zero Data Retention](/docs/en/zero-data-retention) are not enabled for the organization. |

307| Surface | Claude Code CLI, or the Claude desktop app version 1.13576.0 or later. [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions can also publish artifacts when both Claude Tag and artifacts are enabled for the organization. Off by default in [Agent SDK](/docs/en/agent-sdk/overview), GitHub Action, and MCP-server contexts, and when [`CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`](/docs/en/env-vars) is set. |307| Surface | Claude Code CLI, or the Claude desktop app version 1.13576.0 or later. [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions can also publish artifacts when both Claude Tag and artifacts are enabled for the organization. Off by default in [Agent SDK](/docs/en/agent-sdk/overview), GitHub Action, and MCP-server contexts, and when [`CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`](/docs/en/env-vars) is set. |

308 308 

309Whether artifacts are allowed for your organization comes from your organization's policy, which Claude Code loads from `api.anthropic.com`. When Claude Code can't load the policy, artifacts are unavailable. When you ask for one, Claude says why.

310 

311If a proxy, VPN, or web filter is involved, ask your IT admin to let `api.anthropic.com` through. Claude Code keeps retrying in the background, and artifacts become available once the policy loads and allows them.

312 

309## Disable artifacts313## Disable artifacts

310 314 

311To turn artifacts off for your own sessions regardless of your organization's setting, use any of:315To turn artifacts off for your own sessions regardless of your organization's setting, use any of:

Details

7> Run Claude Code sessions in the cloud from your browser, phone, desktop app, or terminal, move them with --cloud and --teleport, and auto-fix pull requests.7> Run Claude Code sessions in the cloud from your browser, phone, desktop app, or terminal, move them with --cloud and --teleport, and auto-fix pull requests.

8 8 

9<Note>9<Note>

10 Cloud sessions are in research preview for Pro, Max, and Team users, and for Enterprise users with premium seats or Chat + Claude Code seats.10 Cloud sessions are available on Pro, Max, and Team plans, and for Enterprise users with premium seats or Chat + Claude Code seats.

11</Note>11</Note>

12 12 

13A cloud session is a Claude Code session that runs on cloud infrastructure instead of on your machine. By default it runs on infrastructure Anthropic manages, or on your organization's [self-hosted environment](/docs/en/self-hosted-environments) when routed there. The session keeps running after you close your laptop, and you can check on it or steer it from any device.13A cloud session is a Claude Code session that runs on cloud infrastructure instead of on your machine. By default it runs on infrastructure Anthropic manages, or on your organization's [self-hosted environment](/docs/en/self-hosted-environments) when routed there. The session keeps running after you close your laptop, and you can check on it or steer it from any device.

Details

7> Configure cloud environments for Claude Code cloud sessions: network access levels, environment variables, setup scripts, and environment caching.7> Configure cloud environments for Claude Code cloud sessions: network access levels, environment variables, setup scripts, and environment caching.

8 8 

9<Note>9<Note>

10 Cloud environments apply to [cloud sessions](/docs/en/claude-code-on-the-web), which are in research preview for Pro, Max, and Team users, and for Enterprise users with [premium seats or Chat + Claude Code seats](https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan).10 Cloud environments apply to [cloud sessions](/docs/en/claude-code-on-the-web), which are available on Pro, Max, and Team plans, and for Enterprise users with [premium seats or Chat + Claude Code seats](https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan).

11</Note>11</Note>

12 12 

13Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environment variables](#set-environment-variables) for the session, on Pro and Max plans store [API credentials](#add-api-credentials) that sessions use without seeing them, and run a [setup script](#setup-scripts) before Claude starts working.13Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environment variables](#set-environment-variables) for the session, on Pro and Max plans store [API credentials](#add-api-credentials) that sessions use without seeing them, and run a [setup script](#setup-scripts) before Claude starts working.

env-vars.md +2 −1

Details

301| `CLAUDE_CODE_IDE_SKIP_VALID_CHECK` | Set to `1` to skip validation of IDE lockfile entries during connection. Use when auto-connect fails to find your IDE despite it running |301| `CLAUDE_CODE_IDE_SKIP_VALID_CHECK` | Set to `1` to skip validation of IDE lockfile entries during connection. Use when auto-connect fails to find your IDE despite it running |

302| `CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS` | How many [subagents](/docs/en/sub-agents#concurrent-subagent-limit) can be running in one session before the Agent tool refuses to spawn another (default: 20). Accepts a positive whole number in plain digits; anything else is ignored, so the variable can adjust the cap but can't disable it. Requires Claude Code v2.1.217 or later |302| `CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS` | How many [subagents](/docs/en/sub-agents#concurrent-subagent-limit) can be running in one session before the Agent tool refuses to spawn another (default: 20). Accepts a positive whole number in plain digits; anything else is ignored, so the variable can adjust the cap but can't disable it. Requires Claude Code v2.1.217 or later |

303| `CLAUDE_CODE_MAX_CONTEXT_TOKENS` | Override the context window size Claude Code assumes for the active model. As of v2.1.193, how it applies depends on how Claude Code resolves the model ID; see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id). Use this when routing to a model through `ANTHROPIC_BASE_URL` whose context window does not match the built-in size for its name |303| `CLAUDE_CODE_MAX_CONTEXT_TOKENS` | Override the context window size Claude Code assumes for the active model. As of v2.1.193, how it applies depends on how Claude Code resolves the model ID; see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id). Use this when routing to a model through `ANTHROPIC_BASE_URL` whose context window does not match the built-in size for its name |

304| `CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH` | Maximum length in characters of each MCP tool description and each MCP server's instructions that Claude Code sends to the model (default: 2048). Claude Code [truncates longer text](/docs/en/mcp#for-mcp-server-authors). Accepts a positive whole number in plain digits. Anything else is ignored and the default applies. Requires Claude Code v2.1.280 or later |

304| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison). Claude Code defaults to 32000 for model IDs it doesn't recognize, such as gateway-specific names, and lowers values above a model's cap to the cap. Increasing this value reduces the effective context window available before [auto-compaction](/docs/en/costs#reduce-token-usage) triggers |305| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Defaults and caps vary by model; see [max output tokens](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison). Claude Code defaults to 32000 for model IDs it doesn't recognize, such as gateway-specific names, and lowers values above a model's cap to the cap. Increasing this value reduces the effective context window available before [auto-compaction](/docs/en/costs#reduce-token-usage) triggers |

305| `CLAUDE_CODE_MAX_RETRIES` | Override the number of times to retry failed API requests (default: 10). Capped at 15 as of v2.1.186; as of v2.1.199, `CLAUDE_CODE_RETRY_WATCHDOG` raises the default and removes the cap. For unattended sessions that need to wait through longer outages, set `CLAUDE_CODE_RETRY_WATCHDOG` instead |306| `CLAUDE_CODE_MAX_RETRIES` | Override the number of times to retry failed API requests (default: 10). Capped at 15 as of v2.1.186; as of v2.1.199, `CLAUDE_CODE_RETRY_WATCHDOG` raises the default and removes the cap. For unattended sessions that need to wait through longer outages, set `CLAUDE_CODE_RETRY_WATCHDOG` instead |

306| `CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION` | Removed in v2.1.224 and now a no-op. Previously capped the total number of [subagents](/docs/en/sub-agents) Claude could spawn with the Agent tool in one session (default: 200); spawning past the cap failed with `Subagent spawn limit reached`. The [concurrent subagent limit](/docs/en/sub-agents#concurrent-subagent-limit) and the [depth limit](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) still apply |307| `CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION` | Removed in v2.1.224 and now a no-op. Previously capped the total number of [subagents](/docs/en/sub-agents) Claude could spawn with the Agent tool in one session (default: 200); spawning past the cap failed with `Subagent spawn limit reached`. The [concurrent subagent limit](/docs/en/sub-agents#concurrent-subagent-limit) and the [depth limit](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents) still apply |


330| `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE` | Set to `1` to let Claude Code run your package manager's upgrade command in the background when a new version is available. Applies to Homebrew and WinGet installations. Other package managers continue to show the upgrade command without running it. See [Auto updates](/docs/en/setup#auto-updates) |331| `CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE` | Set to `1` to let Claude Code run your package manager's upgrade command in the background when a new version is available. Applies to Homebrew and WinGet installations. Other package managers continue to show the upgrade command without running it. See [Auto updates](/docs/en/setup#auto-updates) |

331| `CLAUDE_CODE_PERFORCE_MODE` | Set to `1` to enable Perforce-aware write protection. When set, Edit, Write, and NotebookEdit fail with a `p4 edit <file>` hint if the target file lacks the owner-write bit, which Perforce clears on synced files until `p4 edit` opens them. This prevents Claude Code from bypassing Perforce change tracking |332| `CLAUDE_CODE_PERFORCE_MODE` | Set to `1` to enable Perforce-aware write protection. When set, Edit, Write, and NotebookEdit fail with a `p4 edit <file>` hint if the target file lacks the owner-write bit, which Perforce clears on synced files until `p4 edit` opens them. This prevents Claude Code from bypassing Perforce change tracking |

332| `CLAUDE_CODE_PLUGIN_CACHE_DIR` | Override the plugins root directory. Despite the name, this sets the parent directory, not the cache itself: marketplaces and the plugin cache live in subdirectories under this path. Defaults to `~/.claude/plugins` |333| `CLAUDE_CODE_PLUGIN_CACHE_DIR` | Override the plugins root directory. Despite the name, this sets the parent directory, not the cache itself: marketplaces and the plugin cache live in subdirectories under this path. Defaults to `~/.claude/plugins` |

334| `CLAUDE_CODE_PLUGIN_DIRS` | Plugin directories to load for the session, each loaded the way a [`--plugin-dir`](/docs/en/plugins#test-your-plugins-locally) flag loads it. Separate multiple paths with `:` on Unix or `;` on Windows. Give each path as an absolute path or start it with `~`, because Claude Code skips relative paths. Requires Claude Code v2.1.280 or later |

333| `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` | Timeout in milliseconds for git operations when installing or updating plugins (default: 120000). Increase this value for large repositories or slow network connections. See [Git operations time out](/docs/en/plugin-marketplaces#git-operations-time-out) |335| `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` | Timeout in milliseconds for git operations when installing or updating plugins (default: 120000). Increase this value for large repositories or slow network connections. See [Git operations time out](/docs/en/plugin-marketplaces#git-operations-time-out) |

334| `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` | Set to `1` to skip the re-clone attempt and keep using the existing marketplace checkout when a marketplace refresh can't reach or authenticate to the remote. Useful in offline or airgapped environments where re-cloning would fail the same way. See [Marketplace updates fail in offline environments](/docs/en/plugin-marketplaces#marketplace-updates-fail-in-offline-environments) |336| `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` | Set to `1` to skip the re-clone attempt and keep using the existing marketplace checkout when a marketplace refresh can't reach or authenticate to the remote. Useful in offline or airgapped environments where re-cloning would fail the same way. See [Marketplace updates fail in offline environments](/docs/en/plugin-marketplaces#marketplace-updates-fail-in-offline-environments) |

335| `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` | Set to `1` to clone GitHub `owner/repo` shorthand sources over HTTPS instead of SSH. Applies to plugin install and update, and to `/plugin marketplace add` and `update`. Useful in CI runners, containers, or any environment without a configured SSH key for `github.com` |337| `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` | Set to `1` to clone GitHub `owner/repo` shorthand sources over HTTPS instead of SSH. Applies to plugin install and update, and to `/plugin marketplace add` and `update`. Useful in CI runners, containers, or any environment without a configured SSH key for `github.com` |


512 514 

513With fetching off, you can't:515With fetching off, you can't:

514 516 

515* Have Claude Code [read `AGENTS.md` files](/docs/en/memory#agents-md) as project instructions; it loads `CLAUDE.md` files only

516* [Start sessions in auto mode by default](/docs/en/permission-modes#which-mode-a-session-starts-in) on Pro, Max, and Team plans517* [Start sessions in auto mode by default](/docs/en/permission-modes#which-mode-a-session-starts-in) on Pro, Max, and Team plans

517* Have the VS Code extension [read settings files for the starting permission mode](/docs/en/permission-modes#switch-permission-modes)518* Have the VS Code extension [read settings files for the starting permission mode](/docs/en/permission-modes#switch-permission-modes)

518* Run [`/auto-mode-setup`](/docs/en/auto-mode-config#generate-environment-entries) to draft `autoMode.environment` entries519* Run [`/auto-mode-setup`](/docs/en/auto-mode-config#generate-environment-entries) to draft `autoMode.environment` entries

Details

34 34 

35These have provider-specific differences:35These have provider-specific differences:

36 36 

37* **CLAUDE.md memory**: `CLAUDE.md` files load on every provider. Reading [`AGENTS.md` files](/docs/en/memory#agents-md) as project instructions also requires a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching)

38* **MCP servers**: [connectors from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai) load only when your claude.ai subscription is the active authentication method. [Tool search](/docs/en/mcp#configure-tool-search) is off by default when `ANTHROPIC_BASE_URL` points to a non-first-party host, and isn't supported on Google Cloud's Agent Platform models earlier than the Claude 4.5 generation or on Microsoft Foundry [deployments hosted on Azure](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options)37* **MCP servers**: [connectors from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai) load only when your claude.ai subscription is the active authentication method. [Tool search](/docs/en/mcp#configure-tool-search) is off by default when `ANTHROPIC_BASE_URL` points to a non-first-party host, and isn't supported on Google Cloud's Agent Platform models earlier than the Claude 4.5 generation or on Microsoft Foundry [deployments hosted on Azure](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options)

39* **Subagents**: the built-in [Explore subagent](/docs/en/sub-agents#built-in-subagents) caps its inherited model at Opus on the Claude API, and inherits the main conversation's model directly on any other provider, including Claude Platform on AWS38* **Subagents**: the built-in [Explore subagent](/docs/en/sub-agents#built-in-subagents) caps its inherited model at Opus on the Claude API, and inherits the main conversation's model directly on any other provider, including Claude Platform on AWS

40* **[Commands](/docs/en/commands#all-commands)**:39* **[Commands](/docs/en/commands#all-commands)**:

glossary.md +1 −1

Details

12 12 

13### AGENTS.md13### AGENTS.md

14 14 

15A markdown file of project instructions you write for AI coding agents. If your repository has one and no [CLAUDE.md](#claude-md), Claude reads it as your project instructions without you adding a second file. You can change the **Project instructions** setting in `/config` to have Claude read both files or only `CLAUDE.md`. Reading `AGENTS.md` directly requires Claude Code v2.1.277 or later in a session that fetches feature flags; on other versions, import it from a CLAUDE.md.15A markdown file of project instructions you write for AI coding agents. If your repository has one and no [CLAUDE.md](#claude-md), Claude reads it as your project instructions without you adding a second file. You can change the **Project instructions** setting in `/config` to have Claude read both files or only `CLAUDE.md`. Reading `AGENTS.md` directly requires Claude Code v2.1.277 or later. In some sessions Claude [can't read `AGENTS.md`](/docs/en/memory#when-agents-md-support-is-unavailable), so [import it from a `CLAUDE.md`](/docs/en/memory#share-one-file-with-other-coding-tools) there instead.

16 16 

17Learn more: [AGENTS.md](/docs/en/memory#agents-md)17Learn more: [AGENTS.md](/docs/en/memory#agents-md)

18 18 

mcp.md +3 −1

Details

1420* When Claude should search for your tools1420* When Claude should search for your tools

1421* Key capabilities your server provides1421* Key capabilities your server provides

1422 1422 

1423Claude Code truncates tool descriptions and server instructions at 2KB each. Keep them concise to avoid truncation, and put critical details near the start.1423Claude Code truncates each tool description and each server's instructions at 2,048 characters by default. Keep them concise, and put critical details near the start.

1424 

1425To change the limit for every MCP server in your session, set [`CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH`](/docs/en/env-vars#variables) to a number of characters. This variable requires Claude Code v2.1.280 or later.

1424 1426 

1425### Configure tool search1427### Configure tool search

1426 1428 

memory.md +5 −7

Details

343To change the default, for example to have Claude always read both files, read only `CLAUDE.md`, or read only your organization's managed instructions, [change the **Project instructions** setting](#choose-which-instruction-files-load).343To change the default, for example to have Claude always read both files, read only `CLAUDE.md`, or read only your organization's managed instructions, [change the **Project instructions** setting](#choose-which-instruction-files-load).

344 344 

345<Note>345<Note>

346 Reading `AGENTS.md` directly requires Claude Code v2.1.277 or later. In some sessions, such as those on Amazon Bedrock or with telemetry disabled, Claude [can't read `AGENTS.md`](#when-agents-md-support-is-unavailable), so [import it from a `CLAUDE.md`](#share-one-file-with-other-coding-tools) there instead.346 Reading `AGENTS.md` directly requires Claude Code v2.1.277 or later. In some sessions Claude [can't read `AGENTS.md`](#when-agents-md-support-is-unavailable), so [import it from a `CLAUDE.md`](#share-one-file-with-other-coding-tools) there instead.

347</Note>347</Note>

348 348 

349### When Claude Code reads AGENTS.md349### When Claude Code reads AGENTS.md


394In these sessions Claude reads `CLAUDE.md` files only, and **Project instructions** doesn't appear in the `/config` settings panel:394In these sessions Claude reads `CLAUDE.md` files only, and **Project instructions** doesn't appear in the `/config` settings panel:

395 395 

396* You're on a Claude Code version before v2.1.277396* You're on a Claude Code version before v2.1.277

397* Your session doesn't [fetch feature flags from Anthropic](/docs/en/env-vars#features-that-need-feature-flag-fetching), for example because you use Amazon Bedrock or another third-party provider, or you disabled telemetry. The linked section has the full list

398* It's your [first session after you install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade) to a version with `AGENTS.md` support. Claude reads `AGENTS.md` from your next session on

399* You disabled the built-in `agents-md` plugin in `/plugin`397* You disabled the built-in `agents-md` plugin in `/plugin`

398* In some cases, it's your [first session after you upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade) from v2.1.276 or earlier. Claude reads `AGENTS.md` from your next session on

400 399 

401To give Claude your `AGENTS.md` in these sessions, [import it from a `CLAUDE.md`](#share-one-file-with-other-coding-tools).400Before v2.1.281, some sessions, such as those on Amazon Bedrock or with telemetry disabled, read `CLAUDE.md` files only. On those versions, update Claude Code. To give Claude your `AGENTS.md` in any of these sessions, [import it from a `CLAUDE.md`](#share-one-file-with-other-coding-tools).

402 401 

403### Where AGENTS.md differs from CLAUDE.md402### Where AGENTS.md differs from CLAUDE.md

404 403 


569If your repository has an `AGENTS.md` and Claude doesn't seem to know what it says, the usual cause is a `CLAUDE.md` somewhere on the project path. By default Claude reads `AGENTS.md` only when you have no `CLAUDE.md` or `CLAUDE.local.md` in your working directory or above it. Check these in order:568If your repository has an `AGENTS.md` and Claude doesn't seem to know what it says, the usual cause is a `CLAUDE.md` somewhere on the project path. By default Claude reads `AGENTS.md` only when you have no `CLAUDE.md` or `CLAUDE.local.md` in your working directory or above it. Check these in order:

570 569 

5711. Look for a `CLAUDE.md`, `.claude/CLAUDE.md`, or `CLAUDE.local.md` in your working directory or any directory above it, other than your `~/.claude/CLAUDE.md`. If you find one, Claude reads it instead of `AGENTS.md` unless you set **Project instructions** to `claude-md-and-agents-md`.5701. Look for a `CLAUDE.md`, `.claude/CLAUDE.md`, or `CLAUDE.local.md` in your working directory or any directory above it, other than your `~/.claude/CLAUDE.md`. If you find one, Claude reads it instead of `AGENTS.md` unless you set **Project instructions** to `claude-md-and-agents-md`.

5722. Run `claude --version` and confirm v2.1.277 or later.5712. Run `claude --version` and confirm v2.1.277 or later. Before v2.1.281, some sessions, such as those on Amazon Bedrock or with telemetry disabled, [couldn't load `AGENTS.md`](#when-agents-md-support-is-unavailable) either, so on those versions update to v2.1.281 or later.

5733. Check whether your session is one that [can't load `AGENTS.md`](#when-agents-md-support-is-unavailable), such as a session on a third-party provider or with telemetry disabled.5723. Type `/config` in your session to open the settings panel and confirm **Project instructions** isn't set to `claude-md` or `managed-only`. If you don't see the setting there at all, your session is one that [can't load `AGENTS.md`](#when-agents-md-support-is-unavailable).

5744. Type `/config` in your session to open the settings panel and confirm **Project instructions** isn't set to `claude-md` or `managed-only`. If you don't see the setting there at all, your session is one that [can't load `AGENTS.md`](#when-agents-md-support-is-unavailable).

575 573 

576To check whether Claude read your `AGENTS.md`, run `/memory` and look for its path in the list.574To check whether Claude read your `AGENTS.md`, run `/memory` and look for its path in the list.

577 575 

Details

1117* `num_non_blocking_error`: Count that failed without blocking1117* `num_non_blocking_error`: Count that failed without blocking

1118* `num_cancelled`: Count cancelled before completion1118* `num_cancelled`: Count cancelled before completion

1119* `total_duration_ms`: Wall-clock duration of all matching hooks1119* `total_duration_ms`: Wall-clock duration of all matching hooks

1120* `stdout_chars`: Total characters of stdout across the matching hooks that succeeded. Requires Claude Code v2.1.280 or later

1121* `additional_context_chars`: Total characters of `additionalContext` returned by the matching hooks. Requires Claude Code v2.1.280 or later

1122* `system_message_chars`: Total characters of `systemMessage` returned by the matching hooks. Requires Claude Code v2.1.280 or later

1123* `initial_user_message_chars`: Total characters of `initialUserMessage` returned by the matching hooks. Requires Claude Code v2.1.280 or later

1124* `num_outputs_persisted`: Number of hook outputs over the [10,000-character cap](/docs/en/hooks#json-output) that Claude Code saved to a file. Requires Claude Code v2.1.280 or later

1120* `managed_only`: `"true"` when only managed-policy hooks are permitted1125* `managed_only`: `"true"` when only managed-policy hooks are permitted

1121* `hook_source`: `"policySettings"` or `"merged"`1126* `hook_source`: `"policySettings"` or `"merged"`

1122* `safe_mode`: `"true"` when the session was started with [`--safe-mode`](/docs/en/cli-reference), `"false"` otherwise. Requires Claude Code v2.1.169 or later1127* `safe_mode`: `"true"` when the session was started with [`--safe-mode`](/docs/en/cli-reference), `"false"` otherwise. Requires Claude Code v2.1.169 or later

Details

787 787 

788#### Background auto-updates788#### Background auto-updates

789 789 

790By default, the background refresh disables git credential helpers when it checks the marketplace's remote for new commits, so the check can't authenticate to private repositories over HTTPS even when a helper is configured. SSH remotes aren't affected: a key loaded in `ssh-agent` authenticates the background check the same way as the commands you run.790The background refresh checks the marketplace's remote for new commits with your configured git credential helpers, the same as the commands you run. For SSH remotes, a key loaded in `ssh-agent` authenticates the check. Claude Code runs the check non-interactively: it turns off git's terminal prompts and askpass programs, and tells credential helpers not to prompt. Whether the check can authenticate to a private repository over HTTPS depends on your helper:

791 791 

792When the check finds new commits, or fails because it can't reach or authenticate to the remote, Claude Code clones the marketplace again and swaps the new clone in. If that clone fails, the existing checkout stays in place. The re-clone does use your stored git credentials, but it can [time out on large repositories](#git-operations-time-out), so private-marketplace auto-updates may fail intermittently.792* A helper that can supply a stored credential without prompting authenticates the check. Git Credential Manager, the macOS Keychain helper, and `git-credential-store` work this way once they hold a credential for the host.

793* A helper that needs to prompt you can't answer in the background. The update fails quietly and the existing checkout stays in place, so your plugins keep working from the last synced state. Run `/plugin marketplace update <name>` to refresh the marketplace with your credentials.

794 

795When the check finds the checkout up to date, Claude Code leaves it as it is. When the check finds new commits, or fails because it can't reach or authenticate to the remote, Claude Code clones the marketplace again and swaps the new clone in. If that clone fails, the existing checkout stays in place. The re-clone can [time out on large repositories](#git-operations-time-out).

793 796 

794Two settings make private marketplaces behave predictably:797Two settings make private marketplaces behave predictably:

795 798 

796* Set `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1` to keep the existing checkout without attempting the re-clone when the background check can't reach or authenticate to the remote. Your plugins keep working from the last synced state, and manual updates with `/plugin marketplace update` still authenticate with your credentials.799* Set `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1` to keep the existing checkout without attempting the re-clone when the background check can't reach or authenticate to the remote. Your plugins keep working from the last synced state, and manual updates with `/plugin marketplace update` still authenticate with your credentials.

797* Configure a git credential helper, for example with `gh auth setup-git` for GitHub, so the re-clone can authenticate without prompting.800* Configure a git credential helper, for example with `gh auth setup-git` for GitHub, so the background check and the re-clone can authenticate without prompting.

798 801 

799Setting a provider token such as `GITHUB_TOKEN` in your environment doesn't by itself enable background authentication. Tokens take effect only through a configured credential helper, for example the `gh` CLI's helper, which reads `GH_TOKEN` and `GITHUB_TOKEN`.802Setting a provider token such as `GITHUB_TOKEN` in your environment doesn't by itself enable background authentication. Tokens take effect only through a configured credential helper, for example the `gh` CLI's helper, which reads `GH_TOKEN` and `GITHUB_TOKEN`.

800 803 

801To make the background check itself authenticate over HTTPS, configure a global git URL rewrite. The rewrite embeds a token in the remote URL, so it takes effect even though the background check disables credential helpers. When the check finds the checkout up to date, Claude Code skips the re-clone. The following example rewrites the marketplace repository's URL to include an access token:

802 

803```bash theme={null}

804git config --global url."https://x-access-token:YOUR_TOKEN@github.com/acme-corp/plugins".insteadOf "https://github.com/acme-corp/plugins"

805```

806 

807Scope the rewrite to the marketplace repository or organization path. A rewrite whose base is only the host applies to every fetch and push to that host on the machine and overrides your normal credentials, including pushes to your own repositories.

808 

809Each provider expects a different username in the rewritten URL, and the same path scoping applies to every provider. For self-hosted servers, replace the hostname with your server's hostname:

810 

811| Provider | Rewritten URL form |

812| :-------- | :---------------------------------------------------------------- |

813| GitHub | `https://x-access-token:YOUR_TOKEN@github.com/acme-corp/plugins` |

814| GitLab | `https://oauth2:YOUR_TOKEN@gitlab.com/acme-corp/plugins` |

815| Bitbucket | `https://x-token-auth:YOUR_TOKEN@bitbucket.org/acme-corp/plugins` |

816 

817The rewrite stores the token in plaintext in your gitconfig, so use a token with read-only access to the marketplace repository.

818 

819<Note>804<Note>

820 In CI/CD environments, configure a git credential helper before installing plugins from private repositories. On GitHub Actions, export a token with read access to the marketplace repository as `GH_TOKEN`, then run `gh auth setup-git`. The default workflow token can only access the workflow's own repository, so a private marketplace in another repository needs a personal access token or app token.805 In CI/CD environments, configure a git credential helper before installing plugins from private repositories. On GitHub Actions, export a token with read access to the marketplace repository as `GH_TOKEN`, then run `gh auth setup-git`. The default workflow token can only access the workflow's own repository, so a private marketplace in another repository needs a personal access token or app token.

821 

822 If you configure a global URL rewrite in the pipeline, the rewrite also authenticates the background check directly.

823</Note>806</Note>

824 807 

825### Distribute through organization settings808### Distribute through organization settings


1488 1471 

1489For background auto-updates:1472For background auto-updates:

1490 1473 

1491* By default, background refreshes disable git credential helpers when they check the remote for new commits, so the check can't authenticate over HTTPS. SSH remotes with a key loaded in `ssh-agent` still authenticate1474* The background check uses your configured git credential helpers but never prompts, so your helper must be able to answer with a stored credential. SSH remotes with a key loaded in `ssh-agent` also authenticate

1492* When the check can't authenticate, Claude Code re-clones the marketplace with your stored credentials, but the re-clone may time out on large repositories1475* If your helper needs to prompt you, the background update fails quietly and the existing checkout stays in place. Sign in to your helper first so it holds a credential for the host. For GitHub, run `gh auth login`, then `gh auth setup-git`

1476* When the check finds new commits, or can't reach or authenticate to the remote, Claude Code re-clones the marketplace with the same credentials. The re-clone may time out on large repositories

1493* Set `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1` to keep the existing checkout without attempting the re-clone when the background check can't reach or authenticate to the remote1477* Set `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1` to keep the existing checkout without attempting the re-clone when the background check can't reach or authenticate to the remote

1494* Configure a git credential helper, for example `gh auth setup-git`, so the re-clone can authenticate

1495* If the re-clone times out on a large repository, increase the limit with [`CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS`](#git-operations-time-out)1478* If the re-clone times out on a large repository, increase the limit with [`CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS`](#git-operations-time-out)

1496* Configure a [git URL rewrite](#private-repositories) scoped to the marketplace repository so the background check authenticates directly

1497* Or update private marketplaces manually with `/plugin marketplace update <name>`, which uses your credentials1479* Or update private marketplaces manually with `/plugin marketplace update <name>`, which uses your credentials

1498 1480 

1481Before v2.1.280, the background check ran without your credential helpers and couldn't authenticate to private repositories over HTTPS.

1482 

1499### Marketplace updates fail in offline environments1483### Marketplace updates fail in offline environments

1500 1484 

1501**Symptoms**: In an offline or airgapped environment, the background marketplace refresh can't reach the remote and Claude Code repeatedly attempts a re-clone that can't succeed.1485**Symptoms**: In an offline or airgapped environment, the background marketplace refresh can't reach the remote and Claude Code repeatedly attempts a re-clone that can't succeed.

plugins.md +2 −0

Details

314 To test a plugin together with a plugin it depends on, see [Test a plugin and its dependency locally](/docs/en/plugin-dependencies#test-a-plugin-and-its-dependency-locally).314 To test a plugin together with a plugin it depends on, see [Test a plugin and its dependency locally](/docs/en/plugin-dependencies#test-a-plugin-and-its-dependency-locally).

315</Tip>315</Tip>

316 316 

317To load plugins in a session where you can't add the flag, list their absolute paths in the [`CLAUDE_CODE_PLUGIN_DIRS`](/docs/en/env-vars#variables) environment variable instead. Claude Code loads each path as it loads a `--plugin-dir` path. These plugins load in addition to any you pass with `--plugin-dir`. [Project and local settings can't set this variable](/docs/en/settings-reference#variables-claude-code-ignores-in-env). `CLAUDE_CODE_PLUGIN_DIRS` requires Claude Code v2.1.280 or later.

318 

317Trying the plugin with `--plugin-dir` tells you it can work. To find out how often Claude actually reaches for it and gets the right result, run it against a set of test prompts with [`claude plugin eval`](/docs/en/plugin-evals). Each prompt runs several times with and without the plugin loaded, so you can see what the plugin contributes and catch regressions when you change it or a new model ships.319Trying the plugin with `--plugin-dir` tells you it can work. To find out how often Claude actually reaches for it and gets the right result, run it against a set of test prompts with [`claude plugin eval`](/docs/en/plugin-evals). Each prompt runs several times with and without the plugin loaded, so you can see what the plugin contributes and catch regressions when you change it or a new model ships.

318 320 

319To load several plugins from one place, pass a folder that holds them, such as `--plugin-dir ./plugins`. Loading a folder of plugins requires Claude Code v2.1.265 or later. Claude Code reads the folder's top level to decide which plugins load, and in an interactive session it also watches the folder for later changes:321To load several plugins from one place, pass a folder that holds them, such as `--plugin-dir ./plugins`. Loading a folder of plugins requires Claude Code v2.1.265 or later. Claude Code reads the folder's top level to decide which plugins load, and in an interactive session it also watches the folder for later changes:

skills.md +8 −0

Details

1088 1088 

1089To raise the budget, set the [`skillListingBudgetFraction`](/docs/en/settings-reference#skilllistingbudgetfraction) setting (for example, `0.02` = 2%) or the `SLASH_COMMAND_TOOL_CHAR_BUDGET` environment variable to a fixed character count. To free budget for other skills, set low-priority entries to `"name-only"` in [`skillOverrides`](#override-skill-visibility-from-settings) so they list without a description. You can also trim the `description` and `when_to_use` text at the source: put the key use case first, since each entry's combined text is capped at 1,536 characters regardless of budget. The cap is configurable with [`skillListingMaxDescChars`](/docs/en/settings-reference#skilllistingmaxdescchars).1089To raise the budget, set the [`skillListingBudgetFraction`](/docs/en/settings-reference#skilllistingbudgetfraction) setting (for example, `0.02` = 2%) or the `SLASH_COMMAND_TOOL_CHAR_BUDGET` environment variable to a fixed character count. To free budget for other skills, set low-priority entries to `"name-only"` in [`skillOverrides`](#override-skill-visibility-from-settings) so they list without a description. You can also trim the `description` and `when_to_use` text at the source: put the key use case first, since each entry's combined text is capped at 1,536 characters regardless of budget. The cap is configurable with [`skillListingMaxDescChars`](/docs/en/settings-reference#skilllistingmaxdescchars).

1090 1090 

1091### Personal skills disappeared

1092 

1093If skill folders you created in `~/.claude/skills/` are gone, look in `~/.claude/skills/.trash/`. When Claude Code [syncs skills from claude.ai](#how-synced-skills-behave), it downloads them into the separate `synced` subfolder and doesn't move or delete the folders you create.

1094 

1095Before v2.1.280, a file named `manifest.json` in `~/.claude/skills/` caused Claude Code to move the skill folders that file listed into a timestamped folder under `~/.claude/skills/.trash/`, and those skills stopped loading.

1096 

1097To restore a skill, move its folder from the timestamped folder back into `~/.claude/skills/`. Do this before the [retention sweep](/docs/en/claude-directory#cleaned-up-automatically) deletes trash entries, by default 30 days after they were moved to the trash.

1098 

1091## Related resources1099## Related resources

1092 1100 

1093* **[Debug your configuration](/docs/en/debug-your-config)**: diagnose why a skill isn't appearing or triggering1101* **[Debug your configuration](/docs/en/debug-your-config)**: diagnose why a skill isn't appearing or triggering

ultrareview.md +8 −2

Details

141 141 

142Use `/tasks` to see running and completed reviews, open the detail view for a review, or stop a review that is in progress. If you stop a review, Claude Code archives the cloud session and doesn't return partial findings.142Use `/tasks` to see running and completed reviews, open the detail view for a review, or stop a review that is in progress. If you stop a review, Claude Code archives the cloud session and doesn't return partial findings.

143 143 

144Claude can also tell you that a review was stopped or that its session wasn't found:

145 

146* If the review's cloud session is stopped or [archived](/docs/en/claude-code-on-the-web#archive-sessions) on claude.ai before the review finishes, Claude tells you it was stopped.

147* If the review's cloud session was deleted, or you've signed in to a different Claude account or organization since launching it, Claude tells you the session wasn't found.

148* If you switched accounts, the review may still finish under the account that started it. If the review is still running, sign back in as that account and resume the conversation with `claude --resume` to re-attach it.

149 

144When the review finishes, Claude Code shows the verified findings as a notification in your session. Each finding includes the file location and an explanation of the issue so you can ask Claude to fix it directly.150When the review finishes, Claude Code shows the verified findings as a notification in your session. Each finding includes the file location and an explanation of the issue so you can ask Claude to fix it directly.

145 151 

146## Run ultrareview non-interactively152## Run ultrareview non-interactively


173The subcommand exits with one of three codes:179The subcommand exits with one of three codes:

174 180 

175* **0**: the review completed, with or without findings181* **0**: the review completed, with or without findings

176* **1**: the review failed to launch, the cloud session errored, or the timeout elapsed182* **1**: the review failed to launch or was stopped before it finished, the cloud session errored, or the timeout elapsed

177* **130**: you interrupted the subcommand with Ctrl-C183* **130**: you interrupted the subcommand with Ctrl-C

178 184 

179If you interrupt the subcommand, the remote review keeps running; follow the session URL printed to stderr to watch it in the browser.185If you interrupt the subcommand, the remote review keeps running; follow the session URL printed to stderr to watch it in the browser.

180 186 

181With `--post`, the subcommand starts the post right after printing the findings, and prints the link to stderr.187With `--post`, the subcommand starts the post right after printing the findings, and prints the link to stderr.

182 188 

183* If the run fails, times out, or you interrupt it, the subcommand posts nothing.189* If the run fails, is stopped, or times out, or if you interrupt it, the subcommand posts nothing.

184* If the review completes but the comment isn't posted, Claude Code prints the reason to stderr, and the findings stay on stdout so you can post them by hand.190* If the review completes but the comment isn't posted, Claude Code prints the reason to stderr, and the findings stay on stdout so you can post them by hand.

185 191 

186For automatic reviews on GitHub pull requests, [Code Review](/docs/en/code-review) integrates with your repository directly and posts findings as inline PR comments without a CLI step.192For automatic reviews on GitHub pull requests, [Code Review](/docs/en/code-review) integrates with your repository directly and posts findings as inline PR comments without a CLI step.

Details

65 65 

66The first couple of key-repeat characters type into the input during warmup and are removed automatically when recording activates. A single `Space` tap still types a space, since hold detection only triggers on rapid repeat.66The first couple of key-repeat characters type into the input during warmup and are removed automatically when recording activates. A single `Space` tap still types a space, since hold detection only triggers on rapid repeat.

67 67 

68Holding or tapping `Space` starts dictation only where the keypress would otherwise type into the prompt. In the [transcript viewer](/docs/en/interactive-mode#transcript-viewer), `Space` pages through the conversation, and in [vim mode](/docs/en/interactive-mode#vim-editor-mode) outside INSERT it is a command. A [rebound modifier combination](#rebind-the-dictation-key) like `meta+k` never types text, so it starts dictation from those places too.

69 

68<Tip>70<Tip>

69 To skip the warmup, switch to [tap mode](#tap-to-record-and-send) with `/voice tap`, or [rebind to a modifier combination](#rebind-the-dictation-key) like `meta+k`. Modifier combos start recording on the first keypress.71 To skip the warmup, switch to [tap mode](#tap-to-record-and-send) with `/voice tap`, or [rebind to a modifier combination](#rebind-the-dictation-key) like `meta+k`. Modifier combos start recording on the first keypress.

70</Tip>72</Tip>


91 93 

92The first tap only starts recording when the prompt input is empty, so you can still type spaces normally while composing a message. The second tap stops recording regardless of input contents. Recording also stops automatically after 15 seconds of silence or two minutes total.94The first tap only starts recording when the prompt input is empty, so you can still type spaces normally while composing a message. The second tap stops recording regardless of input contents. Recording also stops automatically after 15 seconds of silence or two minutes total.

93 95 

96## Cancel a recording

97 

98Press `Esc` or `Ctrl+C` to cancel a dictation instead of finalizing it. Claude Code stops the microphone, discards the transcript, and restores the prompt to what it held before the recording started.

99 

100Both keys also cancel while a finished recording's transcript is still processing. A prompt you edited or submitted during processing stays as you left it.

101 

102Neither key does anything else in the press that cancels: `Esc` doesn't interrupt Claude's response, and `Ctrl+C` doesn't clear the prompt or count as the first of the [two presses that exit Claude Code](/docs/en/interactive-mode#general-controls).

103 

94## Change the dictation language104## Change the dictation language

95 105 

96Voice dictation uses the same [`language` setting](/docs/en/settings-reference#language) that controls Claude's response language. If that setting is empty, dictation defaults to English. In the VS Code extension, if `language` is empty, dictation uses VS Code's `accessibility.voice.speechLanguage` setting before defaulting to English.106Voice dictation uses the same [`language` setting](/docs/en/settings-reference#language) that controls Claude's response language. If that setting is empty, dictation defaults to English. In the VS Code extension, if `language` is empty, dictation uses VS Code's `accessibility.voice.speechLanguage` setting before defaulting to English.

vs-code.md +22 −1

Details

105 * **Auto**: a classifier reviews most actions instead of asking you. See [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for what it reviews and blocks.105 * **Auto**: a classifier reviews most actions instead of asking you. See [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for what it reviews and blocks.

106 * **Manual**: Claude asks permission before file edits and most shell commands.106 * **Manual**: Claude asks permission before file edits and most shell commands.

107 * **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.107 * **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.

108 

109 You can also type `/plan` in the prompt box. Requires Claude Code v2.1.280 or later.

110 

111 * `/plan`: switches to plan mode. If you're already in plan mode, shows the current plan instead.

112 * `/plan` with a task, such as `/plan fix the auth bug`: switches to plan mode and starts planning that task.

113 * `/plan open`: when you're already in plan mode, opens the plan file in the editor.

108 * **Edit automatically**: Claude makes edits without asking.114 * **Edit automatically**: Claude makes edits without asking.

109* **Model**: select **Switch model…** from the command menu to change the model mid-session. You can also click the model name at the bottom of the prompt box to open the same picker.115* **Model**: select **Switch model…** from the command menu to change the model mid-session. You can also click the model name at the bottom of the prompt box to open the same picker.

110 116 

111 When the current model supports [effort levels](/docs/en/model-config#adjust-effort-level), the picker also shows an **Effort** row and the model name button shows the selected level. When you pick a level other than `max`, Claude Code saves it for the current model as your default, under [`modelSettings`](/docs/en/settings-reference#modelsettings) in your user settings; `max` applies to the current session only. The model name button and the **Effort** row require Claude Code v2.1.257 or later.117 When the current model supports [effort levels](/docs/en/model-config#adjust-effort-level), the picker also shows an **Effort** row and the model name button shows the selected level. When you pick a level other than `max`, Claude Code saves it for the current model as your default, under [`modelSettings`](/docs/en/settings-reference#modelsettings) in your user settings; `max` applies to the current session only. The model name button and the **Effort** row require Claude Code v2.1.257 or later.

112* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, and toggling extended thinking.118* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, and toggling extended thinking.

113 119 

114 The Customize section provides access to MCP servers, commands, output styles, hooks, memory, instructions, permissions, and plugins. Items with a terminal icon open in the integrated terminal.120 The Customize section includes entries such as MCP servers, commands, output styles, hooks, memory, instructions, permissions, and plugins. Items with a terminal icon open in the integrated terminal.

115 121 

116 * To browse commands such as `/usage` or [`/remote-control`](/docs/en/remote-control), select **Slash commands** in the Customize section. A dialog lists them with a filter box. Pick one to run it. Typing `/` in the prompt box still suggests commands inline. Requires Claude Code v2.1.257 or later.122 * To browse commands such as `/usage` or [`/remote-control`](/docs/en/remote-control), select **Slash commands** in the Customize section. A dialog lists them with a filter box. Pick one to run it. Typing `/` in the prompt box still suggests commands inline. Requires Claude Code v2.1.257 or later.

123 

124 Typing `/skills` also opens this dialog. Each [skill](/docs/en/skills) row shows its [visibility](/docs/en/skills#override-skill-visibility-from-settings), such as **On** or **Name only**. Click the visibility to change it, except on rows marked **locked**, such as plugin skills. The `/skills` shortcut and the visibility controls require Claude Code v2.1.280 or later.

117 * Select **Output styles** in the Customize section to pick an [output style](/docs/en/output-styles), including your custom styles. Requires Claude Code v2.1.257 or later.125 * Select **Output styles** in the Customize section to pick an [output style](/docs/en/output-styles), including your custom styles. Requires Claude Code v2.1.257 or later.

118 126 

119 To create a custom style instead, select **Build a custom style** from the **Output styles** menu. Claude Code writes the [style file](/docs/en/output-styles#create-a-custom-output-style) for you at the project or user level. Requires Claude Code v2.1.261 or later.127 To create a custom style instead, select **Build a custom style** from the **Output styles** menu. Claude Code writes the [style file](/docs/en/output-styles#create-a-custom-output-style) for you at the project or user level. Requires Claude Code v2.1.261 or later.


123 131 

124 Click a saved memory to read it in the dialog, where you can edit the text, delete the memory, or open its file in the editor. Viewing, editing, and deleting a memory in the dialog require Claude Code v2.1.275 or later.132 Click a saved memory to read it in the dialog, where you can edit the text, delete the memory, or open its file in the editor. Viewing, editing, and deleting a memory in the dialog require Claude Code v2.1.275 or later.

125 * Select **Instructions** in the Customize section to edit the [CLAUDE.md files](/docs/en/memory#claude-md-files) Claude reads. Pick a file to open it in the editor. If the file doesn't exist yet, Claude Code creates it first. Requires Claude Code v2.1.274 or later.133 * Select **Instructions** in the Customize section to edit the [CLAUDE.md files](/docs/en/memory#claude-md-files) Claude reads. Pick a file to open it in the editor. If the file doesn't exist yet, Claude Code creates it first. Requires Claude Code v2.1.274 or later.

134 * Select **Status** in the Customize section, or type `/status`, to check the session's Claude Code version, account, model, and MCP server details. Requires Claude Code v2.1.280 or later.

135 * Select **Sandbox** in the Customize section, or type `/sandbox`, to see whether Claude's Bash commands run [sandboxed](/docs/en/sandboxing). You can switch the sandbox mode and add [excluded commands](/docs/en/settings-reference#sandbox-excludedcommands) there. Requires Claude Code v2.1.280 or later.

136 * Select **Claude in Chrome** in the Customize section, or type `/chrome`, to check and manage the [Claude in Chrome](/docs/en/chrome) connection. Both require signing in with a claude.ai account. Requires Claude Code v2.1.280 or later.

137 * Select **Export conversation** in the Context section, or type `/export`, to copy the conversation as plain text or save it to a file. Add a file name, such as `/export notes.txt`, to skip the dialog and choose where to save the file. Requires Claude Code v2.1.280 or later.

126 * The Settings section includes **Enable Remote Control for all sessions**, which sets [`remoteControlAtStartup`](/docs/en/settings-reference#remotecontrolatstartup) to control whether [new interactive sessions connect to Remote Control automatically](/docs/en/remote-control#enable-remote-control-for-all-sessions). Requires Claude Code v2.1.203 or later.138 * The Settings section includes **Enable Remote Control for all sessions**, which sets [`remoteControlAtStartup`](/docs/en/settings-reference#remotecontrolatstartup) to control whether [new interactive sessions connect to Remote Control automatically](/docs/en/remote-control#enable-remote-control-for-all-sessions). Requires Claude Code v2.1.203 or later.

127 139 

128 When you turn the toggle on or off in a VS Code window, the change applies to the sessions already open in that VS Code window, not only to sessions you start afterwards. If you turn it off, the open sessions disconnect. With Claude Code v2.1.261 or later, the change also reaches sessions open in your other VS Code windows.140 When you turn the toggle on or off in a VS Code window, the change applies to the sessions already open in that VS Code window, not only to sessions you start afterwards. If you turn it off, the open sessions disconnect. With Claude Code v2.1.261 or later, the change also reaches sessions open in your other VS Code windows.


173* To attach files, hold `Shift` while dragging them into the prompt box.185* To attach files, hold `Shift` while dragging them into the prompt box.

174* To remove an attachment from context, click the X on it.186* To remove an attachment from context, click the X on it.

175 187 

188### Paste text

189 

190Text you paste stays visible in the prompt box, rather than collapsing to a placeholder as it does [in the terminal](/docs/en/terminal-config#paste-large-content). In sessions where Claude Code [marks pasted text](/docs/en/terminal-config#how-claude-treats-pasted-text), Claude still sees a large paste as text you pasted rather than typed.

191 

192Claude Code also removes [invisible Unicode characters](/docs/en/interactive-mode#invisible-characters-in-prompts) from text you paste into the prompt box and from anything else you send:

193 

194* If a notice such as `Removed 3 invisible characters from the pasted text` appears when you paste, the text went in without those characters.

195* If a notice about removed characters appears when you send, nothing was sent. The cleaned text is back in the prompt box. Send again to send the text as shown.

196 

176### Resume past conversations197### Resume past conversations

177 198 

178Click the **Session history** button at the top of the Claude Code panel to access your conversation history. You can search by keyword or browse by time.199Click the **Session history** button at the top of the Claude Code panel to access your conversation history. You can search by keyword or browse by time.

Details

7> Run Claude Code in the cloud from your browser or phone. Connect a GitHub repository, submit a task, and review the PR without local setup.7> Run Claude Code in the cloud from your browser or phone. Connect a GitHub repository, submit a task, and review the PR without local setup.

8 8 

9<Note>9<Note>

10 Cloud sessions are in research preview for Pro, Max, and Team users, and for Enterprise users with premium seats or Chat + Claude Code seats.10 Cloud sessions are available on Pro, Max, and Team plans, and for Enterprise users with premium seats or Chat + Claude Code seats.

11</Note>11</Note>

12 12 

13A cloud session runs Claude Code on cloud infrastructure instead of your machine, Anthropic-managed by default. This quickstart starts one from [claude.ai/code](https://claude.ai/code) in your browser. You can also start one from the Claude mobile app, the Desktop app, or your terminal with `claude --cloud`.13A cloud session runs Claude Code on cloud infrastructure instead of your machine, Anthropic-managed by default. This quickstart starts one from [claude.ai/code](https://claude.ai/code) in your browser. You can also start one from the Claude mobile app, the Desktop app, or your terminal with `claude --cloud`.