HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
820pages tracked
773 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
19 Oct 2026
159 pages
+17026 −18959 lines
claude-code
model-config
±changed
+2−1
claude-codechanged
model-config
* **`CLAUDE_CODE_AUTO_MODE_MODEL`**: Claude Code ignores the variable and picks the model for its [auto mode classifier requests](/docs/en/permission-modes#default-classifier-model
* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5.
* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: when the allowlist excludes the [default classifier model](/docs/en/permission-modes#defau
+2 −1 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
headless
±changed
+3−1
claude-codechanged
headless
To set a baseline for the whole session instead of listing individual tools, pass a [permission mode](/docs/en/permission-modes). A run where nothing sets a permission mode takes t
Calls to tools you didn't list run if they need no approval. In a [Manual mode](/docs/en/permission-modes#available-modes) `claude -p` run, a call that needs approval is denied unl
To set a baseline for the whole session instead of listing individual tools, pass a [permission mode](/docs/en/permission-modes) with `--permission-mode`, such as `auto`, `dontAsk`
+3 −1 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
errors
±changed
+26−2
claude-codechanged
errors
| `<tool> was not reviewed and did not run: the conversation is too long for auto mode's classifier` | [Server errors](#was-not-reviewed-and-did-not-run) |
In an interactive session, a dim `Not run · auto mode's check had no usable answer` row appears under the tool call instead of this message. Press `Ctrl+O` to read the message in t
In an interactive session, a dim `Not run · auto mode's check had no usable answer` row appears under the tool call instead of this message. Press `Ctrl+O` to read the message in t
* If the message returns on every retry and names the model you set in [`CLAUDE_CODE_AUTO_MODE_MODEL`](/docs/en/permission-modes#choose-the-classifier-model), check that the API or
When the conversation has grown larger than the classifier's context window:
+26 −2 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `permissionMode` | [`PermissionMode`](#permissionmode) | `undefined` | Permission mode for the session. If you omit it, the session can start in auto mode. See [Permission modes]
| `permissionMode` | [`PermissionMode`](#permissionmode) | `undefined` | Permission mode for the session. If you omit it and nothing else sets a permission mode, such as a [`permis
+1 −1 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
agent-sdk/permissions
±changed
+1−8
claude-codechanged
agent-sdk/permissions
If you don't set one, Claude Code picks the starting permission mode by the rules in [Which mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in):
* A `permissions.defaultMode` from the session's [settings files](/docs/en/settings#where-settings-live) when one applies
* Otherwise the built-in default, which can be [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)
+1 −8 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-docs
government/connectors/microsoft-365
±changed
+5−5
claude-docschanged
government/connectors/microsoft-365
Setup has two parts. First, someone with administrator access in Microsoft Entra ID registers an application in your Microsoft tenant. Then you enter that application's details on
Setup has two parts. First, someone with administrator access in Microsoft Entra ID registers an application in your Microsoft tenant. Then you enter that application's details on
Open the [Config](/docs/government/org-admin/configuration) page in another tab and find the **Microsoft 365** card. You'll paste two values from Entra into it at the end.
Open the [Config](/docs/government/org-admin/configuration.md) page in another tab and find the **Microsoft 365** card. You'll paste two values from Entra into it at the end.
Downloads of OneDrive and SharePoint files also need access to your Microsoft tenant's SharePoint and OneDrive hosts. For Office documents, see the network hosts step of [Set up th
+5 −5 lines
Upstream edited 19 Oct 2026 17:13 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
government/connectors/microsoft-365
±changed
+45−47
claude-docschanged
government/connectors/microsoft-365
<Steps>
<Step title="Create the app registration">
1. In the [Microsoft Entra admin center](https://entra.microsoft.com), open **App registrations** from the left navigation and select **+ New registration**.
2. Enter a display name, for example "Claude for Government Microsoft 365".
3. Under **Supported account types**, choose **Single tenant only - \{your organization}**. Older versions of the portal label this option **Accounts in this organizational dir
+45 −47 lines
Upstream edited 19 Oct 2026 17:13 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
government/connectors/microsoft-365
±changed
+2−0
claude-docschanged
government/connectors/microsoft-365
Downloads of OneDrive and SharePoint files also need access to your Microsoft tenant's SharePoint and OneDrive hosts. For Office documents, see the network hosts step of [Set up th
+2 −0 lines
Upstream edited 19 Oct 2026 17:13 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 19 Oct 2026 17:07 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
* Your account is close to or at its usage limit. To keep suggestions on until you reach the limit, set [`CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION`](/docs/en/env-vars) to `true`. Befor
* Your account is close to or at its usage limit. To keep this skip from applying until you reach the limit, set [`CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION`](/docs/en/env-vars) to `tru
+1 −1 lines
Upstream edited 19 Oct 2026 16:48 UTC Recorded here 19 Oct 2026 17:07 UTC
claude-code
sandbox-environments
±changed
+30−30
claude-codechanged
sandbox-environments
> For the broader security model, see [Security](/docs/en/security). For Agent SDK deployments, see [Secure deployment](/docs/en/agent-sdk/secure-deployment).
> For the broader security model, see [Security](/docs/en/security.md). For Agent SDK deployments, see [Secure deployment](/docs/en/agent-sdk/secure-deployment.md).
The [sandboxed Bash tool](/docs/en/sandboxing) is built into Claude Code and restricts Bash commands. Built-in file tools, MCP servers, and hooks still run directly on your host. E
The [sandboxed Bash tool](/docs/en/sandboxing.md) is built into Claude Code and restricts Bash commands. Built-in file tools, MCP servers, and hooks still run directly on your host
> Sandbox isolation reduces the impact of a breach, but it does not eliminate risk. Any approach that allows network egress can still leak data the agent can read, and any approach
+30 −30 lines
Upstream edited 19 Oct 2026 16:44 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
sandbox-environments
±changed
+11−11
claude-codechanged
sandbox-environments
<Info>
For the broader security model, see [Security](/docs/en/security). For Agent SDK deployments, see [Secure deployment](/docs/en/agent-sdk/secure-deployment).
</Info>
> [!NOTE]
>
+11 −11 lines
Upstream edited 19 Oct 2026 16:44 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
sandbox-environments
±changed
+9−3
claude-codechanged
sandbox-environments
Once the settings file is in place, launch Claude Code with `npx` and pass `claude` as the command to wrap:
Install the runtime globally, under a prefix outside every path you allow writes to:
npx @anthropic-ai/sandbox-runtime claude
npm install -g @anthropic-ai/sandbox-runtime
Claude Code starts inside the sandbox with the filesystem and network boundaries you configured. The same command works for sandboxing standalone MCP servers or other helper proces
+9 −3 lines
Upstream edited 19 Oct 2026 16:44 UTC Recorded here 19 Oct 2026 17:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 19 Oct 2026 16:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+4−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.42304.2" description="2026-10-19">
No configuration changes in this release.
</Update>
+4 −0 lines
Upstream edited 19 Oct 2026 16:36 UTC Recorded here 19 Oct 2026 16:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+1−1
claude-docschanged
third-party/claude-desktop/configuration
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to sign in with your br
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to fetch a key via brow
+1 −1 lines
Upstream edited 19 Oct 2026 16:36 UTC Recorded here 19 Oct 2026 16:37 UTC
claude-docs
third-party/claude-desktop/claude-api
±changed
+1−1
claude-docschanged
third-party/claude-desktop/claude-api
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to sign in with your br
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to fetch a key via brow
+1 −1 lines
Upstream edited 19 Oct 2026 16:36 UTC Recorded here 19 Oct 2026 16:37 UTC
claude-docs
cowork/changelog
±changed
+20−0
claude-docschanged
cowork/changelog
<Update label="v2.42304.2" description="2026-10-19">
Bundled Claude Code version: 2.1.299.
**General**
+20 −0 lines
Upstream edited 19 Oct 2026 16:36 UTC Recorded here 19 Oct 2026 16:37 UTC
claude-code
hooks-guide
±changed
+24−29
claude-codechanged
hooks-guide
The exit code determines what happens next:
* **Exit 0**: your hook reports no objection through its exit code.
* For a `PreToolUse` hook this doesn't approve the tool call: the normal [permission flow](/docs/en/permissions) still applies.
* For `UserPromptSubmit`, `UserPromptExpansion`, `SessionStart`, and `PostModelSwitch` hooks, Claude Code adds stdout it [treats as plain text](/docs/en/hooks#exit-code-0) to Cla
+24 −29 lines
Upstream edited 19 Oct 2026 16:35 UTC Recorded here 19 Oct 2026 16:37 UTC
claude-code
hooks
±changed
+18−24
claude-codechanged
hooks
Your hook's exit code tells Claude Code whether to continue with the action that triggered the hook, such as a tool call or a prompt. A run that finishes has one of three outcomes:
When your hook's run finishes, Claude Code uses its exit code to decide whether to continue with the action that triggered it, such as a tool call or a prompt:
Exit 0 means success, and is the intended exit code when you print JSON for structured control.
For most events, Claude Code writes stdout to the debug log and doesn't show it in the transcript. The exceptions are `UserPromptSubmit`, `UserPromptExpansion`, `SessionStart`, and
+18 −24 lines
Upstream edited 19 Oct 2026 16:35 UTC Recorded here 19 Oct 2026 16:37 UTC
claude-docs
government/config/settings
±changed
+5−1
claude-docschanged
government/config/settings
Each conversation turn produces events such as `user_prompt`, `api_request`, and `tool_result` that record the model, token counts, durations, and tool names. Every record also car
Each conversation turn produces events such as `user_prompt`, `api_request`, and `tool_result` that record the model, token counts, durations, and tool names. Every record from Cla
<Note>
On Claude Desktop versions earlier than 1.37937.0, and for a member who has not signed in again since updating to that version or later, `enduser.id` carries the operating-system
+5 −1 lines
Upstream edited 19 Oct 2026 14:23 UTC Recorded here 19 Oct 2026 14:37 UTC
18 Oct 2026
5 pages
+30 −32 lines
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 18 Oct 2026 23:07 UTC
claude-code
changelog
±changed
+4−0
claude-codechanged
changelog
<Update label="2.1.303" description="October 18, 2026">
* Bug fixes and reliability improvements
</Update>
+4 −0 lines
Upstream edited 18 Oct 2026 22:38 UTC Recorded here 18 Oct 2026 23:07 UTC
claude-docs
cowork/changelog
±changed
+1−1
claude-docschanged
cowork/changelog
* Added Environment to the sidebar's Group by menu. It groups sessions by their saved local or SSH environment, or by folder or repository when they have none. Custom groups are
* Changed the sidebar to group sessions by environment, or by folder or repository when there is no saved environment. Custom groups are now called sections (not yet in third-par
+1 −1 lines
Upstream edited 18 Oct 2026 20:40 UTC Recorded here 18 Oct 2026 21:07 UTC
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 18 Oct 2026 04:37 UTC
mcp
seps/index
±changed
+1−1
mcpchanged
seps/index
* **Final**: 42
* **Final**: 43
+1 −1 lines
Recorded here 18 Oct 2026 02:07 UTC
mcp
seps/2640-skills-extension
±changed
+2−2
mcpchanged
seps/2640-skills-extension
> specification](/specification/latest) and its changelog for authoritative
> specification](/specification/latest.md) and its changelog for authoritative
* [Skills Over MCP Working Group charter](https://modelcontextprotocol.io/community/skills-over-mcp/charter)
* [Skills Over MCP Working Group charter](https://modelcontextprotocol.io/community/skills-over-mcp/charter.md)
+2 −2 lines
Upstream edited 18 Oct 2026 02:02 UTC Recorded here 22 Oct 2026 20:37 UTC
mcp
seps/2640-skills-extension
±changed
+11−17
mcpchanged
seps/2640-skills-extension
<div className="flex items-center gap-2 mb-4">
<Badge color="green" shape="pill">
Final
</Badge>
+11 −17 lines
Upstream edited 18 Oct 2026 02:02 UTC Recorded here 20 Oct 2026 20:07 UTC
mcp
seps/2640-skills-extension
±changed
+3−3
mcpchanged
seps/2640-skills-extension
* [SEP-2133]: Extensions
* [SEP-2549]: TTL for list results
* [SEP-2076]: Agent Skills as first-class primitive (alternative approach)
* [SEP-2133][]: Extensions
* [SEP-2549][]: TTL for list results
+3 −3 lines
Upstream edited 18 Oct 2026 02:02 UTC Recorded here 18 Oct 2026 02:07 UTC
17 Oct 2026
22 pages
+1492 −1462 lines
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 17 Oct 2026 04:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `denyWrite` | `string[]` | `[]` | File path patterns to deny write access to. To block sandboxed writes to a file in the session's working directory, list its absolute path. If y
| `denyWrite` | `string[]` | `[]` | File path patterns to deny write access to. To block sandboxed writes to a file in the session's working directory, list its absolute path. |
+1 −1 lines
Upstream edited 17 Oct 2026 04:13 UTC Recorded here 17 Oct 2026 04:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
To keep sandboxed commands from writing to a file, list its absolute path under [`denyWrite`](/docs/en/settings-reference#sandbox-filesystem-denywrite) in your sandbox settings, su
To keep sandboxed commands from writing to a file, list its absolute path under [`denyWrite`](/docs/en/settings-reference#sandbox-filesystem-denywrite) in your sandbox settings, su
+1 −1 lines
Upstream edited 17 Oct 2026 04:13 UTC Recorded here 17 Oct 2026 04:37 UTC
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 17 Oct 2026 01:37 UTC
claude-code
sandboxing
±changed
+106−112
claude-codechanged
sandboxing
<Note>
This page covers the sandbox around shell commands on your own machine. Other pages cover related questions:
* For how a cloud session is isolated, see [Security and isolation](/docs/en/claude-code-on-the-web#security-and-isolation)
* To compare other isolation approaches such as dev containers, custom containers, and virtual machines, see [Sandbox environments](/docs/en/sandbox-environments)
+106 −112 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/mcp
±changed
+629−665
claude-codechanged
agent-sdk/mcp
<Note>
This page covers MCP configuration for the Agent SDK. To add MCP servers to the Claude Code CLI so they load in every project, see [MCP installation scopes](/docs/en/mcp#mcp-inst
</Note>
> [!NOTE]
>
+629 −665 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/hooks
±changed
+570−596
claude-codechanged
agent-sdk/hooks
<Steps>
<Step title="An event fires">
Something happens during agent execution and the SDK fires an event: a tool is about to be called (`PreToolUse`), a tool returned a result (`PostToolUse`), a subagent started o
</Step>
+570 −596 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
sub-agents
±changed
+15−5
claude-codechanged
sub-agents
| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. Same format as `tools`. An entry with a specifier, such as `Bash(git push *)`, still [removes th
| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. Same format as `tools`. An entry with a specifier, such as `Bash(git push *)`, still [removes th
To restrict tools, use the `tools` field as an allowlist or the `disallowedTools` field as a denylist. This example uses `tools` to allow only Read, Grep, Glob, and Bash. The subag
#### Restrict which tools a subagent can use
+15 −5 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
sandboxing
±changed
+12−0
claude-codechanged
sandboxing
### `/sandbox` prints `Sandbox settings not changed`
This line means `/sandbox` couldn't save the choice you made in its panel to your project's `.claude/settings.local.json`:
```text theme={null}
+12 −0 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
plugins/mods/events
±changed
+6−3
claude-codechanged
plugins/mods/events
On `main`, the hook returns `deny`, even when a rule allows `git push`. On another branch, and for other commands, the call gets the decision it would get without the mod.
The hook denies `git push` on `main` and passes every other call through:
* **On `main`**: the hook returns `deny`, even when a rule allows `git push`
* **On another branch, and for other commands**: the call gets the decision it would get without the mod
+6 −3 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
plugins/mods/create
±changed
+1−1
claude-codechanged
plugins/mods/create
In the `default` and `acceptEdits` [permission modes](/docs/en/permission-modes#protected-paths), Claude Code asks before Claude creates each of the mod's files, because `~/.
In the `default` and `acceptEdits` [permission modes](/docs/en/permission-modes), Claude Code asks before Claude creates each of the mod's files, because the mods folder is a
+1 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
permissions
±changed
+16−2
claude-codechanged
permissions
MCP rules use the server name as configured in Claude Code, optionally followed by the name of a tool from that server.
To match every tool from an MCP server, write `mcp__<server>__*`. To match one tool, write its full name, `mcp__<server>__<tool>`.
For `<server>`, write the server's name the way it appears in that server's tool names. These examples show the rule to write for a name with special characters, a server from a pl
+16 −2 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
permission-modes
±changed
+7−4
claude-codechanged
permission-modes
The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsibility for actions taken without permission
<span id="bypass-permissions-acceptance" />The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsib
* With `skipDangerousModePermissionPrompt` set only in `.claude/settings.local.json`, the background session starts with the bypass request ignored and pins the notice `Bypass perm
On Linux and macOS, Claude Code refuses to start in this mode when running as root or under `sudo`:
+7 −4 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `trigger`: What caused the change. One of `"shift_tab"`, `"exit_plan_mode"`, `"auto_gate_denied"`, or `"auto_opt_in"`. Absent when the transition originates from the SDK or bridg
* `trigger`: What caused the change. One of `"shift_tab"`, `"exit_plan_mode"`, `"auto_gate_denied"`, or `"auto_opt_in"`. Absent for some changes, such as when the SDK sets the perm
+1 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
hooks-guide
±changed
+18−5
claude-codechanged
hooks-guide
* **Any other exit code**: for most events, the outcome depends on what your hook printed to stdout:
* **Any other exit code**: for most events, the action proceeds as a [non-blocking error](/docs/en/hooks#exit-code-output), unless the hook is one [whose failure blocks the action]
* `"allow"`: skip the interactive permission prompt. Deny and ask rules, including enterprise managed deny lists, still apply, as do prompts for reads from [network paths](/docs/en
* `"allow"`: skip the interactive permission prompt. Deny and ask rules, including enterprise managed deny lists, still apply, as do prompts for:
+18 −5 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
hooks
±changed
+51−18
claude-codechanged
hooks
| `onFailure` | no | What happens to the action when the hook fails: `"continue"`, the default, or `"block"`. See [Block the action when a hook fails](#block-the-action-when-a-hook
| `onFailure` | no | Whether the action that triggered the hook goes ahead when the hook fails: `"continue"` or `"block"`. See [Block the action when a hook fails](#block-the-actio
* **Non-blocking error**: your hook exits with any other code, or fails in some other way, such as not starting or printing invalid JSON. The action goes ahead, and on events such
What your hook prints to stdout can change the outcome. For example, if a `PreToolUse` hook exits 1 but prints JSON that passes validation, the run is a success and the JSON fields
+51 −18 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
errors
±changed
+3−1
claude-codechanged
errors
| `Bypass permissions was requested at launch and ignored` | [Skip all checks with bypassPermissions mode](/docs/en/permission-modes#bypass-permissions-acceptance) |
* A streaming request the API never answers with response headers, on a connection where the [first-byte deadline runs](/docs/en/network-config#streaming-idle-watchdogs): Claude Co
* A streaming request the API never answers with response headers, on a connection where the [first-byte deadline runs](/docs/en/network-config#streaming-idle-watchdogs): Claude Co
* If the entry names a connected MCP server, compare the entry with that server's name as the server's [tool names](/docs/en/permissions#mcp) spell it, such as `reports__v2` in `mc
+3 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-view
±changed
+2−2
claude-codechanged
agent-view
* **Dispatched from an agent view you opened with `←`**: the target's own configuration comes first, and the permission mode of the session you came from applies when nothing else
* **Dispatched from an agent view you opened with `←`**: Claude Code takes the new session's permission mode from the target directory's configuration first, then from the session
2. The permission mode of the session you came from
2. The permission mode of the session you came from. If that session was in `bypassPermissions` mode, the new session can start in Manual mode instead, with the notice `Bypass perm
+2 −2 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `setModel()` | Changes the model (only available in streaming input mode). Passing `undefined` or the string `"default"` resets to [Claude Code's default model](/docs/en/model-co
| `setModel()` | Changes the model (only available in streaming input mode). Passing `undefined` or the string `"default"` resets to [Claude Code's default model](/docs/en/model-co
+1 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
| `set_model(model)` | Change the model for the current session. Pass `None` to reset to [Claude Code's default model](/docs/en/model-config) |
| `set_model(model)` | Change the model for the current session. Pass `None` to reset to [Claude Code's default model](/docs/en/model-config). A session in `auto` mode [changes to
+1 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-sdk/permissions
±changed
+14−3
claude-codechanged
agent-sdk/permissions
Run [hooks](/docs/en/agent-sdk/hooks) first. A hook can deny the call outright or pass it on. A hook that returns `allow` does not skip the deny and ask rules below; those are
Run [hooks](/docs/en/agent-sdk/hooks) first. A hook can deny the call outright or pass it on. A hook that returns `allow` does not skip the deny and ask rules below; those are
Pass `permission_mode` (Python) or `permissionMode` (TypeScript) when creating a query. This mode applies for the entire session unless changed dynamically.
Pass `permission_mode` (Python) or `permissionMode` (TypeScript) when creating a query.
File edits are never auto-approved in plan mode, even when an allow rule matches. They prompt through your `canUseTool` callback instead. On Claude Code v2.1.212 or later, shell co
+14 −3 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-sdk/mcp
±changed
+10−1
claude-codechanged
agent-sdk/mcp
MCP tools follow the naming pattern `mcp__<server-name>__<tool-name>`. For example, a GitHub server named `"github"` with a `list_issues` tool becomes `mcp__github__list_issues`.
MCP tools are named `mcp__<server-name>__<tool-name>`, where `<server-name>` is the name you register the server under, such as its key in `mcpServers`.
Characters in the server name such as `.` and spaces are replaced by `_`. This table shows the full name of a `list_issues` tool for two server keys:
+10 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-sdk/hooks
±changed
+1−1
claude-codechanged
agent-sdk/hooks
| `matcher` | `string` | `undefined` | Pattern matched against the event's filter field, following the [rules for matchers in settings files](/docs/en/hooks#matcher-patterns). For
| `matcher` | `string` | `undefined` | Pattern matched against the event's filter field, following the [rules for matchers in settings files](/docs/en/hooks#matcher-patterns). For
+1 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
agent-sdk/custom-tools
±changed
+1−1
claude-codechanged
agent-sdk/custom-tools
Pass the MCP server you created to `query` via the `mcpServers` option. The key in `mcpServers` becomes the `{server_name}` segment in each tool's fully qualified name: `mcp__{serv
Pass the MCP server you created to `query` via the `mcpServers` option. Each tool's [fully qualified name](/docs/en/agent-sdk/mcp#tool-naming-convention) is `mcp__{server_name}__{t
+1 −1 lines
Upstream edited 17 Oct 2026 01:27 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
network-config
±changed
+7−3
claude-codechanged
network-config
Claude Code runs four independent timers that abort a streaming model response when it goes quiet, so a dead connection fails and retries instead of hanging. The first-byte deadlin
Claude Code runs four independent timers that abort a streaming model response when it goes quiet, so a dead connection fails and retries instead of hanging. A request that gets no
* **Where the first-byte deadline runs**: the first attempt ends at that deadline. To change it, set `CLAUDE_STREAM_FIRST_BYTE_TIMEOUT_MS`. For the retry's wait, see [No response f
* **On the other connections**: the request ends after 5 to 6 minutes, when the body idle timeout fires, unless you turned that timeout off. To end it sooner, lower `API_TIMEOUT_MS
+7 −3 lines
Upstream edited 17 Oct 2026 01:16 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
prompt-caching
±changed
+10−12
claude-codechanged
prompt-caching
<img src="https://mintcdn.com/claude-code/VbDJw--l6T9a9Wvm/images/prompt-caching-prefix.svg?fit=max&auto=format&n=VbDJw--l6T9a9Wvm&q=85&s=f2e8f0b8298a50305fe428ca3f1d1594" classNam
<img src="https://mintcdn.com/claude-code/_xqph1dUOslCOwsj/images/prompt-caching-prefix-dark.svg?fit=max&auto=format&n=_xqph1dUOslCOwsj&q=85&s=297dc1c639f0915cae858d0c4b6f3be5" cla
, there is no cache left to read, so the summarization request reprocesses the full history as uncached input. This i
After a break longer than the [cache lifetime](#cache-lifetime), there is no cache left to read, so the summarization request reprocesses the full history as uncached input. This i
On a Pro or Max plan, when you resume a large session after a long break, Claude Code [offers to resume from a summary](/docs/en/sessions#resume-from-a-summary) so later requests d
+1 −3 lines
Upstream edited 17 Oct 2026 01:14 UTC Recorded here 17 Oct 2026 01:37 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
* **Cache misses**: your first message after a break longer than the [cache lifetime](/docs/en/prompt-caching#cache-lifetime) misses the cache and reprocesses your full context. Th
* **Cache misses**: your first message after a break longer than the [cache lifetime](/docs/en/prompt-caching#cache-lifetime) misses the cache and reprocesses your full context. Th
+1 −1 lines
Upstream edited 17 Oct 2026 01:14 UTC Recorded here 17 Oct 2026 01:37 UTC
16 Oct 2026
258 pages
+6410 −3320 lines
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 16 Oct 2026 21:37 UTC
claude-code
plugins/mods/gallery
±changed
+86−118
claude-codechanged
plugins/mods/gallery
<Steps>
<Step title="Create the mod">
Create a directory named `gallery` with `.claude-plugin` and `hooks` directories inside it. [Create a mod](/docs/en/plugins/mods/create#write-a-mod-yourself) explains the files
Save the manifest as `gallery/.claude-plugin/plugin.json`:
+86 −118 lines
Upstream edited 16 Oct 2026 21:17 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/mods/reference
±changed
+44−2
claude-codechanged
plugins/mods/reference
| [`Box`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `key`, flex layout, `gap`, `padding`, `margin`, `width`, `height`, [`borderStyle`](#box-border-styles), `bac
| [`Text`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `color`, `backgroundColor`, `bold`, `italic`, `underline`, `dimColor`, `inverse`, `wrap` | ✓ | ✓ | ✓ |
| [`Box`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `key`, flex layout, [`gap`, `padding`, `margin`](#box-spacing-steps), `width`, `height`, [`borderStyle`](#bo
| [`Text`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `color`, `backgroundColor`, [`bold`](#text-bold), `italic`, `underline`, `dimColor`, `inverse`, `wrap`, [`s
* **`Text`**: `size`, `mono`, and `tabular`
+44 −2 lines
Upstream edited 16 Oct 2026 21:17 UTC Recorded here 16 Oct 2026 21:37 UTC
claude-code
plugins/mods/interface
±changed
+2−2
claude-codechanged
plugins/mods/interface
| `Box` | A flex container. Takes layout props such as `flexDirection`, `columnGap`, `padding`, [`borderStyle`](/docs/en/plugins/mods/reference#box-border-styles), and `width`. | E
| `Text` | Styled text. Takes `color`, `bold`, `dimColor`, `italic`, and `wrap`. A `color` is a theme key or a color such as `'red'`. A `wrap` is `'wrap'`, `'truncate'`, `'truncate
| `Box` | A flex container that takes layout props such as `flexDirection`, [`borderStyle`](/docs/en/plugins/mods/reference#box-border-styles), and `width`. Spacing props such as `
| `Text` | Styled text. Takes `color`, `bold`, `dimColor`, `italic`, `wrap`, and others such as [`weight`](/docs/en/plugins/mods/reference#text-typography). A `color` is a theme ke
+2 −2 lines
Upstream edited 16 Oct 2026 21:17 UTC Recorded here 16 Oct 2026 21:37 UTC
claude-code
plugins/mods/gallery
±changed
+1−1
claude-codechanged
plugins/mods/gallery
`Text` draws a string with the styles you give it. This sample shows one line for each style:
`Text` draws a string with the styles you give it. This sample shows plain text and eight styles, one on each line:
+1 −1 lines
Upstream edited 16 Oct 2026 21:17 UTC Recorded here 16 Oct 2026 21:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 16 Oct 2026 21:07 UTC
claude-code
changelog
±changed
+77−0
claude-codechanged
changelog
<Update label="2.1.302" description="October 16, 2026">
**Added**
* Added `CLAUDE_CODE_AUTO_MODE_MODEL` to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode
+77 −0 lines
Upstream edited 16 Oct 2026 21:03 UTC Recorded here 16 Oct 2026 21:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+13−0
claude-codechanged
plugins/mods/troubleshoot
<h3 id="another-mods-band-shows-and-yours-doesnt">
Another mod's band shows and yours doesn't
</h3>
There is one band above the prompt, and every mod shares it. A mod that runs [before yours](/docs/en/plugins/mods/events#the-order-mods-run-in) replaces your band when it returns a
+13 −0 lines
Upstream edited 16 Oct 2026 20:59 UTC Recorded here 16 Oct 2026 21:07 UTC
claude-code
sandboxing
±changed
+2−2
claude-codechanged
sandboxing
* Explicit [deny rules](/docs/en/permissions) are always respected
* `rm` or `rmdir` commands that target a [critical path](/docs/en/permission-modes#critical-paths) still go through the regular permission flow
* A command in a [form that a `Bash` deny rule matches](/docs/en/permissions#bash-rule-limits) is still blocked
* `rm` or `rmdir` commands recognized as targeting a [critical path](/docs/en/permission-modes#which-paths-are-critical) still go through the regular permission flow
+2 −2 lines
Upstream edited 16 Oct 2026 20:56 UTC Recorded here 16 Oct 2026 21:07 UTC
claude-code
permissions
±changed
+0−2
claude-codechanged
permissions
* Explicit deny rules still apply
* `rm` or `rmdir` commands that target a [critical path](/docs/en/permission-modes#critical-paths) still go through the regular permission flow
+0 −2 lines
Upstream edited 16 Oct 2026 20:56 UTC Recorded here 16 Oct 2026 21:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 16 Oct 2026 20:37 UTC
claude-code
zero-data-retention
±changed
+9−9
claude-codechanged
zero-data-retention
Claude for Enterprise organizations that have enabled HIPAA can bring the Claude Code CLI and the Code tab in Claude Desktop under their Business Associate Agreement (BAA) without
Claude for Enterprise organizations that have enabled HIPAA can bring the Claude Code CLI and the Code tab in Claude Desktop under their Business Associate Agreement (BAA) without
* [Analytics](/docs/en/analytics) dashboard
* [Server-managed settings](/docs/en/server-managed-settings)
* [Analytics](/docs/en/analytics.md) dashboard
+9 −9 lines
Upstream edited 16 Oct 2026 20:33 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
zero-data-retention
±changed
+6−6
claude-codechanged
zero-data-retention
<Note>
ZDR is not included in the standard Claude for Enterprise plan and cannot be enabled from your admin settings. It is available to qualified accounts and requires separate enablem
</Note>
> [!NOTE]
>
+6 −6 lines
Upstream edited 16 Oct 2026 20:33 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
zero-data-retention
±changed
+1−0
claude-codechanged
zero-data-retention
| [Chat and Cowork unified](https://support.claude.com/en/articles/17444462-set-up-and-manage-the-new-unified-claude-experience-for-your-enterprise-organization) | Requires cloud s
+1 −0 lines
Upstream edited 16 Oct 2026 20:33 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
agent-sdk/skills
±changed
+23−23
claude-codechanged
agent-sdk/skills
Near the start of the stream, the SDK yields a system message with subtype `init`. Check its `skills` array to confirm your skills loaded before Claude starts working. The array in
Near the start of the stream, the SDK yields a system message with subtype `init`. Check its `skills` array to confirm your skills loaded before Claude starts working. The array in
By default, both you and Claude can invoke any skill. You can restrict either path through the skill's [frontmatter](/docs/en/skills#control-who-invokes-a-skill). For definitions o
By default, both you and Claude can invoke any skill. You can restrict either path through the skill's [frontmatter](/docs/en/skills.md#control-who-invokes-a-skill). For definition
A skill with [`user-invocable: false`](/docs/en/skills#control-who-invokes-a-skill) in its frontmatter doesn't appear in this list or in the `skills` array from [Confirm skills loa
+23 −23 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/skills
±changed
+300−318
claude-codechanged
agent-sdk/skills
<Note>
Skills are discovered through the filesystem setting sources. With default `query()` options, the SDK loads user and project sources, so skills in `~/.claude/skills/`, `<cwd>/.cl
</Note>
> [!NOTE]
>
+300 −318 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
skills
±changed
+7−5
claude-codechanged
skills
You can also stack several skills at the start of one message. Typing `/write-tests /fix-issue 123` loads both skills and passes the trailing text `123` as `$ARGUMENTS` to each of
Claude Code expands the first skill plus up to five more stacked after it. Expansion stops at the first token that isn't an inline user-invocable skill, so a skill that runs as a [
+7 −5 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
code-review-local
±changed
+1−1
claude-codechanged
code-review-local
* **Without `ultra`**: everything left is the review target, even when it starts with another command name. `/code-review /fix-issue 123` reviews with `/fix-issue 123` as target te
* **Without `ultra`**: everything left is the review target, even when it starts with another command name. `/code-review /fix-issue 123` reviews with `/fix-issue 123` as target te
+1 −1 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
agent-sdk/skills
±changed
+1−1
claude-codechanged
agent-sdk/skills
* [Pass arguments to skills](/docs/en/skills#pass-arguments-to-skills): `$ARGUMENTS`, `$0`, `$1`, and skill stacking. The [full substitution table](/docs/en/skills#available-string
* [Pass arguments to skills](/docs/en/skills#pass-arguments-to-skills): `$ARGUMENTS`, `$0`, and `$1`. The [full substitution table](/docs/en/skills#available-string-substitutions)
+1 −1 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
large-codebases
±changed
+6−6
claude-codechanged
large-codebases
<Tip>
For workflow techniques that keep context small in any repository, such as [running exploration in a subagent](/docs/en/best-practices#use-subagents-for-investigation) so file re
</Tip>
> [!TIP]
>
+6 −6 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
claude-security
±changed
+18−20
claude-codechanged
claude-security
<Steps>
<Step title="Open the Claude Security menu">
Run `/claude-security` and pick **Scan codebase**.
</Step>
**1. Open the Claude Security menu**
+18 −20 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
security-guidance
±changed
+1−1
claude-codechanged
security-guidance
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
* `Plugin "<name>" not found in marketplace "claude-plugins-official"`: your local copy of the marketplace catalog may be out of date. Refresh it with `/plugin marketplace update c
+1 −1 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
* `Plugin "<name>" not found in marketplace "claude-plugins-official"`: your local copy of the marketplace catalog may be out of date. Refresh it with `/plugin marketplace upda
+1 −1 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
large-codebases
±changed
+1−1
claude-codechanged
large-codebases
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
* `Plugin "<name>" not found in marketplace "claude-plugins-official"`: your local copy of the marketplace catalog may be out of date. Refresh it with `/plugin marketplace update c
+1 −1 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
claude-security
±changed
+3−3
claude-codechanged
claude-security
If the install fails, the fix depends on which message Claude Code reports:
If the install fails, match the message Claude Code reports:
* If it reports `Marketplace "claude-plugins-official" not found`, add the marketplace with `/plugin marketplace add anthropics/claude-plugins-official`, then retry the install.
* If it reports that it [can't find the plugin in the marketplace](/docs/en/plugins/install#install-a-plugin), check the plugin name for a typo.
* `Marketplace "claude-plugins-official" not found`: add the marketplace with `/plugin marketplace add anthropics/claude-plugins-official`, then retry the install.
+3 −3 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
channels
±changed
+4−4
claude-codechanged
channels
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
* `Plugin "<name>" not found in marketplace "claude-plugins-official"`: your local copy of the marketplace catalog may be out of date. Refresh it with `/plugin marketplace
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
* `Plugin "<name>" not found in marketplace "claude-plugins-official"`: your local copy of the marketplace catalog may be out of date. Refresh it with `/plugin marketplace
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
+4 −4 lines
Upstream edited 16 Oct 2026 20:27 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
terminal-config
±changed
+2−1
claude-codechanged
terminal-config
Claude Code paints `userMessageBackground`, `bashMessageBackgroundColor`, and `memoryBackgroundColor` in both the default and fullscreen renderers. It uses `userMessageBackground
Claude Code uses `userMessageBackgroundHover`, `selectionBg`, and `composerSidebarBackground` only in [fullscreen rendering mode](/docs/en/fullscreen). It paints `userMessageBack
| `composerSidebarBackground` | Background of the panel beside the conversation, such as the [diff panel](/docs/en/fullscreen#watch-your-changes-in-the-diff-panel) or a [mod's pa
+2 −1 lines
Upstream edited 16 Oct 2026 20:21 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `type`: (`"input"`, `"output"`, `"cacheRead"`, `"cacheCreation"`). The `"input"` type excludes tokens read from or written to the prompt cache, which are counted under `"cacheRea
* `type`: (`"input"`, `"output"`, `"cacheRead"`, `"cacheCreation"`). The `"input"` type excludes tokens read from or written to the prompt cache, which are counted under `"cacheRea
+1 −1 lines
Upstream edited 16 Oct 2026 20:21 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
auto-mode-classifier-billing
±changed
+11−11
claude-codechanged
auto-mode-classifier-billing
In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), a classifier checks actions such as shell commands and network requests before they run. Wherever [serve
In [auto mode](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode), a classifier checks actions such as shell commands and network requests before they run. Wherever [se
Where the notice can't wait for an answer, Claude Code reports the same text and the session continues in auto mode, unless a gateway acknowledgment on this machine in the last 24
Where the notice can't wait for an answer, Claude Code reports the same text and the session continues in auto mode, unless a gateway acknowledgment on this machine in the last 24
If a gateway is the cause, ask your company's admin or your gateway provider to pass requests and replies through unchanged. That means forwarding request headers and body fields a
+11 −11 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
features-overview
±changed
+241−237
claude-codechanged
features-overview
<Note>
For how the core agentic loop works, see [How Claude Code works](/docs/en/how-claude-code-works).
</Note>
> [!NOTE]
>
+241 −237 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
features-overview
±changed
+1−1
claude-codechanged
features-overview
| **Determinism** | Always fires on its event; the trigger is guaranteed | Claude interprets the instructions; outcome can vary |
| **Determinism** | Fires on its event without Claude deciding | Claude interprets the instructions; outcome can vary |
+1 −1 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
claude-directory
±changed
+1−1
claude-codechanged
claude-directory
tips: [<>Use <C>$ARGUMENTS</C> in the file to accept parameters: <C>/fix-issue 123</C></>, 'If a skill and command share a name, the skill takes precedence', 'New command
tips: [<>Use <C>$ARGUMENTS</C> in the file to accept parameters: <C>/fix-issue 123</C></>, 'If a skill and command share a name, the skill takes precedence', 'New command
+1 −1 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
auto-mode-classifier-billing
±changed
+3−1
claude-codechanged
auto-mode-classifier-billing
At the prompt, Claude Code holds the first action it would check that way until you answer. Nothing is broken: auto mode keeps working, and its classifier requests are billed as th
At the prompt, Claude Code holds the first action it would check that way until you answer. Auto mode keeps working, and its classifier requests are billed as they were before.
The most common cause is an LLM gateway or proxy between Claude Code and the API, and when Claude Code can identify one, the notice names it. Press **Enter** to continue, or see [M
+3 −1 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
agent-view
±changed
+1−1
claude-codechanged
agent-view
Except in the kept cases covered in [What deleting a session removes](#what-deleting-a-session-removes), deleting removes the session from the list, and a worktree Claude created f
Except in the kept cases covered in [What deleting a session removes](#what-deleting-a-session-removes), deleting removes the session from the list, and a worktree Claude created f
+1 −1 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
agent-teams
±changed
+5−5
claude-codechanged
agent-teams
The team's shared directories are cleaned up automatically when the session ends, so there's no separate cleanup step. See [Architecture](#architecture) for which directories are r
The team's shared directories are cleaned up automatically when the session ends, so there's no separate cleanup step. See [Architecture](#architecture) for which directories are r
* **Team config**: `~/.claude/teams/{team-name}/config.json`
* **Task list**: `~/.claude/tasks/{team-name}/`
+5 −5 lines
Upstream edited 16 Oct 2026 20:20 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
security
±changed
+30−30
claude-codechanged
security
A session's permission mode sets which actions Claude can take without asking you first. Auto mode is the built-in starting permission mode for interactive terminal and VS Code ses
A session's permission mode sets which actions Claude can take without asking you first. Auto mode is the built-in starting permission mode for interactive terminal and VS Code ses
* **Auto mode**: A separate classifier model reviews actions instead of you and blocks the ones it judges unsafe. [How the classifier evaluates actions](/docs/en/permission-modes#h
* **Manual mode**: Claude Code starts with read-only permissions. When it needs to edit files, run tests, or execute commands, it asks you first, and you choose whether to approve
* **Auto mode**: A separate classifier model reviews actions instead of you and blocks the ones it judges unsafe. [How the classifier evaluates actions](/docs/en/permission-modes.m
+30 −30 lines
Upstream edited 16 Oct 2026 20:11 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
security
±changed
+8−8
claude-codechanged
security
<Warning>
**Windows WebDAV security risk**: When running Claude Code on Windows, we recommend against enabling WebDAV or allowing Claude Code to access paths such as `\\*` that may contain
</Warning>
> [!WARNING]
>
+8 −8 lines
Upstream edited 16 Oct 2026 20:11 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
vs-code
±changed
+204−145
claude-codechanged
vs-code
With the extension, you can review and edit Claude's plans before accepting them, auto-accept edits as they're made, @-mention files with specific line ranges from your selection,
With the extension, you can:
* Review and edit Claude's plans before accepting them
* Auto-accept edits as they're made
+204 −145 lines
Upstream edited 16 Oct 2026 20:11 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
security
±changed
+1−1
claude-codechanged
security
See [VS Code security and privacy](/docs/en/vs-code#security-and-privacy) for more information on running Claude Code in an IDE.
See [The built-in IDE MCP server](/docs/en/vs-code#the-built-in-ide-mcp-server) for more information on running Claude Code in an IDE.
+1 −1 lines
Upstream edited 16 Oct 2026 20:11 UTC Recorded here 16 Oct 2026 20:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 16 Oct 2026 20:07 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+1−1
claude-docschanged
third-party/claude-desktop/configuration
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to fetch a key via brow
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to sign in with your br
+1 −1 lines
Upstream edited 16 Oct 2026 19:49 UTC Recorded here 16 Oct 2026 20:07 UTC
claude-docs
third-party/claude-desktop/claude-api
±changed
+1−1
claude-docschanged
third-party/claude-desktop/claude-api
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to fetch a key via brow
| <span id="inferenceanthropicapikey" />Claude API key<br />`inferenceAnthropicApiKey` | `string` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Leave blank to sign in with your br
+1 −1 lines
Upstream edited 16 Oct 2026 19:49 UTC Recorded here 16 Oct 2026 20:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.