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
812pages tracked
765 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 22 Oct 2026
100 on this page
5,591 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
22 Sep 2026
83 pages
+1716 −1107 lines
claude-code
plugins-reference
±changed
+53−14
claude-codechanged
plugins-reference
Plugin agents support `name`, `description`, `model`, `effort`, `maxTurns`, `tools`, `disallowedTools`, `skills`, `memory`, `background`, [`omitClaudeMd`](/docs/en/sub-agents#suppo
For security reasons, plugin-shipped agents don't support `hooks`, `mcpServers`, or `permissionMode`.
#### Plugin agent frontmatter
+53 −14 lines
Upstream edited 22 Sep 2026 17:25 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
output-styles
±changed
+10−8
claude-codechanged
output-styles
### Frontmatter
<h3 id="frontmatter">
Frontmatter reference
</h3>
Output style files support these frontmatter fields:
+10 −8 lines
Upstream edited 22 Sep 2026 17:25 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
memory
±changed
+12−0
claude-codechanged
memory
<h4 id="rules-frontmatter-reference">
Rule frontmatter reference
</h4>
+12 −0 lines
Upstream edited 22 Sep 2026 17:25 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
glossary
±changed
+8−0
claude-codechanged
glossary
## F
### Frontmatter
+8 −0 lines
Upstream edited 22 Sep 2026 17:25 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
claude-directory
±changed
+14−0
claude-codechanged
claude-directory
## Frontmatter fields by file
Skills, command files, subagents, output styles, and rules read their configuration from YAML [frontmatter](/docs/en/glossary#frontmatter) at the top of the file, and each accepts
| File | Frontmatter fields
+14 −0 lines
Upstream edited 22 Sep 2026 17:25 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
discover-plugins
±changed
+1−1
claude-codechanged
discover-plugins
* The marketplace wasn't [added from GitHub, another Git host, or a remote URL](#add-marketplaces).
* The marketplace wasn't [added from GitHub, another Git host, a remote URL](#add-marketplaces), or [claude.ai](#add-from-claude-ai).
+1 −1 lines
Upstream edited 22 Sep 2026 17:24 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
settings-reference
±changed
+2−3
claude-codechanged
settings-reference
Have Claude respond in a language other than English by default. There is no fixed list for responses: Claude Code adds the value verbatim to the system prompt as an instruction to
Have Claude respond in a language other than English by default. There is no fixed list for responses: Claude Code passes the value verbatim to Claude as an instruction to always r
Claude Code enforces these lists at the OS sandbox boundary, so they apply to every subprocess a sandboxed command starts, such as `kubectl`, `terraform`, or `npm`, not only to Cla
Claude Code enforces these lists at the OS sandbox boundary, so they apply to every subprocess a sandboxed command starts, such as `kubectl`, `terraform`, or `npm`. Claude Code add
| `npm` | `{ "source": "npm", "package": "@acme-corp/claude-plugins" }` | `package` required, the npm pack
+2 −3 lines
Upstream edited 22 Sep 2026 17:24 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
network-config
±changed
+1−0
claude-codechanged
network-config
| `github.com` | Cloning GitHub-hosted [plugin marketplaces](/docs/en/plugin-marketplaces) and plugins, including the official Anthropic marketplace, over H
+1 −0 lines
Upstream edited 22 Sep 2026 17:23 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
errors
±changed
+2−1
claude-codechanged
errors
* On macOS and Linux, an entry path that contains a backslash anywhere after the leading `./`
* If you maintain the marketplace, write the entry's `source` as a plain relative path such as `./plugins/my-plugin`, and keep any symlink it crosses pointed inside the marketplace
* If you maintain the marketplace, write the entry's `source` as a plain relative path with forward slashes, such as `./plugins/my-plugin`, and keep any symlink it crosses pointed
+2 −1 lines
Upstream edited 22 Sep 2026 17:22 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
agent-sdk/typescript
±changed
+42−7
claude-codechanged
agent-sdk/typescript
readMcpResource(serverName: string, uri: string): Promise<SDKControlMcpReadResourceResponse>;
| `mcpServerStatus()` | Returns status of connected MCP servers
| `mcpServerStatus()` | Returns the status of connected MCP servers as [`McpServerStatus`](#mcpserverstatus)`[]`
| `readMcpResource(serverName, uri)` | *Alpha.* Reads one MCP Apps `ui://` resource from a connected MCP server so your application can render a tool's widget. Resolves with an
### `SDKControlMcpReadResourceResponse`
+42 −7 lines
Upstream edited 22 Sep 2026 17:07 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
keybindings
±changed
+1−1
claude-codechanged
keybindings
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input and conversation. In [fullscreen rendering](/docs/en/fullscreen#clear-the
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input and conversation
+1 −1 lines
Upstream edited 22 Sep 2026 17:07 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Ctrl+L` | Redraw or clear the screen
| `Ctrl+L` | Redraw the screen
+1 −1 lines
Upstream edited 22 Sep 2026 17:07 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
fullscreen
±changed
+3−3
claude-codechanged
fullscreen
To clear the screen and keep the conversation, press `Ctrl+L`. The earlier messages scroll up out of view, and you can scroll back with `PgUp` or the mouse wheel to read them again
`Cmd+K` does the same as `Ctrl+L` when your terminal passes it through to Claude Code. iTerm2 and Terminal.app handle `Cmd+K` themselves, and Claude Code redraws the conversation i
If the display looks garbled or partially blank, press `Ctrl+L` to redraw the screen. The redraw keeps the conversation and your input in place.
+3 −3 lines
Upstream edited 22 Sep 2026 17:07 UTC Recorded here 22 Sep 2026 17:37 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **Diff of your changes**: when the session's directory is in a git repository, a connected device's diff pane shows the diff of your uncommitted changes. The device requests the
* **Diff of your changes**: when the session's directory is in a git repository, a connected device's diff pane shows your changes. The device requests the diff over the connection
+1 −1 lines
Upstream edited 22 Sep 2026 17:05 UTC Recorded here 22 Sep 2026 17:07 UTC
claude-code
hooks
±changed
+3−2
claude-codechanged
hooks
* `PermissionRequest`
`PermissionRequest` supports `command`, `http`, `mcp_tool`, and `prompt` hooks but not `agent` hooks. If you configure an agent hook on this event, Claude Code skips it and the per
Agent-based hooks (`type: "agent"`) are like prompt-based hooks but with multi-turn tool access. Instead of a single LLM call, an agent hook spawns a subagent that can read files,
Agent-based hooks (`type: "agent"`) are like prompt-based hooks but with multi-turn tool access. Instead of a single LLM call, an agent hook spawns a subagent that can read files,
+3 −2 lines
Upstream edited 22 Sep 2026 17:04 UTC Recorded here 22 Sep 2026 17:07 UTC
claude-code
memory
±changed
+10−9
claude-codechanged
memory
* You or your organization set [`disableAllHooks`](/docs/en/settings-reference#disableallhooks) or [`allowManagedHooksOnly`](/docs/en/settings-reference#allowmanagedhooksonly), or
* You disabled the built-in `agents-md` plugin in `/plugin`
| | `CLAUDE.md`
| :------------------------------------------------------------------------------------------------------------------------------------ | :-----------------------------------------
| `/memory` and the **Memory files** list in `/context` | Listed
+10 −9 lines
Upstream edited 22 Sep 2026 16:52 UTC Recorded here 22 Sep 2026 17:07 UTC
claude-code
sub-agents
±changed
+3−1
claude-codechanged
sub-agents
The second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a ba
The second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a ba
Before v2.1.280, background subagents couldn't use `LSP`.
+3 −1 lines
Upstream edited 22 Sep 2026 16:49 UTC Recorded here 22 Sep 2026 17:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* For a tool that [background subagents drop](/docs/en/sub-agents#available-tools), such as `LSP`, remove the entry. To keep the tool, [turn fork mode off](/docs/en/sub-agents#turn
* For a tool that [background subagents drop](/docs/en/sub-agents#available-tools), such as `CronCreate`, remove the entry. To keep the tool, [turn fork mode off](/docs/en/sub-agen
+1 −1 lines
Upstream edited 22 Sep 2026 16:49 UTC Recorded here 22 Sep 2026 17:07 UTC
claude-code
changelog
±changed
+117−0
claude-codechanged
changelog
<Update label="2.1.280" description="September 22, 2026">
* Added Claude Opus 5.5 (`claude-opus-5-5`), now the default Opus model — 1M context, $4/$20 per Mtok with \$0.20/Mtok cache reads
* Added mouse support to more lists in fullscreen mode: the wheel scrolls the `/skills` list, and a skill's state options in `/plugin` can be clicked
* Added `CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH` to change the 2,048-character cap on MCP tool descriptions and server instructions for every MCP server in the session
+117 −0 lines
Upstream edited 22 Sep 2026 16:48 UTC Recorded here 22 Sep 2026 17:07 UTC
claude-code
fast-mode
±changed
+8−8
claude-codechanged
fast-mode
| Model | Input (MTok) | Output (MTok) |
| -------- | ------------ | ------------- |
| Opus 5.5 | \$8 | \$40 |
| Opus 5 | \$10 | \$50 |
| Opus 4.8 | \$10 | \$50 |
+8 −8 lines
Upstream edited 22 Sep 2026 16:44 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
keybindings
±changed
+25−3
claude-codechanged
keybindings
| `confirm:yes` | Y, Enter | Confirm action
| `confirm:no` | N, Escape | Decline action
| `confirm:yes` | Enter | Confirm action
| `confirm:no` | Escape | Decline action
+25 −3 lines
Upstream edited 22 Sep 2026 16:44 UTC Recorded here 22 Sep 2026 16:47 UTC
claude-code
fast-mode
±changed
+1−1
claude-codechanged
fast-mode
* Type `/fast` and press Tab to toggle on or off
* Run `/fast`, press Space to toggle on or off, then press Enter to confirm
+1 −1 lines
Upstream edited 22 Sep 2026 16:44 UTC Recorded here 22 Sep 2026 16:47 UTC
claude-code
google-vertex-ai
±changed
+3−3
claude-codechanged
google-vertex-ai
| Model type | Default value |
| :--------------- | :--------------------------- |
| Primary model | `claude-opus-5-5` |
| Model type | Default value |
| :- | :- |
+3 −3 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, `fable`, a full model ID such as `claude-opus-5`, or `inherit`. When you omit it, Claud
| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, `fable`, a full model ID such as `claude-opus-5-5`, or `inherit`. When you omit it, Cla
* **Full model ID**: use a full model ID such as `claude-opus-5` or `claude-sonnet-5`. Accepts the same values as the `--model` flag
* **Full model ID**: use a full model ID such as `claude-opus-5-5` or `claude-sonnet-5`. Accepts the same values as the `--model` flag
+2 −2 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
"id": "claude-opus-5",
"id": "claude-opus-5-5",
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
settings-reference
±changed
+11−11
claude-codechanged
settings-reference
* **Type**: string, one of the aliases `"fable"`, `"opus"`, or `"sonnet"`, which resolve to Claude Code's current default version of that model family, or a full model ID such as `
* **Type**: string, one of the aliases `"fable"`, `"opus"`, or `"sonnet"`, which resolve to Claude Code's current default version of that model family, or a full model ID such as `
On models that always think, such as the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` paramet
On models that always think, such as Opus 5.5 and the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thin
In a session attached to a remote worker, `/effort` applies to that session only. In a `-p` run or the Agent SDK it also applies to that session only, [unless a hold on the model's
+11 −11 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
settings-example
±changed
+7−3
claude-codechanged
settings-example
"effortLevel": "xhigh",
"modelSettings": {
"claude-sonnet-5": { "effortLevel": "xhigh" }
},
// Reason more deeply than the default high level on models without a saved level; /effort saves a level per model, and --effort sets one for a single session
+7 −3 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models and Opus 5 is also a model switch. When a safety classifier flags a request in a category
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models, Opus 5.5, and Opus 5 is also a model switch. When a safety classifier flags a request in
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
model-config
±changed
+43−45
claude-codechanged
model-config
| Anthropic API | Opus 5 | Sonnet 5 |
| [Claude Platform on AWS](/docs/en/claude-platform-on-aws) | Opus 5 | Sonnet 4.6 |
| Amazon Bedrock, Google Cloud's Agent Platform | Opus 5 | Sonnet 4.5 |
| Anthropic API | Opus 5.5 | Sonnet 5 |
| [Claude Platform on AWS](/docs/en/claude-platform-on-aws) | Opus 5.5 | Sonnet 4.6 |
+43 −45 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
google-vertex-ai
±changed
+3−3
claude-codechanged
google-vertex-ai
Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Google Cloud's Agent Platform resolves to Opus 5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resol
Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Google Cloud's Agent Platform resolves to Opus 5.5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias res
| Primary model | `claude-opus-5` |
| Primary model | `claude-opus-5-5` |
On v2.1.207 through v2.1.218, the primary model on Google Cloud's Agent Platform defaulted to Opus 4.8 and the `opus` alias resolved to Opus 4.8. Before v2.1.207, the primary model
+3 −3 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
github-actions
±changed
+1−1
claude-codechanged
github-actions
--model claude-opus-4-8
--model claude-opus-5-5
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
fast-mode
±changed
+4−3
claude-codechanged
fast-mode
Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities w
Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities w
* Fast mode pricing per MTok input/output is \$10/\$50 on Opus 5 and Opus 4.8.
* Fast mode pricing per MTok input/output is \$8/\$40 on Opus 5.5 and \$10/\$50 on Opus 5 and Opus 4.8.
Opus 5 is the fast mode default in Claude Code v2.1.219 and later. Before v2.1.219, fast mode defaulted to Opus 4.8 on v2.1.154 through v2.1.218, and to Opus 4.7 on v2.1.142 throug
+4 −3 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
errors
±changed
+5−4
claude-codechanged
errors
| `Opus 5.5's safeguards flagged this session`
* Run `claude update` and restart Claude Code. Opus 4.7 needs v2.1.111 or later. Opus 4.8 needs v2.1.154 or later. Sonnet 5 needs v2.1.197 or later. Opus 5 needs v2.1.219 or later
* Run `claude update` and restart Claude Code. Opus 4.7 needs v2.1.111 or later. Opus 4.8 needs v2.1.154 or later. Sonnet 5 needs v2.1.197 or later. Opus 5 needs v2.1.219 or later.
* If you hit this in the [Agent SDK](/docs/en/agent-sdk/overview), upgrade the SDK package instead. Opus 4.8 needs TypeScript SDK v0.3.154 or later and Python SDK v0.2.88 or later.
* If you hit this in the [Agent SDK](/docs/en/agent-sdk/overview), upgrade the SDK package instead. Opus 4.8 needs TypeScript SDK v0.3.154 or later and Python SDK v0.2.88 or later.
+5 −4 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
env-vars
±changed
+3−2
claude-codechanged
env-vars
| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and g
| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and g
| `MAX_THINKING_TOKENS` | Fixed token budget for [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking). Cla
| `MAX_THINKING_TOKENS` | Fixed token budget for [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking). Cla
| `VERTEX_REGION_CLAUDE_5_5_OPUS` | Override region for Claude Opus 5.5 when using Google Cloud's Agent Platform. Added in v2.1.280
+3 −2 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthrop
[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthrop
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
costs
±changed
+2−2
claude-codechanged
costs
Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session,
Sonnet handles most coding tasks well and costs less than Opus. Reserve Opus for complex architectural decisions or multi-step reasoning. Use `/model` to switch models mid-session,
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
+2 −2 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
communications-kit
±changed
+9−9
claude-codechanged
communications-kit
biology content falls back to Opus automatically. Opus 5 runs its own
checks, so flagged cybersecurity content switches models and flagged
biology content is refused.
biology content falls back to Opus automatically. Opus 5.5 and Opus 5 run
their own checks too: flagged content switches to an earlier Opus, except
+9 −9 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/effort [level\|auto\|status]` | Set the [effort level](/docs/en/model-config#adjust-effort-level):
| `/effort [level\|auto\|status]` | Set the [effort level](/docs/en/model-config#adjust-effort-level):
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
claude-platform-on-aws
±changed
+1−1
claude-codechanged
claude-platform-on-aws
The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROP
The default aliases `fable`, `opus`, `sonnet`, and `haiku` resolve to Claude Code's built-in defaults for Claude Platform on AWS, which can lag the newest release. Without `ANTHROP
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms
* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
amazon-bedrock
±changed
+8−8
claude-codechanged
amazon-bedrock
Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Amazon Bedrock resolves to Opus 5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resolves to Sonnet 4
Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Amazon Bedrock resolves to Opus 5.5, and without `ANTHROPIC_DEFAULT_SONNET_MODEL`, the `sonnet` alias resolves to Sonnet
| You set | The `opus` alias resolves to |
| :------------------------------------------------------------ | :---------------------------------------------------------------------------- |
| `ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'` | `us.anthropic.claude-opus-4-8`, the exact ID you pinned |
+8 −8 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this value with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-
The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this value with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k-
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this header with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k
The `context-1m-2025-08-07` beta is retired as of April 30, 2026. Passing this header with Claude Sonnet 4.5 or Sonnet 4 has no effect, and requests that exceed the standard 200k
+1 −1 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
advisor
±changed
+2−2
claude-codechanged
advisor
| Opus 5 | Fable, Opus 5 | An Opus 4.6 or Sonnet advisor is rejected, and the API refuses an Opus 4.7 or Opus 4.8 advisor |
| Opus 5.5 or Opus 5 | Fable, and Opus 5 or later | An Opus 4.6 or Sonnet advisor is rejected, and the API refuses an Opus 4.7 or Opus 4.8 advisor |
Set the advisor as `fable`, `opus`, or `sonnet`. These aliases resolve to Claude Code's built-in default version for each model family, which advances with new Claude Code releases
Set the advisor as `fable`, `opus`, or `sonnet`. These aliases resolve to Claude Code's built-in default version for each model family, which advances with new Claude Code releases
+2 −2 lines
Upstream edited 22 Sep 2026 16:28 UTC Recorded here 22 Sep 2026 16:37 UTC
claude-code
slack
±changed
+19−19
claude-codechanged
slack
| Requirement | Details |
| :------------------- | :------------------------------------------------------------------------------------------------ |
| Claude Plan | Pro, Max, Team, or Enterprise with Claude Code access (premium seats or Chat + Claude Code seats) |
| Cloud sessions | [Cloud sessions](/docs/en/claude-code-on-the-web) are enabled for your account |
| GitHub Account | Connected at [claude.ai/code](https://claude.ai/code) with at least one repository authenticated |
+19 −19 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
self-hosted-environments-reference
±changed
+102−102
claude-codechanged
self-hosted-environments-reference
| Flag | Env var | Default | Description
| :---------------------------------------- | :------------------------------------------------ | :---------------------------- | :-------------------------------------------------
| `--api-url <url>` | none | `https://api.anthropic.com` | API base URL. Override only for testing.
| `--base-dir <path>` | `SELF_HOSTED_RUNNER_BASE_DIR` | `/workspace`; none on Windows | Directory for repository checkouts and per-session
| `--capacity <n>` | none | `1` | Maximum concurrent sessions this runner handles. A
+102 −102 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
chrome
±changed
+6−6
claude-codechanged
chrome
| Error | Cause
| ------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------
| "Browser extension is not connected" | Native messaging host cannot reach the extension, or your organization's IP allowlist rejects the connection to `bridge.claudeuserco
| Extension shows "Not detected" in `/chrome` | Chrome extension is not installed or is disabled
| "No tab available" | Claude tried to act before a tab was ready
+6 −6 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/subagents
±changed
+31−31
claude-codechanged
agent-sdk/subagents
| Field | Type | Required | Description
| :---------------- | :---------------------------------------------------------- | :------- | :------------------------------------------------------------------------------------
| `description` | `string` | Yes | Natural language description of when to use this agent
| `prompt` | `string` | Yes | The agent's system prompt defining its role and behavior
| `tools` | `string[]` | No | Array of allowed tool names. If omitted, inherits every [tool available to subagents]
+31 −31 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+33−33
claude-codechanged
agent-sdk/claude-code-features
| Source | What it loads | Location
| :---------- | :--------------------------------------------------------------------------------------------------------------------- | :------------------------------------------
| Source | What it loads | Location |
| :- | :- | :- |
| `"user"` | User `settings.json`; user CLAUDE.md and `~/.claude/rules/*.md`; user skills, commands, and subagents | `~/.claude/` for `settings.json`, CLAUDE.md
+33 −33 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
vs-code
±changed
+4−4
claude-codechanged
vs-code
* VS Code 1.94.0 or higher
* VS Code 1.94.0 or later
Connect Claude to your Chrome browser to test web apps, debug with console logs, and automate browser workflows without leaving VS Code. This requires the [Claude in Chrome extensi
Connect Claude to your Chrome browser to test web apps, debug with console logs, and automate browser workflows without leaving VS Code. This requires the [Claude in Chrome extensi
Once configured, ask Claude to use the tools (e.g., "Review PR #456").
+4 −4 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
Run `/statusline` and ask it to remove or clear your status line (e.g., `/statusline delete`, `/statusline clear`, `/statusline remove it`). You can also manually delete the `statu
Run `/statusline` and ask it to remove or clear your status line (for example, `/statusline delete`, `/statusline clear`, `/statusline remove it`). You can also manually delete the
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
slack
±changed
+1−1
claude-codechanged
slack
* **Collaborative debugging**: When team discussions provide crucial context (e.g., error reproductions or user reports), Claude can use that information to inform its debugging ap
* **Collaborative debugging**: When team discussions provide crucial context (for example, error reproductions or user reports), Claude can use that information to inform its debug
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
skills
±changed
+2−2
claude-codechanged
skills
2. The subagent receives the skill content as its prompt ("Research \$ARGUMENTS thoroughly...")
2. The subagent receives the skill content as its prompt (the "Research \$ARGUMENTS thoroughly" instructions)
To raise the budget, set the [`skillListingBudgetFraction`](/docs/en/settings-reference#skilllistingbudgetfraction) setting (e.g. `0.02` = 2%) or the `SLASH_COMMAND_TOOL_CHAR_BUDGE
To raise the budget, set the [`skillListingBudgetFraction`](/docs/en/settings-reference#skilllistingbudgetfraction) setting (for example, `0.02` = 2%) or the `SLASH_COMMAND_TOOL_CH
+2 −2 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
self-hosted-environments-reference
±changed
+1−1
claude-codechanged
self-hosted-environments-reference
| `--use-anthropic-git-proxy` | `CLAUDE_RUNNER_USE_GIT_PROXY=1` | off | Clone via the [Anthropic git proxy](/docs/en/self-
| `--use-anthropic-git-proxy` | `CLAUDE_RUNNER_USE_GIT_PROXY=1` | off | Clone via the [Anthropic git proxy](/docs/en/self-
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+3−3
claude-codechanged
self-hosted-environments-deploy
Git version floors on the runner host: [`--configure-git`](#let-the-runner-configure-git) SSH commit signing requires Git 2.34 or newer, [`--use-anthropic-git-proxy`](#use-the-anth
Git version floors on the runner host: [`--configure-git`](#let-the-runner-configure-git) SSH commit signing requires Git 2.34 or later, [`--use-anthropic-git-proxy`](#use-the-anth
Commit signing requires git 2.34 or newer; the runner checks at startup and exits with an error if your git is older. This flag doesn't configure push credentials, which you still
Commit signing requires git 2.34 or later; the runner checks at startup and exits with an error if your git is older. This flag doesn't configure push credentials, which you still
The proxy requires `--capacity 1` because the proxy URL is per-session, and git 2.32 or newer because older git ignores the configuration mechanism the proxy uses to isolate sessio
+3 −3 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
quickstart
±changed
+6−6
claude-codechanged
quickstart
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+6 −6 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
plugins-reference
±changed
+1−1
claude-codechanged
plugins-reference
| LSP `Executable not found in $PATH` | Language server not installed | Install the binary (e.g., `npm install -g typescript-language-server typescript`)
| LSP `Executable not found in $PATH` | Language server not installed | Install the binary (for example, `npm install -g typescript-language-server typescript`)
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
plugin-marketplaces
±changed
+9−9
claude-codechanged
plugin-marketplaces
| Source | Type | Fields | Notes
| ------------- | ------------------------------- | ---------------------------------- | -------------------------------------------------------------------------------------------
| Relative path | `string` (e.g. `"./my-plugin"`) | none | Local directory within the marketplace repo. Must start with `./`, unless you write a [bare
| `github` | object | `repo`, `ref?`, `sha?` |
| `url` | object | `url`, `ref?`, `sha?` | Git URL source
+9 −9 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
overview
±changed
+6−6
claude-codechanged
overview
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+6 −6 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
3. Provide an image path to Claude. E.g., "Analyze this image: /path/to/your/image.png"
3. Provide an image path to Claude, for example "Analyze this image: /path/to/your/image.png"
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
chrome
±changed
+1−1
claude-codechanged
chrome
* [Claude in Chrome extension](https://chromewebstore.google.com/detail/claude/fcoeoabgfenejglbffodgkkbkcdhcgfn) version 1.0.36 or higher, available in the Chrome Web Store
* [Claude in Chrome extension](https://chromewebstore.google.com/detail/claude/fcoeoabgfenejglbffodgkkbkcdhcgfn) version 1.0.36 or later, available in the Chrome Web Store
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/user-input
±changed
+7−7
claude-codechanged
agent-sdk/user-input
| `toolName` | The name of the tool Claude wants to use (e.g., `"Bash"`, `"Write"`, `"Edit"`)
| `toolName` | The name of the tool Claude wants to use (for example, `"Bash"`, `"Write"`, `"Edit"`)
* **Approve with changes**: modify the input before execution (e.g., sanitize paths, add constraints)
* **Approve with changes**: modify the input before execution (for example, sanitize paths, add constraints)
| From the question object | Use as |
+7 −7 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/typescript
±changed
+4−4
claude-codechanged
agent-sdk/typescript
| `name` | `string` | Agent type identifier (e.g., `"Explore"`, `"general-purpose"`)
| `name` | `string` | Agent type identifier (for example, `"Explore"`, `"general-purpose"`)
Status update message (e.g., compacting).
Status update message (for example, compacting).
| `allowLocalBinding` | `boolean` | `false` | Allow processes to bind to local ports (e.g., for dev servers)
+4 −4 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/subagents
±changed
+1−1
claude-codechanged
agent-sdk/subagents
* **Use explicit prompting**: mention the subagent by name in your prompt, for example "Use the code-reviewer agent to..."
* **Use explicit prompting**: mention the subagent by name in your prompt, for example "Use the code-reviewer agent to check the authentication module"
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/quickstart
±changed
+1−1
claude-codechanged
agent-sdk/quickstart
This example uses streaming to show progress in real-time. If you don't need live output (e.g., for background jobs or CI pipelines), you can collect all messages at once. See [S
This example uses streaming to show progress in real-time. If you don't need live output (for example, for background jobs or CI pipelines), you can collect all messages at once.
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/python
±changed
+2−2
claude-codechanged
agent-sdk/python
| `stop_reason` | `str \| None` | Stop reason from the API (e.g. `end_turn`, `tool_use`) |
| `stop_reason` | `str \| None` | Stop reason from the API (for example, `end_turn`, `tool_use`) |
| `allowLocalBinding` | `bool` | `False` | Allow processes to bind to local ports (e.g., for dev servers)
| `allowLocalBinding` | `bool` | `False` | Allow processes to bind to local ports (for example, for dev servers)
+2 −2 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/custom-tools
±changed
+1−1
claude-codechanged
agent-sdk/custom-tools
| If you want to... | Do this
| What you want to do | Do this
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+1−1
claude-codechanged
agent-sdk/claude-code-features
| You want to... | Use | SDK surface
| What you want to do | Use | SDK surface
+1 −1 lines
Upstream edited 22 Sep 2026 14:15 UTC Recorded here 22 Sep 2026 14:37 UTC
claude-code
third-party-integrations
±changed
+3−3
claude-codechanged
third-party-integrations
**Claude for Teams** is self-service and includes collaboration features, admin tools, and billing management. Best for smaller teams that need to get started quickly.
**Claude for Enterprise** adds SSO and domain capture, role-based permissions, compliance API access, and managed policy settings for deploying organization-wide Claude Code config
**Claude for Teams** is self-service and includes collaboration features, admin tools, SSO, billing management, and [server-managed settings](/docs/en/server-managed-settings) for
+3 −3 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
quickstart
±changed
+1−0
claude-codechanged
quickstart
* **Courses**: Take [Claude Code 101](https://academy.claude.com/courses/claude-code-101) and other free self-paced courses on [Claude Academy](https://academy.claude.com/)
+1 −0 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
prompt-library
±changed
+1−1
claude-codechanged
prompt-library
For video walkthroughs of these patterns, see the free [Claude Code in Action](https://anthropic.skilljar.com/claude-code-in-action) course on Anthropic Academy.
For video walkthroughs of these patterns, see the free [Claude Code in Action](https://academy.claude.com/courses/claude-code-in-action) course on [Claude Academy](https://academy.
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
permissions
±changed
+2−10
claude-codechanged
permissions
Sometimes a permission prompt offers only a one-time approval, with no "don't ask again" option and no option to allow the action for the rest of the session. Claude Code offers th
When the directory you started Claude Code in is what makes the option's label too long, Claude Code shortens it in the label, replacing your home directory with `~` and then the e
* **Command or edit:** too large to show in full.
+2 −10 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
* **Yes, and use auto mode**: approve and start in [auto mode](#eliminate-prompts-with-auto-mode). When auto mode is unavailable, this option reads **Yes, auto-accept edits**. If y
* **Yes, and use auto mode**: approve and start in [auto mode](#eliminate-prompts-with-auto-mode). If auto mode isn't [available to your session](#eliminate-prompts-with-auto-mode)
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
overview
±changed
+1−0
claude-codechanged
overview
* [Claude Academy](https://academy.claude.com/): free self-paced courses, including [Claude Code 101](https://academy.claude.com/courses/claude-code-101) and [Claude Code in Action
+1 −0 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
memory
±changed
+1−1
claude-codechanged
memory
User-level rules are loaded before project rules, giving project rules higher priority.
Claude Code loads user-level rules before project rules, so a project rule appears later in Claude's context than a user rule. Neither set overrides the other: if a user rule and a
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
managed-settings
±changed
+1−0
claude-codechanged
managed-settings
| `syncClaudeAiPlugins` | Treated as `false`, so syncing of [claude.ai plugins](/docs/en/settings-reference#syncclaudeaiplugins) is off until the value is fixed.
+1 −0 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
how-claude-code-works
±changed
+3−3
claude-codechanged
how-claude-code-works
The agentic loop is powered by two components: [models](#models) that reason and [tools](#tools) that act. Claude Code serves as the **agentic harness** around Claude: it provides
The agentic loop is powered by two components: [models](#models) that reason and [tools](#tools) that act. Claude Code is the layer around the model that provides the tools and man
You can redirect Claude at any point without waiting for the turn to finish or starting over:
You can redirect Claude at any point without starting over. Do either of these:
* **Type a correction and press `Enter`** to send it without stopping the running tool. Claude reads it as soon as the current action completes and adjusts before deciding its next
+3 −3 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
headless
±changed
+2−2
claude-codechanged
headless
With `--output-format json`, the response payload includes `total_cost_usd` and a per-model cost breakdown, so scripted callers can track spend per invocation without consulting th
With `--output-format json`, the response payload includes `total_cost_usd` and a per-model cost breakdown, so scripted callers can track spend without consulting the [usage dashbo
When you enable either option, Claude Code forwards messages from [subagents at every nesting depth](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents): when a subagent s
When you enable either option, Claude Code forwards messages from [subagents at every nesting depth](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents), whether each one
+2 −2 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
features-overview
±changed
+1−1
claude-codechanged
features-overview
* **CLAUDE.md files** are additive: all levels contribute content to Claude's context simultaneously. Files from your working directory and above load at launch; subdirectories loa
* **CLAUDE.md files** are additive: all levels contribute content to Claude's context simultaneously. Files from your working directory and above load at launch; subdirectories loa
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
For a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies
For a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
* **At the end**: `/compact` replaces the conversation with a structured summary. Most startup content reloads automatically; the table below shows what happens to each mechanism.
* **At the end of the walkthrough**: you run `/compact`, which replaces the conversation with a structured summary. Most startup content reloads automatically; the table below show
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
communications-kit
±changed
+1−1
claude-codechanged
communications-kit
https://anthropic.skilljar.com/claude-code-in-action
https://academy.claude.com/courses/claude-code-in-action
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
cli-reference
±changed
+83−81
claude-codechanged
cli-reference
| Flag | Description
| :---------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------
| `--add-dir` | Add additional working directories for Claude to read and edit files. Grants file access; Claude Code [doesn't discover](/docs/e
| `--advisor <model>` | Enable the server-side [advisor tool](/docs/en/advisor) for this session with a model alias, `fable`, `opus`, or `sonnet`, or a
| `--agent` | Specify an agent for the current session (overrides the `agent` setting)
+83 −81 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
authentication
±changed
+2−2
claude-codechanged
authentication
* **Claude for Teams**: self-service plan with collaboration features, admin tools, and billing management. Best for smaller teams.
* **Claude for Enterprise**: adds SSO, domain capture, role-based permissions, compliance API, and managed policy settings for organization-wide Claude Code configurations. Best fo
* **Claude for Teams**: self-service plan with collaboration features, admin tools, SSO, billing management, and [server-managed settings](/docs/en/server-managed-settings) for org
* **Claude for Enterprise**: adds domain capture, role-based permissions, and the compliance API. Best for larger organizations with security and compliance requirements.
+2 −2 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-teams
±changed
+0−4
claude-codechanged
agent-teams
<Note>
This page describes agent teams as of v2.1.178. With `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` set, spawning a teammate no longer needs a setup step, and cleanup happens automatical
</Note>
+0 −4 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/typescript
±changed
+65−82
claude-codechanged
agent-sdk/typescript
| `parent_tool_use_id` | `string \| null` | For subagent messages, the `tool_use_id` of the spawning `Agent` tool call. `null` for main-session messages and older sessions
| `parent_tool_use_id` | `string \| null` | For subagent messages, the `tool_use_id` of the `Agent` or `Skill` tool call that started the subagent. `null` for main-session m
| `forwardSubagentText` | `boolean`
| `forwardSubagentText` | `boolean`
| `maxBudgetUsd` | `number`
+65 −82 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/subagents
±changed
+1−1
claude-codechanged
agent-sdk/subagents
| Spend | `maxBudgetUsd` in TypeScript, `max_budget_usd` in Python | No limit. Compared against `total_cost_usd`, so subagent requests count |
| Spend | `maxBudgetUsd` in TypeScript, `max_budget_usd` in Python | No limit. Counts the call's own spend, subagent requests included |
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/python
±changed
+20−38
claude-codechanged
agent-sdk/python
| `max_budget_usd` | `float \| None` | `None` | Stop the query when t
| `max_budget_usd` | `float \| None` | `None` | Stop the query when t
In [streaming input mode](/docs/en/agent-sdk/streaming-vs-single-mode), `model_usage` and `total_cost_usd` are cumulative across turns, so read the latest result rather than summin
In [streaming input mode](/docs/en/agent-sdk/streaming-vs-single-mode), `model_usage` and `total_cost_usd` are cumulative across turns, so read the latest result rather than summin
"timeout_ms": int | None, # Kill after this deadline (default 300000, max 3600000)
+20 −38 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+5−1
claude-codechanged
agent-sdk/modifying-system-prompts
The SDK splits the prompt only when it calls the Claude API directly or runs on [Claude Platform on AWS](/docs/en/claude-platform-on-aws). In every other configuration, such as A
Claude Code splits the prompt only when it calls the Claude API directly or runs on [Claude Platform on AWS](/docs/en/claude-platform-on-aws). In every other configuration, such
With the CLI's [`--system-prompt` or `--system-prompt-file` flags](/docs/en/cli-reference#system-prompt-flags), the prompt is one string, so there is no array to carry the marker.
+5 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/cost-tracking
±changed
+19−9
claude-codechanged
agent-sdk/cost-tracking
* **Session:** a series of `query()` calls linked by a session ID (using the `resume` option). Each `query()` call within a session reports its own cost independently.
* **Session:** a series of `query()` calls linked by a session ID through the `resume` option. A resumed call's results report the session's whole spend, not just that call's own.
When the `query()` call completes, the SDK emits a result message with `total_cost_usd` and cumulative `usage`, typed as [`SDKResultMessage`](/docs/en/agent-sdk/typescript#sdkr
When the `query()` call completes, the SDK emits a result message with `total_cost_usd` and cumulative `usage`, typed as [`SDKResultMessage`](/docs/en/agent-sdk/typescript#sdkr
+19 −9 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/configuration
±changed
+3−1
claude-codechanged
agent-sdk/configuration
* **`updateSettings()`**: writes an allowlisted set of keys to the project's local settings file, as in `await session.updateSettings("localSettings", { outputStyle: "Explanatory"
* **`updateSettings()`**: writes one allowlisted key to a settings file. The [`updateSettings()` reference](/docs/en/agent-sdk/typescript#updatesettings) names the key each source
* Pass `"localSettings"` to write the project's local settings file, as in `await session.updateSettings("localSettings", { outputStyle: "Explanatory" })`. The written key takes
* Pass `"userSettings"` to write `effortLevel`, the only key that source accepts. Claude Code saves it as the default effort level for the session's current model, and the runnin
+3 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
admin-setup
±changed
+1−1
claude-codechanged
admin-setup
* [Claude 101](https://anthropic.skilljar.com/claude-101) and [Claude Code in Action](https://anthropic.skilljar.com/claude-code-in-action): self-paced Anthropic Academy courses
* [Claude Code 101](https://academy.claude.com/courses/claude-code-101) and [Claude Code in Action](https://academy.claude.com/courses/claude-code-in-action): free self-paced cours
+1 −1 lines
Recorded here 22 Sep 2026 03:37 UTC
claude-code
agent-sdk/configuration
±changed
+38−38
claude-codechanged
agent-sdk/configuration
`allowedTools` (TypeScript) or `allowed_tools` (Python) pre-approves the listed tools, so calls to them run without stopping for approval. Tools outside the list stay available. Wh
`allowedTools` (TypeScript) or `allowed_tools` (Python) pre-approves the listed tools, so calls to them run without stopping for approval. Tools outside the list stay available. Wh
* **`settings`**: loads a settings file path or an inline JSON string in either language, and TypeScript also accepts a settings object. Whichever form you pass overrides user, pro
Pass `[]` to disable user, project, and local settings. For more information, see [Use Claude Code features in the SDK](/docs/en/agent-sdk/claude-code-features).
+38 −38 lines
Upstream edited 22 Sep 2026 03:07 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/configuration
±changed
+144−154
claude-codechanged
agent-sdk/configuration
<CodeGroup>
```typescript TypeScript theme={null}
import { query } from "@anthropic-ai/claude-agent-sdk";
for await (const message of query({
+144 −154 lines
Upstream edited 22 Sep 2026 03:07 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/cost-tracking
±changed
+5−5
claude-codechanged
agent-sdk/cost-tracking
| Field | Subagent activity |
| ---------------------------- | ------------------------------------------------------------------------------------------------- |
| `usage` | Excluded. Counts only the top-level agent loop, so tokens consumed inside subagents are not added |
| `total_cost_usd` | Included. Counts subagent requests alongside the top-level loop |
| `modelUsage` / `model_usage` | Included. Counts subagent requests alongside the top-level loop, broken down by model |
+5 −5 lines
Upstream edited 22 Sep 2026 03:07 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/configuration
±changed
+19−19
claude-codechanged
agent-sdk/configuration
| TypeScript | Python | Controls | Covered in
| ------------------------- | --------------------------- | ---------------------------------------- | -----------------------------------------------------------------------------
| `permissionMode` | `permission_mode` | What the agent can do without approval | [Configure permissions](/docs/en/agent-sdk/permissions)
| `allowedTools` | `allowed_tools` | Which tool calls are pre-approved | [Configure permissions](/docs/en/agent-sdk/permissions)
| `canUseTool` | `can_use_tool` | Your approval callback for tool calls | [Handle tool approval requests](/docs/en/agent-sdk/user-input#handle-tool-app
+19 −19 lines
Upstream edited 22 Sep 2026 03:07 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
vs-code
±changed
+46−7
claude-codechanged
vs-code
To review a proposed edit one change at a time, use the **Accept this change** and **Reject this change** buttons under each change in the diff. Rejecting a change reverts it i
The same actions are available at the cursor from the editor's context menu and from the Command Palette as **Claude Code: Accept Change at Cursor** and **Claude Code: Reject C
* **Command menu**: click `/` or type `/` to open the command menu. Options include attaching files, switching models, and toggling extended thinking. The Customize section provide
+46 −7 lines
Recorded here 22 Sep 2026 03:07 UTC
claude-code
terminal-config
±changed
+14−8
claude-codechanged
terminal-config
When you paste more than 800 characters or more than three lines into the prompt, Claude Code collapses the input to a placeholder such as `[Pasted text #1 +120 lines]` so the inpu
When you paste more than 800 characters or more than three lines into the prompt, Claude Code collapses the input to a placeholder such as `[Pasted text #1 +120 lines]` so the inpu
When you delete with a word or line shortcut such as `Ctrl+W` or `Ctrl+K`, or with a vim delete through an `f`/`t` motion such as `df]`, and the deleted range reaches inside a plac
Claude Code keeps the collapsed content under `~/.claude/paste-cache/`, so when you recall a prompt from [command history](/docs/en/interactive-mode#command-history) and resubmit i
+14 −8 lines
Recorded here 22 Sep 2026 03:07 UTC
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
Explore and Plan skip your CLAUDE.md files and the parent session's git status to keep research fast and inexpensive. Every other built-in and [custom subagent](#configure-subagent
Explore and Plan skip your CLAUDE.md files and the git status snapshot to keep research fast and inexpensive. Every other built-in and [custom subagent](#configure-subagents) loads
* **Git status**: a snapshot taken at the start of the parent session. Absent when the working directory isn't a Git repository or when [`includeGitInstructions`](/docs/en/settings
* **Git status**: a snapshot Claude Code reads from your repository when the subagent starts. Absent outside a Git repository or whenever the snapshot is turned off; see [`includeG
+2 −2 lines
Recorded here 22 Sep 2026 03:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.