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
821pages tracked
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
69 changed this week · last read 24 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
8 Oct 2026
301 pages
+64234 −29772 lines
api
api/beta/sessions/events/stream
±changed
+82−2
apichanged
api/beta/sessions/events/stream
Emitted when a subagent is spawned as a new thread. Written to the parent thread's output stream so clients observing the session see child creation.
Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation.
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+82 −2 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/sessions/events/send
±changed
+1−1
apichanged
api/beta/sessions/events/send
"id": "sevt_011CZkZGOp0iBcp4kaQSihUmy",
"id": "sevt_011CZkZGPp1iBcp4kaQSihUm",
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/sessions/events/list
±changed
+83−3
apichanged
api/beta/sessions/events/list
Emitted when a subagent is spawned as a new thread. Written to the parent thread's output stream so clients observing the session see child creation.
Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation.
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+83 −3 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/sessions/events
±changed
+329−9
apichanged
api/beta/sessions/events
Emitted when a subagent is spawned as a new thread. Written to the parent thread's output stream so clients observing the session see child creation.
Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation.
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+329 −9 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/sessions/create
±changed
+195−4
apichanged
api/beta/sessions/create
- `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
- `BetaManagedAgentsModel = "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string`
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+195 −4 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/sessions/archive
±changed
+83−3
apichanged
api/beta/sessions/archive
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+83 −3 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/sessions
±changed
+1723−40
apichanged
api/beta/sessions
- `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
- `BetaManagedAgentsModel = "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string`
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+1723 −40 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/spend_limits/set
±changed
+108−0
apichanged
api/beta/organization/spend_limits/set
## Headers
- `"anthropic-beta": optional array of AnthropicBeta`
+108 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/spend_limits/list
±changed
+1−1
apichanged
api/beta/organization/spend_limits/list
maxItems: 6
maxItems: 100
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/spend_limits
±changed
+109−1
apichanged
api/beta/organization/spend_limits
### Headers
- `"anthropic-beta": optional array of AnthropicBeta`
+109 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation/rules/update
±changed
+1−1
apichanged
api/beta/organization/federation/rules/update
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation/rules/retrieve
±changed
+1−1
apichanged
api/beta/organization/federation/rules/retrieve
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation/rules/list
±changed
+1−1
apichanged
api/beta/organization/federation/rules/list
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation/rules/create
±changed
+1−1
apichanged
api/beta/organization/federation/rules/create
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation/rules/archive
±changed
+1−1
apichanged
api/beta/organization/federation/rules/archive
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation/rules
±changed
+6−6
apichanged
api/beta/organization/federation/rules
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
+6 −6 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/federation
±changed
+5−5
apichanged
api/beta/organization/federation
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
+5 −5 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/user_usage_report/list
±changed
+1−1
apichanged
api/beta/organization/analytics/user_usage_report/list
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/user_usage_report
±changed
+1−1
apichanged
api/beta/organization/analytics/user_usage_report
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/user_cost_report/list
±changed
+1−1
apichanged
api/beta/organization/analytics/user_cost_report/list
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/user_cost_report
±changed
+1−1
apichanged
api/beta/organization/analytics/user_cost_report
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/usage_report/list
±changed
+1−1
apichanged
api/beta/organization/analytics/usage_report/list
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/usage_report
±changed
+1−1
apichanged
api/beta/organization/analytics/usage_report
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/cost_report/list
±changed
+1−1
apichanged
api/beta/organization/analytics/cost_report/list
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics/cost_report
±changed
+1−1
apichanged
api/beta/organization/analytics/cost_report
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization/analytics
±changed
+4−4
apichanged
api/beta/organization/analytics
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this wa
RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case every bucket's `results` list is emp
+4 −4 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/organization
±changed
+118−10
apichanged
api/beta/organization
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account.
Identity that tokens minted via this rule act as. Currently always a `service_account` target.
+118 −10 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/models/retrieve
±changed
+35−3
apichanged
api/beta/models/retrieve
Whether the model supports code execution tools.
Whether code that the model runs in the code execution tool can call the request's other tools, as in programmatic tool calling and dynamic filtering for web search and web f
- `server_tools: BetaServerToolsCapability`
Whether this model supports the web search and code execution server tools. `supported` is true when the model supports at least one of the tools. A supported tool can still
+35 −3 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/models/list
±changed
+35−3
apichanged
api/beta/models/list
Whether the model supports code execution tools.
Whether code that the model runs in the code execution tool can call the request's other tools, as in programmatic tool calling and dynamic filtering for web search and web f
- `server_tools: BetaServerToolsCapability`
Whether this model supports the web search and code execution server tools. `supported` is true when the model supports at least one of the tools. A supported tool can still
+35 −3 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/models
±changed
+155−21
apichanged
api/beta/models
Whether the model supports code execution tools.
Whether code that the model runs in the code execution tool can call the request's other tools, as in programmatic tool calling and dynamic filtering for web search and web f
- `server_tools: BetaServerToolsCapability`
Whether this model supports the web search and code execution server tools. `supported` is true when the model supports at least one of the tools. A supported tool can still
+155 −21 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/messages/create
±changed
+9−1
apichanged
api/beta/messages/create
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+9 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/messages/count_tokens
±changed
+4−0
apichanged
api/beta/messages/count_tokens
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+4 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/messages/batches/results
±changed
+4−0
apichanged
api/beta/messages/batches/results
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+4 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/messages/batches/create
±changed
+4−0
apichanged
api/beta/messages/batches/create
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+4 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/messages/batches
±changed
+20−0
apichanged
api/beta/messages/batches
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
- `"claude-haiku-5-5"`
+20 −0 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/messages
±changed
+7637−1
apichanged
api/beta/messages
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+7637 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/versions/list
±changed
+81−1
apichanged
api/beta/agents/versions/list
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+81 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/versions
±changed
+81−1
apichanged
api/beta/agents/versions
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+81 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/update
±changed
+183−3
apichanged
api/beta/agents/update
- `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
- `BetaManagedAgentsModel = "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string`
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+183 −3 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/retrieve
±changed
+81−1
apichanged
api/beta/agents/retrieve
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+81 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/list
±changed
+81−1
apichanged
api/beta/agents/list
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+81 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/create
±changed
+184−4
apichanged
api/beta/agents/create
- `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
- `BetaManagedAgentsModel = "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string`
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+184 −4 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents/archive
±changed
+81−1
apichanged
api/beta/agents/archive
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+81 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta/agents
±changed
+1819−13
apichanged
api/beta/agents
- `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
- `BetaManagedAgentsModel = "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string`
- `"claude-haiku-5-5"`
Fastest model for high-volume, real-time tasks
+1819 −13 lines
Recorded here 8 Oct 2026 02:07 UTC
api
api/beta
±changed
+2109−70
apichanged
api/beta
Whether the model supports code execution tools.
Whether code that the model runs in the code execution tool can call the request's other tools, as in programmatic tool calling and dynamic filtering for web search and web f
- `server_tools: BetaServerToolsCapability`
Whether this model supports the web search and code execution server tools. `supported` is true when the model supports at least one of the tools. A supported tool can still
+2109 −70 lines
Recorded here 8 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/overview
±changed
+18−18
apichanged
agents-and-tools/tool-use/overview
| Model | Tool use system prompt tokens: auto, none
| :------------------------------------------------------------------------------------------------------------------------------------ | :----------------------------------------
| Claude Opus 5.5 | 286 tokens
| Claude Opus 5 | 286 tokens
| Claude Opus 4.8 | 290 tokens
+18 −18 lines
Recorded here 8 Oct 2026 02:07 UTC
api
about-claude/use-case-guides/legal-summarization
±changed
+36−20
apichanged
about-claude/use-case-guides/legal-summarization
Model accuracy is extremely important when summarizing legal documents. Claude Opus 5 is an excellent choice for use cases such as this where high accuracy is required. If the size
Model accuracy is extremely important when summarizing legal documents. Claude Opus 5 is an excellent choice for use cases such as this where high accuracy is required. If the size
* Input tokens: 86M (assuming 1 token per 3.5 characters)
* Output tokens per summary: 350
* Total output tokens: 350,000
+36 −20 lines
Recorded here 8 Oct 2026 02:07 UTC
api
about-claude/use-case-guides/customer-support-chat
±changed
+1−1
apichanged
about-claude/use-case-guides/customer-support-chat
For customer support chat, Claude Opus 5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning across
For customer support chat, Claude Opus 5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning across
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
api
about-claude/pricing
±changed
+64−74
apichanged
about-claude/pricing
| Model | Base input tokens | 5m cache writes |
| :------------------------------------------------------------------------------------------------------------------------------------ | :-------------------- | :-------------- |
| Claude Fable 5.1 | $10 / MTok | $12.50 / MTok |
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok |
| Claude Fable 5 | $10 / MTok | $12.50 / MTok |
+64 −74 lines
Recorded here 8 Oct 2026 02:07 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+1−1
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
13. **Chartography:** Surge AI, "Chartography," 2026. The complete released 100-question set, measured August 6 and 9, 2026 (Claude Opus 5 alone) and September 20, 2026 (Claude Opu
13. **Chartography:** Surge AI, "Chartography," 2026. The complete released 100-question set, measured August 6 and 9, 2026 (Claude Opus 5 alone) and September 20, 2026 (Claude Opu
+1 −1 lines
Recorded here 8 Oct 2026 02:07 UTC
claude-code
agent-view
±changed
+4−3
claude-codechanged
agent-view
* A session that's working: the reply joins the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, and tak
* A session that's working: `/model`, `/effort`, `/rename`, and `/usage` run right away. Other replies join the session's [message queue](/docs/en/interactive-mode#queue-messages-w
* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): r
* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): r
* **Working, paused on a permission prompt or other dialog, or attached**: the process keeps running. A running subagent, workflow, or monitor counts as working.
+4 −3 lines
Upstream edited 8 Oct 2026 02:05 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
| `content-type` | Return `text/event-stream` on streamed Anthropic Messages-format responses, and `application/vnd.amazon.eventstream`, unmodified, on Amazon Bedrock-format respon
| `content-type` | Return `text/event-stream` on streamed Anthropic Messages-format responses, and `application/vnd.amazon.eventstream`, unmodified, on Amazon Bedrock-format respon
+1 −1 lines
Upstream edited 8 Oct 2026 02:03 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
mcp
±changed
+0−4
claude-codechanged
mcp
<Warning>
If you frequently encounter output warnings with specific MCP servers you don't control, consider increasing the `MAX_MCP_OUTPUT_TOKENS` limit. You can also ask the server author
</Warning>
+0 −4 lines
Upstream edited 8 Oct 2026 02:02 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
desktop
±changed
+0−1
claude-codechanged
desktop
a-cdn.claude.ai
+0 −1 lines
Upstream edited 8 Oct 2026 02:02 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
This includes the full content of the file in the conversation.
This includes the content of the file in the conversation when it fits the [Read tool](/docs/en/tools-reference#read-tool-behavior)'s token limit, 25,000 tokens by default. A t
+1 −1 lines
Upstream edited 8 Oct 2026 02:02 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
keybindings
±changed
+45−0
claude-codechanged
keybindings
| `AbovePrompt` | The [band above the prompt](#above-prompt-actions), or a button in it, has keyboard focus |
| `AbovePromptInput` | An input field in the band above the prompt or in a mod's pane has keyboard focus |
| `AbovePromptSelect` | A select in the band above the prompt or in a mod's pane has keyboard focus |
### Above-prompt actions
+45 −0 lines
Upstream edited 8 Oct 2026 01:58 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
corporate-launcher
±changed
+1−0
claude-codechanged
corporate-launcher
* **Don't depend on how arguments are spelled.** A flag's value can arrive as its own argument, `--flag value`, or joined to the flag, `--flag=value`. Which form a flag uses can ch
+1 −0 lines
Upstream edited 8 Oct 2026 01:56 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
vs-code
±changed
+1−0
claude-codechanged
vs-code
* **Queued messages**: when you send a message while Claude is working, the extension announces "Message queued." for that message.
+1 −0 lines
Upstream edited 8 Oct 2026 01:56 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
plugins/mods/reference
±changed
+2−2
claude-codechanged
plugins/mods/reference
| `Code` | The code | ✓ | ✓ |
| [`Code`](/docs/en/plugins/mods/gallery#show-code-and-changes) | `source`, `language`, `path`, `startLine`, `format`, `wrap` | ✓ | ✓ |
| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path | ✓ | |
| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path, `columns` and `rows` up to 255, and `alt` text. | ✓ | |
+2 −2 lines
Upstream edited 8 Oct 2026 01:56 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
github-actions
±changed
+25−25
claude-codechanged
github-actions
* [Code Review](/docs/en/code-review.md): automatic review on every pull request, without writing a workflow
* [Claude Code in the cloud](/docs/en/claude-code-on-the-web.md): Claude Code sessions that run on cloud infrastructure instead of your machine
* [Claude Agent SDK](/docs/en/agent-sdk/overview.md): custom automation outside GitHub Actions. The Claude Code GitHub Action is built on the SDK
* [GitHub Enterprise Server](/docs/en/github-enterprise-server.md): Claude Code with self-hosted GitHub
* [Code Review](https://code.claude.com/docs/en/code-review.md): automatic review on every pull request, without writing a workflow
+25 −25 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
github-actions
±changed
+24−24
claude-codechanged
github-actions
* [Code Review](/docs/en/code-review): automatic review on every pull request, without writing a workflow
* [Claude Code in the cloud](/docs/en/claude-code-on-the-web): Claude Code sessions that run on cloud infrastructure instead of your machine
* [Claude Agent SDK](/docs/en/agent-sdk/overview): custom automation outside GitHub Actions. The Claude Code GitHub Action is built on the SDK
* [GitHub Enterprise Server](/docs/en/github-enterprise-server): Claude Code with self-hosted GitHub
* [Code Review](/docs/en/code-review.md): automatic review on every pull request, without writing a workflow
+24 −24 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
github-actions
±changed
+33−35
claude-codechanged
github-actions
<Note>
* When you install the GitHub App, you grant it several permissions. See [GitHub App permissions](#github-app-permissions) for the full set
* Quick setup works with the Claude API and Claude subscriptions. If you use Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, see [Use Claude Code GitHub Acti
</Note>
> [!NOTE]
+33 −35 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
setup
±changed
+1−1
claude-codechanged
setup
When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or i
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation
+1 −1 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
quickstart
±changed
+1−1
claude-codechanged
quickstart
When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found or i
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installation
+1 −1 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
overview
±changed
+1−1
claude-codechanged
overview
When the installer finishes, open a new terminal window and run `claude --version`. A working installation prints a version number. If your shell says `claude` isn't found
The install command shows no progress while it downloads Claude Code. When the installer finishes, open a new terminal window and run `claude --version`. A working installa
+1 −1 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
github-actions
±changed
+2−0
claude-codechanged
github-actions
| Administration | Read |
| Merge queues | Read |
+2 −0 lines
Upstream edited 8 Oct 2026 01:55 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
plugins/mods/api
±changed
+5−0
claude-codechanged
plugins/mods/api
A mod can refuse your `$.process.spawn` call after the command has produced output or exited, and nothing the command did is undone. The call then rejects with a message that ends
* **`$.process.spawn started, and a plugin withheld its result:`**: the refusing mod hadn't read the command's output to the end. Claude Code stops the command if it's still runnin
* **`$.process.spawn ran, and a plugin withheld its result:`**: the refusing mod had read the command's output to the end, so the command had exited
+5 −0 lines
Upstream edited 8 Oct 2026 01:49 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
WebSearch is available on the Claude API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws). On Microsoft Foundry it requires a [deployment hosted on Anthropic](https:
WebSearch is available on the Claude API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and Microsoft Foundry. On Google Cloud's Agent Platform it works with Claude
+1 −1 lines
Upstream edited 8 Oct 2026 01:47 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
feature-availability
±changed
+1−2
claude-codechanged
feature-availability
<td>✓ ([deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options))</td>
<td>✓</td>
* [Web search](/docs/en/tools-reference#websearch-tool-behavior): [deployments hosted on Anthropic](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-fo
+1 −2 lines
Upstream edited 8 Oct 2026 01:47 UTC Recorded here 8 Oct 2026 02:07 UTC
claude-code
plugins/mods/gallery
±changed
+8−0
claude-codechanged
plugins/mods/gallery
Unless Claude Code detects that the terminal draws kitty graphics protocol images with Unicode placeholders, the user sees an `Image`'s `alt` text, dimmed, in place of the picture.
* **Other terminals**: any terminal that isn't one of those two, or that doesn't answer the query.
* **tmux and screen**: a session running inside tmux or screen, in any terminal, kitty and Ghostty included.
* **Background sessions**: every [background session](/docs/en/agent-view), whatever terminal it's attached from.
+8 −0 lines
Upstream edited 8 Oct 2026 01:46 UTC Recorded here 8 Oct 2026 02:07 UTC
7 Oct 2026
209 pages
+3198 −2398 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 7 Oct 2026 23:37 UTC
claude-code
mcp
±changed
+2−4
claude-codechanged
mcp
WebSocket servers don't appear in `claude mcp list` output. Use `claude mcp get <name>` or the `/mcp` panel to check them.
* Asks HTTP servers whether they support the newer revision, and uses it with those that do. In sessions where it fetches feature flags, it also asks claude.ai connector servers, a
* Asks HTTP and stdio servers whether they support the newer revision, and uses it with those that do. In sessions where it fetches feature flags, it also asks claude.ai connector
Claude Code asks stdio servers for that revision when you set [`MCP_PROTOCOL_NEGOTIATION`](/docs/en/env-vars) to `auto`. Anthropic is also turning that on by default, for Claude Co
+2 −4 lines
Upstream edited 7 Oct 2026 23:27 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
settings-reference
±changed
+13−4
claude-codechanged
settings-reference
Choose where Claude Code stores the plan files it writes in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode). Claude Code resolves the path relative to
Choose where Claude Code stores the plan files it writes in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode). Claude Code resolves the path relative to
Claude Code stores plans in `~/.claude/plans` instead of the directory you set in cases such as these:
+13 −4 lines
Upstream edited 7 Oct 2026 23:26 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
desktop
±changed
+10−4
claude-codechanged
desktop
Administrators can distribute SSH connections to team members by adding `sshConfigs` to a [managed settings](/docs/en/managed-settings) file. Connections defined this way appear in
Administrators can distribute SSH connections to team members by setting `sshConfigs` in [managed settings](/docs/en/managed-settings). Connections defined this way appear in each
Administrators can limit Desktop's SSH sessions to an approved set of hosts by adding `sshHostAllowlist` to a [managed settings](/docs/en/managed-settings) file. When set, users ca
Administrators can limit Desktop's SSH sessions to an approved set of hosts by setting `sshHostAllowlist` in [managed settings](/docs/en/managed-settings). When set, users can only
+10 −4 lines
Upstream edited 7 Oct 2026 23:26 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/create
±changed
+1−1
claude-codechanged
plugins/mods/create
The `hooks:` line lists the events your module hooks, each with its filter in braces. The `calls:` line lists every mods API method it calls. A module that reads or sets environmen
Check the `hooks:` line for the events your module hooks, each with its filter in braces, and `calls:` for every mods API method it calls. If your module reads or sets environment
+1 −1 lines
Upstream edited 7 Oct 2026 23:24 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/admin
±changed
+1−1
claude-codechanged
plugins/mods/admin
Two lines in the output describe the mod's code:
The `hooks:` and `calls:` lines in the output describe the mod's code:
+1 −1 lines
Upstream edited 7 Oct 2026 23:24 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/cli-reference
±changed
+1−0
claude-codechanged
plugins/cli-reference
* `gatingHooks`: whether each [mod](/docs/en/plugins/mods/overview) hook that can refuse an action, such as a `tool.call` hook, has a [`.catch` handler](/docs/en/plugins/mods/eve
+1 −0 lines
Upstream edited 7 Oct 2026 23:24 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/test
±changed
+3−1
claude-codechanged
plugins/mods/test
* `returned neither { value } nor { deny }`: a stub for a mods API call returned a bare value
* `returned neither { value } nor { deny }`: a stub for a mods API call returned a bare value, which fails the test
When an `expect` fails inside a stub or hook that you passed to `on` as a plain function rather than an async generator, the test fails. The engine skips that hook, and the failure
+3 −1 lines
Upstream edited 7 Oct 2026 23:23 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/interface
±changed
+1−0
claude-codechanged
plugins/mods/interface
* **Hold the result of each `atom` call in a `const`**: if you declare `count` with `let`, validation fails with `takes a source the scan can read`
+1 −0 lines
Upstream edited 7 Oct 2026 23:23 UTC Recorded here 7 Oct 2026 23:37 UTC
claude-code
plugins/mods/api
±changed
+4−0
claude-codechanged
plugins/mods/api
<Tip>
When [MCP tool search](/docs/en/mcp#scale-with-mcp-tool-search) defers a registered tool, Claude sees its name but not its description until it searches for it. If Claude should
</Tip>
+4 −0 lines
Upstream edited 7 Oct 2026 23:13 UTC Recorded here 7 Oct 2026 23:37 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 7 Oct 2026 22:37 UTC
claude-code
statusline
±changed
+22−5
claude-codechanged
statusline
The command runs once per refresh tick and receives all visible subagent rows as a single JSON object on stdin. The input includes the [base hook fields](/docs/en/hooks#common-inpu
The per-task `model` field is the resolved model ID the task runs on. `contextWindowSize` is that model's context window in tokens, computed the same way as the main status line's
The per-task `effort` field is the reasoning effort set for that subagent, in its [definition frontmatter](/docs/en/sub-agents#supported-frontmatter-fields) or on the individual in
+22 −5 lines
Upstream edited 7 Oct 2026 22:36 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
agent-view
±changed
+7−5
claude-codechanged
agent-view
If a tool is running when you press `←`, Claude Code waits up to about ten seconds for it to finish before backgrounding, and Claude continues the response in the background sessio
The ten-second limit doesn't apply while the [foreground subagents](/docs/en/sub-agents#run-subagents-in-foreground-or-background) Claude started in the conversation are still runn
Claude Code doesn't background the session while you have unsent text in the prompt input, because the text stays in your terminal's input box and wouldn't move to the background s
+7 −5 lines
Upstream edited 7 Oct 2026 22:31 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
agent-sdk/python
±changed
+1−0
claude-codechanged
agent-sdk/python
"effort": "low" | "medium" | "high" | "xhigh" | "max" | None, # Reasoning effort for this agent
+1 −0 lines
Upstream edited 7 Oct 2026 22:28 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
routines
±changed
+1−1
claude-codechanged
routines
* **Environment variables**: provide values Claude can use during each run. They're [visible to anyone who uses the environment](/docs/en/cloud-environments#what-carries-over-f
* **Environment variables**: provide values Claude can use during each run. They're [visible to anyone who uses the environment](/docs/en/cloud-environments#what-carries-over-f
+1 −1 lines
Upstream edited 7 Oct 2026 22:14 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
Anyone who uses an environment can read its variables, so don't put a credential there, such as a collector token in `OTEL_EXPORTER_OTLP_HEADERS`. A [network secret](/docs/en/cloud
Anyone who uses an environment can read its variables, so don't put a credential there, such as a collector token in `OTEL_EXPORTER_OTLP_HEADERS`. A [network secret](/docs/en/cloud
+1 −1 lines
Upstream edited 7 Oct 2026 22:14 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
cloud-environments
±changed
+12−10
claude-codechanged
cloud-environments
Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environm
Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environm
The dialog includes the name, network access level, environment variables, and setup script. When you edit an existing cloud environment on a Pro or Max plan, the dialog also i
The dialog includes the name, network access level, environment variables, and setup script. When you edit an existing cloud environment on a Pro or Max plan, the dialog also i
Anyone who uses the environment can read the values. On Pro and Max plans, use a [network secret](#add-api-credentials) instead for a key the agent proxy can attach to a request. T
+12 −10 lines
Upstream edited 7 Oct 2026 22:14 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
claude-projects
±changed
+1−1
claude-codechanged
claude-projects
If cloud threads need to reach an internal API or a private package registry, or need a token your machine normally holds, change the environment rather than the project: see [Netw
If cloud threads need to reach an internal API or a private package registry, or need a token your machine normally holds, change the environment rather than the project: see [Netw
+1 −1 lines
Upstream edited 7 Oct 2026 22:14 UTC Recorded here 7 Oct 2026 22:37 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
* **Network secrets**: in Anthropic-hosted environments on Pro and Max plans, keys you [add to a cloud environment](/docs/en/cloud-environments#add-api-credentials) stay outside th
* **Network secrets**: in Anthropic-hosted environments on Pro and Max plans, keys you [add to a cloud environment](/docs/en/cloud-environments#add-network-secrets) stay outside th
+1 −1 lines
Upstream edited 7 Oct 2026 22:14 UTC Recorded here 7 Oct 2026 22:37 UTC
api
models/sonnet-5/overview
±changed
+1−1
apichanged
models/sonnet-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/sonnet-5-5/overview
±changed
+2−2
apichanged
models/sonnet-5-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
| [Cache read](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) | $0.20 / MTok |
| [Cache read](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) | $0.10 / MTok |
+2 −2 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/sonnet-4-6/overview
±changed
+1−1
apichanged
models/sonnet-4-6/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/sonnet-4-5/overview
±changed
+1−1
apichanged
models/sonnet-4-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/overview
±changed
+1−1
apichanged
models/overview
* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5
* **Pricing:** Base price per million tokens. Batch API requests are 50% off; prompt cache reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/opus-5/overview
±changed
+1−1
apichanged
models/opus-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/opus-5-5/overview
±changed
+1−1
apichanged
models/opus-5-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/opus-4-8/overview
±changed
+1−1
apichanged
models/opus-4-8/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/opus-4-7/overview
±changed
+1−1
apichanged
models/opus-4-7/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/opus-4-6/overview
±changed
+1−1
apichanged
models/opus-4-6/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
api
models/opus-4-5/overview
±changed
+1−1
apichanged
models/opus-4-5/overview
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 a
+1 −1 lines
Recorded here 7 Oct 2026 22:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.