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
808pages tracked
587 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 22 Oct 2026
Claude Documentation
278pages tracked
74 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
ReadSourcePageWhatLines
22 Oct 2026
210 pages
+1010 −754 lines
api
build-with-claude/thinking
±changed
+10−10
apichanged
build-with-claude/thinking
```json
```text
```json Output
```text Output wrap
```sse Output
+10 −10 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/task-budgets
±changed
+3−3
apichanged
build-with-claude/task-budgets
```json
```text
**A budget that is too small for the task can cause refusal-like behavior.** When Claude sees a budget that is clearly insufficient for the work being asked (for example, a 20,00
**A budget that is too small for the task can cause refusal-like behavior.** When Claude receives a budget that is clearly insufficient for the work being asked (for example, a 2
<Card title="Compaction" icon="arrows-clockwise" href="https://platform.claude.com/docs/en/build-with-claude/compaction">
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/structured-outputs
±changed
+14−20
apichanged
build-with-claude/structured-outputs
```json Output
```text Output wrap
```json Output
```text Output wrap
```json Output
+14 −20 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/streaming
±changed
+10−10
apichanged
build-with-claude/streaming
```sse Example error
```text Example error
```sse Text delta
```text Text delta
```sse Input JSON delta
+10 −10 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/skills-guide
±changed
+2−2
apichanged
build-with-claude/skills-guide
2. **Rename fields** in your code: `display_title` to `display_name`, `latest_version` to `latest_version_id`, and read `source.type` instead of comparing `source` to a string.
2. **Rename fields** in your code: `display_title` to `display_name` and `latest_version` to `latest_version_id`. Read `source.type` instead of comparing `source` to a string.
After migrating, deleting a Skill through `client.skills` (csharp, go: `client.Skills`; java: `client.skills()`; php: `$client->skills`) or `client.beta.skills` (csharp, go: `cli
After migrating, deleting a Skill through `client.skills` (csharp, go: `client.Skills`; java: `client.skills()`; php: `$client->skills`) or `client.beta.skills` (csharp, go: `cli
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/search-results
±changed
+3−3
apichanged
build-with-claude/search-results
```json
```text
```json
```text wrap
```json
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/refusals-and-fallback
±changed
+4−4
apichanged
build-with-claude/refusals-and-fallback
```json
```text
```json
```text wrap
Pass `BetaRefusalFallbackMiddleware` (typescript: `betaRefusalFallbackMiddleware`; go: `betafallback.BetaRefusalFallbackMiddleware`; csharp: `BetaRefusalFallbackHandler`; java: `Be
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5
±changed
+2−2
apichanged
build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5
If long tool-calling turns still go quiet for longer than you want, your harness can prompt an update. Have it count consecutive tool-calling steps that send the user no text or pr
If long tool-calling turns still go quiet for longer than you want, your harness can prompt an update. Have it count consecutive tool-calling steps that send the user no text or pr
A token countdown that your harness adds after every tool result can cause this. So can letting users send messages while the model is partway through a multistep turn, or having y
A token countdown that your harness adds after every tool result can cause this. So can letting users send messages while the model is partway through a multistep turn, or having y
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-sonnet-5
±changed
+3−3
apichanged
build-with-claude/prompt-engineering/prompting-claude-sonnet-5
Claude Sonnet 5 might settle into a consistent default visual style on open-ended frontend and design briefs. A default house style can read well for some briefs but feel off for d
Claude Sonnet 5 might settle into a consistent default visual style on open-ended frontend and design briefs. A default house style can read well for some briefs but be a poor fit
If your code-review harness was tuned for an earlier model, you may initially see lower recall on Claude Sonnet 5. This is likely a harness effect, not a capability regression. Whe
If your code-review harness was tuned for an earlier model, you might initially see lower recall on Claude Sonnet 5. This is likely a harness effect, not a capability regression. W
If you do want the model to self-filter in a single pass, be concrete about where the bar is rather than using qualitative terms such as "important": for example, "report any bugs
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-5-5
±changed
+2−2
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-5-5
* **Biology:** The biology safeguards are the same as Claude Fable 5.1's and are new if you're coming from Claude Opus 5. Everyday health and educational questions are unaffected.
* **Cybersecurity:** Finding vulnerabilities in source code is allowed. High-risk dual-use cybersecurity activities are not. If the cybersecurity classifier gets in the way of your
* **Biology:** The biology safeguards are the same as Claude Fable 5.1's and are new if you're coming from Claude Opus 5. Everyday health and educational questions are unaffected.
* **Cybersecurity:** Finding vulnerabilities in source code is allowed. High-risk dual-use cybersecurity activities are not. If the cybersecurity classifier blocks your organizatio
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-5
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-5
* **Efficiency at lower effort:** `low` and `medium` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) produce strong quality at a fraction of the tokens and l
* **Efficiency at lower effort:** `low` and `medium` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) produce strong quality at a fraction of the tokens and l
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-4-8
±changed
+3−3
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-4-8
Claude Opus 4.8 has strong design instincts, with a consistent default house style: warm cream/off-white backgrounds (\~`#F4F1EA`), serif display type (Georgia, Fraunces, Playfair)
Claude Opus 4.8 has strong design instincts, with a consistent default house style: warm cream/off-white backgrounds (\~`#F4F1EA`), serif display type (Georgia, Fraunces, Playfair)
Claude Opus 4.8 is meaningfully better at finding bugs than prior models, and has both higher recall and precision in internal evals. However, if your code-review harness was tuned
Claude Opus 4.8 is meaningfully better at finding bugs than prior models, and has both higher recall and precision in internal evals. However, if your code-review harness was tuned
If you do want the model to self-filter in a single pass, be concrete about where the bar is rather than using qualitative terms such as "important": for example, "report any bugs
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-fable-5
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/prompting-claude-fable-5
* **Refactor existing prompts and skills.** Skills developed for prior models are often too prescriptive for Claude Fable 5 and can degrade output quality. Review and consider remo
* **Refactor existing prompts and skills.** Skills developed for prior models are often too prescriptive for Claude Fable 5 and can degrade output quality. Review and consider remo
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+2−2
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
Claude Opus 4.5 and Claude Opus 4.6 are also more responsive to the system prompt than previous models. If your prompts were designed to reduce undertriggering on tools or skills,
Claude Opus 4.5 and Claude Opus 4.6 are also more responsive to the system prompt than previous models. If your prompts were designed to reduce undertriggering on tools or skills,
4. **Starting fresh versus compacting:** When a context window is cleared, consider starting with a brand new context window rather than using compaction. Claude's latest models ar
4. **Choose between starting fresh and compacting:** When a context window is cleared, consider starting with a brand new context window rather than using compaction. Claude's late
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/prompt-caching
±changed
+4−4
apichanged
build-with-claude/prompt-caching
```json Output
```text Output wrap
The 5-minute and 1-hour cache behave the same with respect to latency. You generally see improved time-to-first-token for long documents.
The 5-minute and 1-hour caches behave the same with respect to latency. You generally see improved time-to-first-token for long documents.
```json Output
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/preserved-thinking
±changed
+8−8
apichanged
build-with-claude/preserved-thinking
```json
```text wrap
It usually ends with a sentence naming what changed, for example that the `system` prompt or the `tools` list differs from when the block was created. [Troubleshooting thinking](ht
It usually ends with a sentence naming what changed, for example that the `system` prompt or the `tools` list differs from when the block was created. For what that sentence can na
```json
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/pdf-support
±changed
+2−2
apichanged
build-with-claude/pdf-support
```json Output
```text Output
<Step title="Claude analyzes both the text and images to better understand the document.">
<Step title="Claude analyzes both the text and images.">
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/overview
±changed
+1−1
apichanged
build-with-claude/overview
| [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) | Enable Claude to call your tools programmatically from
| [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) | Allow Claude to call your tools programmatically from w
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+2−2
apichanged
build-with-claude/mid-conversation-system-messages
```json
```text
* **Declare what you know up front.** A tool you know about at the first request belongs in `tools`, with `defer_loading: true` and a later `tool_addition` reference if it shouldn'
* **Declare what you know up front.** A tool you know about at the first request belongs in `tools`, with `defer_loading: true` and a later `tool_addition` reference if you don't w
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/handling-stop-reasons
±changed
+3−3
apichanged
build-with-claude/handling-stop-reasons
```json Example response
```text Example response wrap
```json A mixed tool_use response
```text A mixed tool_use response wrap
When using [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), the API might return `pause_turn` if the server-side sampling loop reaches it
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/files
±changed
+18−18
apichanged
build-with-claude/files
```json Response
```text Response wrap
| File type | MIME type
| --------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------
| PDF | `application/pdf`
+18 −18 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/fast-mode
±changed
+3−3
apichanged
build-with-claude/fast-mode
* [Prompt caching multipliers](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching) apply on top of fast mode pricing
* [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency) multipliers apply on top of fast mode pricing
* [Prompt caching multipliers](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching) apply on top of fast mode pricing.
* [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency) multipliers apply on top of fast mode pricing.
```json Output
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/fallback-credit
±changed
+1−1
apichanged
build-with-claude/fallback-credit
You need this page only when you build the retry yourself: over raw HTTP or with custom retry logic. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/re
You need this page only when you build the retry yourself: over raw HTTP or with custom retry logic. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/re
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/embeddings
±changed
+5−5
apichanged
build-with-claude/embeddings
* Dataset size and domain specificity: size of the model training dataset and its relevance to the domain you want to embed. Larger or more domain-specific data generally produces
* Inference performance: embedding lookup speed and end-to-end latency. This is a particularly important consideration for large-scale production deployments
* Customization: options for continued training on private data, or specialization of models for very specific domains. This can improve performance on unique vocabularies
* Dataset size and domain specificity: size of the model training dataset and its relevance to the domain you want to embed. Larger or more domain-specific data generally produces
* Inference performance: embedding lookup speed and end-to-end latency. This is a particularly important consideration for large-scale production deployments.
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/effort
±changed
+1−1
apichanged
build-with-claude/effort
| `medium` | The drop-in for the average workflow where you want good results while reducing costs.
| `medium` | The setting for the average workflow where you want good results while reducing costs.
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/context-editing
±changed
+4−4
apichanged
build-with-claude/context-editing
```json Output
```text Output wrap
```json Streaming Response
```text Streaming Response wrap
```json Output
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/compaction-threshold
±changed
+2−2
apichanged
build-with-claude/compaction-threshold
```json Output
```text Output
```json Output
```text Output wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/compaction-on-demand
±changed
+1−1
apichanged
build-with-claude/compaction-on-demand
```json Response
```text Response
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+6−5
apichanged
build-with-claude/claude-platform-on-aws
2. From the **Claude Platform on AWS** service page, choose **Open Claude Console**. The AWS Console issues a JWT and redirects you to `platform.claude.com`.
2. From the **Claude Platform on AWS** service page, click **Open Claude Console**. The AWS Console issues a JWT and redirects you to `platform.claude.com`.
API keys for Claude Platform on AWS are managed in the AWS Console, not the Claude Console. Keys created in the standard Claude Console at [platform.claude.com](https://platform.
API keys for Claude Platform on AWS are managed in the AWS Console, not the Claude Console. Keys created in the standard Claude Console at [platform.claude.com](https://platform.
Claude Platform on AWS uses the standard Claude Console at [platform.claude.com](https://platform.claude.com). When you sign in from the AWS Console, an **Account managed by AWS**
+6 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+5−5
apichanged
build-with-claude/claude-on-vertex-ai
* Useful when you need data residency within a broad geography but want higher availability than a single region
* 10 percent pricing premium over global endpoints
* Only supports pay-as-you-go traffic (provisioned throughput requires regional endpoints)
* Are useful when you need data residency within a broad geography but want higher availability than a single region
* Carry a 10 percent pricing premium over global endpoints
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+3−3
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
* Required for data residency and compliance requirements
* Available for US, EU, Japan, and Asia-Pacific
* 10 percent pricing premium reflects infrastructure costs for dedicated regional capacity
* Are required for data residency and compliance requirements
* Are available for US, EU, Japan, and Asia-Pacific
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/citations
±changed
+6−6
apichanged
build-with-claude/citations
* However, the citations feature is very efficient with output tokens. Internally, the model outputs citations in a standardized format that are then parsed into cited text and doc
* However, the citations feature is very efficient with output tokens. Internally, the model outputs citations in a standardized format, and those citations are then parsed into ci
```json
```text
```json
+6 −6 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/cache-diagnostics
±changed
+1−1
apichanged
build-with-claude/cache-diagnostics
```json
```text wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/batch-processing
±changed
+4−4
apichanged
build-with-claude/batch-processing
```json Output
```text Output wrap
```jsonl .jsonl file
```text .jsonl file
```json Output
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
api/service-tiers
±changed
+1−1
apichanged
api/service-tiers
```json
```text wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
api/rate-limits
±changed
+2−2
apichanged
api/rate-limits
```json
```text
In addition to providing token and request charts, the Usage page provides two separate rate limit charts. Use these charts to see what headroom you have to grow, identify when you
In addition to providing token and request charts, the **Usage** page provides two separate rate limit charts. Use these charts to see what headroom you have to grow, identify when
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
api/overview
±changed
+2−2
apichanged
api/overview
* A [Claude Console account](https://platform.claude.com)
* A [Claude Console account](https://platform.claude.com/)
In the Console, you can view your rate limits on the [Rate limits](https://platform.claude.com/usage/limits) page and your spend limits on the [Billing](https://platform.claude.com
You can view your rate limits under [Rate limits in the Claude Console](https://platform.claude.com/usage/limits) and your spend limits on the Console's [Billing](https://platform.
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
api/errors
±changed
+3−3
apichanged
api/errors
```json JSON
```text JSON wrap
See [Streaming messages](https://platform.claude.com/docs/en/build-with-claude/streaming#get-the-final-message-without-handling-events) for more details.
See [Get the final message without handling events](https://platform.claude.com/docs/en/build-with-claude/streaming#get-the-final-message-without-handling-events) for more details.
```json
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
api/claude-code/routines-fire
±changed
+2−2
apichanged
api/claude-code/routines-fire
```json
```text
```json
```text wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
api/beta-headers
±changed
+1−1
apichanged
api/beta-headers
```json Output
```text Output
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+7−7
apichanged
agents-and-tools/tool-use/web-search-tool
* `country`: The two-letter [ISO 3166-1 alpha-2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) country code. The API rejects unsupported country codes with a 400 error.
* `timezone`: The [IANA time zone ID](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones).
* `country`: The two-letter [ISO 3166-1 alpha-2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) country code (the API rejects an unsupported code with a 400 error)
* `timezone`: The [IANA time zone ID](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones)
```json Output
+7 −7 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/web-fetch-tool
±changed
+5−5
apichanged
agents-and-tools/tool-use/web-fetch-tool
```json Output
```text Output
```json Output
```text Output wrap
```json Output
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/troubleshooting-tool-use
±changed
+1−1
apichanged
agents-and-tools/tool-use/troubleshooting-tool-use
| Claude calls with wrong parameter types | Model guessing at ambiguous schema | Add `strict: true` (if your schema is in the supported subset) or add `input_examples`
| Claude calls with wrong parameter types | Ambiguous schema | Add `strict: true` (if your schema is in the supported subset) or add `input_examples`
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/tool-search-tool
±changed
+5−5
apichanged
agents-and-tools/tool-use/tool-search-tool
```json JSON
```text JSON
```json
```text
```json
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/text-editor-tool
±changed
+13−13
apichanged
agents-and-tools/tool-use/text-editor-tool
```json
```text wrap
```json
```text wrap
```json
+13 −13 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/strict-tool-use
±changed
+2−2
apichanged
agents-and-tools/tool-use/strict-tool-use
* Functions receive correctly typed arguments every time
* Correctly typed function arguments every time
```json Output
```text Output wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/server-tools
±changed
+3−3
apichanged
agents-and-tools/tool-use/server-tools
```json
```text wrap
```json
```text wrap
```json
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/programmatic-tool-calling
±changed
+8−8
apichanged
agents-and-tools/tool-use/programmatic-tool-calling
* **Multistep workflows:** Save tokens and latency by calling tools serially or in a loop without sampling Claude in-between tool calls.
* **Multistep workflows:** Save tokens and latency by calling tools serially or in a loop without sampling Claude between tool calls.
```json
```text wrap
```json
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/parallel-tool-use
±changed
+1−1
apichanged
agents-and-tools/tool-use/parallel-tool-use
When `tool_choice` type is `auto` (the default), setting `disable_parallel_tool_use: true` means Claude calls at most one tool in each response. Claude can still answer in plain te
When the `tool_choice` type is `auto` (the default), setting `disable_parallel_tool_use: true` means Claude calls at most one tool in each response. Claude can still answer in plai
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/overview
±changed
+3−3
apichanged
agents-and-tools/tool-use/overview
[Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls) covers each step in detail, including result formatting and error signaling; [P
[Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls) covers each step in detail, including result formatting and error signaling; [P
```json JSON
```text JSON wrap
Some server tools add usage-based charges on top of tokens: see [Web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool#usage-and-pricing) a
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/memory-tool
±changed
+2−2
apichanged
agents-and-tools/tool-use/memory-tool
```json
```text wrap
```json
```text wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/handle-tool-calls
±changed
+1−1
apichanged
agents-and-tools/tool-use/handle-tool-calls
```json JSON
```text JSON wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+1−1
apichanged
agents-and-tools/tool-use/define-tools
```json JSON
```text JSON
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/computer-use-tool
±changed
+11−11
apichanged
agents-and-tools/tool-use/computer-use-tool
```json Output
```text Output wrap
```json
```text wrap
1. **Virtual display:** A virtual X11 display server (using Xvfb) that renders the desktop interface Claude sees through screenshots and controls with mouse/keyboard actions.
+11 −11 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+7−7
apichanged
agents-and-tools/tool-use/code-execution-tool
```json Output
```text Output
```json Output
```text Output wrap
```json Output
+7 −7 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/build-a-tool-using-agent
±changed
+8−8
apichanged
agents-and-tools/tool-use/build-a-tool-using-agent
This tutorial builds a calendar-management agent in five concentric rings. Each ring is a complete, runnable program that adds exactly one concept to the ring before it. By the end
This tutorial builds a calendar-management agent in five concentric rings. Each ring is a complete, runnable program that adds exactly one concept to the ring before it. By the end
## Ring 5: The Tool Runner SDK abstraction
Rings 2 through 4 wrote the same loop by hand: call the API, check `stop_reason`, run tools, append results, repeat. The Tool Runner does this for you. Define each tool as a functi
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/browser-use-tool
±changed
+3−3
apichanged
agents-and-tools/tool-use/browser-use-tool
```json Output
```text Output
```json
```text wrap
```json
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/browser-use-sdk
±changed
+5−5
apichanged
agents-and-tools/tool-use/browser-use-sdk
With a driver from a provider, such as one under [Partner integrations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk#partner-integrations), you can
With a driver from a provider, such as one under [Partner integrations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk#partner-integrations), you can
The SDK doesn't check a URL's scheme, so your driver must refuse every scheme it doesn't mean to open, such as `javascript:`, `view-source:`, `data:`, and `file:`. Most drivers n
The SDK doesn't check a URL's scheme, so your driver must refuse every scheme that you don't intend it to open, such as `javascript:`, `view-source:`, `data:`, and `file:`. Most
* URL schemes. The SDK doesn't check them, so refuse every scheme your driver doesn't mean to open.
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/bash-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/bash-tool
```json Output
```text Output wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+13−13
apichanged
agents-and-tools/tool-use/advisor-tool
The advisor tool also accepts the generic properties available on any tool definition: `cache_control`, `allowed_callers`, `defer_loading`, and `strict` (covered in [structured out
The advisor tool also accepts the generic properties available on any tool definition: `cache_control`, `allowed_callers`, `defer_loading`, and `strict` (covered in [structured out
```json
```text
```json
+13 −13 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/mcp-tunnels/quickstart
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/quickstart
* A role in the [Claude Console](https://platform.claude.com) that can manage MCP tunnels. See the [Console guide prerequisites](https://platform.claude.com/docs/en/agents-and-tool
* A role in the [Claude Console](https://platform.claude.com/) that can manage MCP tunnels. See the [Console guide prerequisites](https://platform.claude.com/docs/en/agents-and-too
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/mcp-connector
±changed
+4−4
apichanged
agents-and-tools/mcp-connector
```json
```text wrap
```json
```text wrap
```json
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/agent-skills/overview
±changed
+1−1
apichanged
agents-and-tools/agent-skills/overview
![Agent Skills architecture - showing how Skills integrate with the agent's configuration and virtual machine](https://platform.claude.com/docs/images/agent-skills-architecture.s
![Agent Skills architecture, showing how Skills integrate with the agent's configuration and virtual machine](https://platform.claude.com/docs/images/agent-skills-architecture.sv
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/agent-skills/enterprise
±changed
+1−1
apichanged
agents-and-tools/agent-skills/enterprise
| Tool invocations | Instructions directing Claude to use bash, file operations, or other tools | Medium: review what operations are performed
| Tool calls | Instructions directing Claude to use bash, file operations, or other tools | Medium: review what operations are performed
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
agents-and-tools/agent-skills/best-practices
±changed
+8−8
apichanged
agents-and-tools/agent-skills/best-practices
* Keep `SKILL.md` body under 500 lines for optimal performance
* Split content into separate files when approaching this limit
* Use the following patterns to organize instructions, code, and resources effectively
* Keep the `SKILL.md` body under 500 lines for optimal performance.
* Split content into separate files when approaching this limit.
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
about-claude/use-case-guides/ticket-routing
±changed
+5−5
apichanged
about-claude/use-case-guides/ticket-routing
Traditional ML approaches often rely on bag-of-words models or simple pattern matching. Claude excels at understanding and applying underlying rules when classes are defined by
Traditional ML approaches often rely on bag-of-words models or simple pattern matching. Claude excels at applying underlying rules when classes are defined by conditions rather
This measures the percentage of tickets resolved during the first interaction with the customer. Higher rates indicate efficient routing and well-prepared support teams. Indust
This measures the percentage of tickets resolved during the first interaction with the customer. Higher rates indicate efficient routing and well-prepared support teams. Indust
Build the deployment structure. Start by defining the function signature for wrapping the call to Claude. Extend the function you started writing earlier, which takes `ticket_conte
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
about-claude/use-case-guides/legal-summarization
±changed
+1−1
apichanged
about-claude/use-case-guides/legal-summarization
<Accordion title="You require automated extraction of key metadata">
<Accordion title="You need automated extraction of key metadata">
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
about-claude/use-case-guides/customer-support-chat
±changed
+4−4
apichanged
about-claude/use-case-guides/customer-support-chat
For customer support chat, Claude Opus 5.5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning acros
For customer support chat, Claude Opus 5.5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning acros
You will also want to include any important instructions outlining dos and don'ts for how Claude should interact with the customer. This might draw from brand guardrails or support
Also include any important instructions outlining dos and don'ts for how Claude should interact with the customer. This might draw from brand guardrails or support policies.
Test deploying this code with Streamlit using a main method. This `main()` function sets up a Streamlit-based chat interface. Streamlit is a Python framework, so this part of the w
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
about-claude/use-case-guides/content-moderation
±changed
+3−3
apichanged
about-claude/use-case-guides/content-moderation
<Accordion title="You require interpretable reasoning for your moderation decisions">
<Accordion title="You need interpretable reasoning for your moderation decisions">
<Accordion title="You require multimodal support">
<Accordion title="You need multimodal support">
One additional consideration is that instead of treating content moderation as a binary classification problem, you can instead create multiple categories to represent various risk
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
about-claude/pricing
±changed
+48−48
apichanged
about-claude/pricing
| Concept | Details
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------
| **Billing unit** | Claude Consumption Unit (CCU)
| **CCU price** | $0.01 per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price)
| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Claude API pricing](https://platform.claude.com/docs/en/about-claude/pricing#mod
+48 −48 lines
Recorded here 22 Oct 2026 02:07 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+5−4
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
Across Anthropic's measured runs, cache reads are routinely the largest single component of task cost, making caching worth more than most model-choice decisions. Anthropic priced
Anthropic priced the DeepResearch Bench II[7](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs) runs with and without caching:
* A newer model follows such instructions to the letter, producing extra tool rounds and extra writing, so the bill goes up with no gain in accuracy.
* A newer model follows such instructions to the letter, producing extra tool rounds and extra writing that you pay for with no gain in accuracy.
If you are a model or two behind, the cheapest lever is the model string. In Anthropic's measurements, each newer model solved at least as many tasks as the one before it, usually
+5 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 22 Oct 2026 01:07 UTC
claude-docs
claude-science/manage-on-devices
±changed
+1−1
claude-docschanged
claude-science/manage-on-devices
| `auto_update = false` under `[update]` | Turns off the background check for updates on Windows, on Linux, and on a Mac where Claude Science opens in a browser tab; pair with your
| `auto_update = false` under `[update]` | Turns off the background check for updates; pair with your own distribution channel. On a Mac where Claude Science opens in its own windo
+1 −1 lines
Upstream edited 22 Oct 2026 01:03 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-docs
claude-science/corporate-networks
±changed
+1−1
claude-docschanged
claude-science/corporate-networks
pip verifies package downloads against the operating system's trust store, and in this release setting `[conda] ca_bundle` alone may not be sufficient for pip, so also install the
pip verifies package downloads against the operating system's trust store, and in this release setting `[conda] ca_bundle` alone may not be sufficient for pip, so also install the
+1 −1 lines
Upstream edited 22 Oct 2026 01:03 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-docs
claude-science/changelog
±changed
+9−0
claude-docschanged
claude-science/changelog
**0.1.69**
* A new **Trouble updating?** link opens [Update Claude Science](/docs/claude-science/update-claude-science), a help page with other ways to update. It shows in **Settings > Genera
* Cloud storage in Settings now works with Google Cloud Storage HMAC keys on computers where no AWS region is set
+9 −0 lines
Upstream edited 22 Oct 2026 01:03 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+1−1
claude-codechanged
self-hosted-environments-deploy
* **Runner's own clone and fetches**: run without the variable and check Anthropic-managed git against a per-session certificate file the runner writes. That file holds the runne
* **Runner's own clone and fetches**: run without the variable and check Anthropic-managed git against a per-session certificate file the runner writes. The runner builds that fi
+1 −1 lines
Upstream edited 22 Oct 2026 00:44 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
errors
±changed
+2−0
claude-codechanged
errors
| `The model's tool call could not be parsed (retry also failed).` | [Automatic retries](#automatic-retries) |
* A response that says Claude is calling a tool but contains no tool call. Claude Code retries by asking Claude for the tool call, up to two times. If both retries fail the same wa
+2 −0 lines
Upstream edited 22 Oct 2026 00:44 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
auto-mode-config
±changed
+5−3
claude-codechanged
auto-mode-config
To see what the classifier blocked, find the tool call in the conversation. If the call appears shortened or folded into a summary line such as `Ran 3 shell commands`, press `Ctrl+
Two other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · [Data Exfiltration] · /permissions`,
To read the command or URL behind a notice such as `bash denied by auto mode · [Data Exfiltration] · /permissions`, use the **Recently denied** tab, a hook, or the conversation:
+5 −3 lines
Upstream edited 22 Oct 2026 00:44 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
permission-modes
±changed
+31−11
claude-codechanged
permission-modes
* `rm` and `rmdir` removals targeting a [critical path](#critical-paths), which no allow rule or `PreToolUse` hook `"allow"` approves
* Recognized `rm` and `rmdir` [critical-path removals](#critical-paths), which no allow rule or `PreToolUse` hook `"allow"` approves
Each path also goes through the [symlink check](/docs/en/permissions#symlinks), so a write that resolves outside that scope isn't auto-approved either. Paths outside that scope, wr
These still prompt:
+31 −11 lines
Upstream edited 22 Oct 2026 00:41 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
agent-sdk/permissions
±changed
+10−8
claude-codechanged
agent-sdk/permissions
Run [hooks](/docs/en/agent-sdk/hooks) first. A hook can deny the call outright or pass it on. A hook that returns `allow` does not skip the deny and ask rules below; those are eval
Run [hooks](/docs/en/agent-sdk/hooks) first. A hook can deny the call outright or pass it on. A hook that returns `allow` doesn't skip the deny and ask rules below, which are evalu
A `PreToolUse` hook that returns `allow` also can't approve an `rm` or `rmdir` command whose target Claude Code recognizes as a [critical path](/docs/en/permission-modes#critical-p
* In `bypassPermissions` mode, Claude Code approves everything that reaches this step except `rm` and `rmdir` removals targeting a [critical path](/docs/en/permission-modes#critica
+10 −8 lines
Upstream edited 22 Oct 2026 00:41 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+11−0
claude-codechanged
plugins/mods/troubleshoot
If the reason ends with `; the version loaded before is unloaded`, no version of the mod is running now. Once you fix the error, run [`/reload-plugins`](/docs/en/plugins/cli-refere
### `the parser stopped` or `the engine ran out of stack loading the file`
+11 −0 lines
Upstream edited 22 Oct 2026 00:39 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
plugins/loading
±changed
+5−1
claude-codechanged
plugins/loading
#### Sync timing in cloud Cowork sessions
If you turn a plugin on or off for your claude.ai account during a Cowork session that runs in the cloud, keep working in that session. If nothing has changed after a few messages,
If you enable a plugin on claude.ai while a session is running, the plugin downloads the next time you start Claude Code.
+5 −1 lines
Upstream edited 22 Oct 2026 00:39 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
plugins/components
±changed
+1−0
claude-codechanged
plugins/components
* **A `name` longer than 256 characters**: Claude Code ignores it and names the agent after its file, as it does when the field is missing
+1 −0 lines
Upstream edited 22 Oct 2026 00:39 UTC Recorded here 22 Oct 2026 01:07 UTC
claude-code
mcp
±changed
+31−4
claude-codechanged
mcp
* **In [`claude -p`](/docs/en/headless) runs and [Agent SDK](/docs/en/agent-sdk/overview) sessions**: Claude Code makes the same five attempts, with no `/mcp` panel to show them. W
* **In [`claude -p`](/docs/en/headless) runs and [Agent SDK](/docs/en/agent-sdk/overview) sessions**: Claude Code makes the same five attempts, with no `/mcp` panel to show them. I
* **After a transient error, such as a 5xx response or a timeout**: Claude Code keeps retrying an HTTP or SSE server in the background. Retries last up to about half an hour, and
* **When the server [needs you to sign in again](#authenticate-with-remote-mcp-servers)**: Claude Code stops retrying, and an Agent SDK session reports the server's status as `ne
In `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web) outside a [project](/docs/en/claude-projects#what-threads-pick-u
+31 −4 lines
Upstream edited 22 Oct 2026 00:34 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
desktop
±changed
+34−8
claude-codechanged
desktop
The Code tab is built around panes you can arrange in any layout: chat, diff, browser, terminal, file, plan, tasks, and subagent, along with the [iOS Simulator](/docs/en/desktop-io
The Code tab is built around panes you can arrange in any layout: chat, diff, browser, terminal, file, plan, tasks, and subagent, along with the [iOS Simulator](/docs/en/desktop-io
To open another pane, click its icon button in the session's title bar. Hover to see each button's name, such as **Terminal**, **Changes** for the diff view, **Browser**, and **Fil
+34 −8 lines
Upstream edited 22 Oct 2026 00:34 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
code-review-pull-requests
±changed
+1−1
claude-codechanged
code-review-pull-requests
| `@claude review stop` | Ends the PR's subscription to push-triggered reviews, without starting a review or canceling one that's already queued or running. Claude replies with a c
| `@claude review stop` | Ends the PR's subscription to push-triggered reviews, without starting a review or canceling one that's already running. Claude replies with a comment ins
+1 −1 lines
Upstream edited 22 Oct 2026 00:34 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
errors
±changed
+16−1
claude-codechanged
errors
| `Your organization's managed settings need your approval, which couldn't be asked for here.` | [Configuration warnings](#managed-settings-need-your-approval) |
* If you use a custom [`ANTHROPIC_BASE_URL`](/docs/en/env-vars) and the error starts with `Prompt is too long · automatic compaction failed`, [set the model's context window](/do
* On v2.1.305, with many MCP tools and a direct connection to the Anthropic API, this error can hide an unrelated 400 or 422 error from the API. [Update Claude Code](/docs/en/setup
You ran [`claude import`](/docs/en/cli-reference#cli-commands) while Claude Code couldn't parse `~/.claude.json`, the file where it stores your login and per-project state. The sub
You ran [`claude import`](/docs/en/cli-reference#cli-commands) while Claude Code couldn't parse `~/.claude.json`, the file where it stores your account details and per-project stat
+16 −1 lines
Upstream edited 22 Oct 2026 00:33 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway-spend-limits
±changed
+6−0
claude-codechanged
claude-apps-gateway-spend-limits
#### Long-prompt rates
The list price for [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) has a [higher rate for prompts over a token threshold](/docs/en/model-config#ha
+6 −0 lines
Upstream edited 22 Oct 2026 00:33 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
authentication
±changed
+13−1
claude-codechanged
authentication
After [installing Claude Code](/docs/en/setup#install-claude-code), run `claude` in your terminal. On first launch, Claude Code opens a browser window for you to log in. If you've
After [installing Claude Code](/docs/en/setup#install-claude-code), run `claude` in your terminal. Claude Code opens a browser window for you to log in on first launch, except in c
* **API key**: you've set the `ANTHROPIC_API_KEY` environment variable and you approve the key when Claude Code asks whether to use it
* **Earlier sign-in**: you ran [`claude auth login`](/docs/en/cli-reference#cli-commands) in your shell before your first session, or you rebuilt a dev container that keeps your cr
+13 −1 lines
Upstream edited 22 Oct 2026 00:33 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `has_hooks`: whether the plugin contributes hooks
* `has_hooks`: whether the plugin contributes hooks, through [hook configuration](/docs/en/plugins/components#hooks) or as a [mod](/docs/en/plugins/mods/overview#how-a-mod-works)
+1 −1 lines
Upstream edited 22 Oct 2026 00:33 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
devcontainer
±changed
+6−2
claude-codechanged
devcontainer
By default, the container's home directory is discarded on rebuild, so engineers must sign in again each time. Claude Code stores its authentication token, user settings, and sessi
By default, the container's home directory is discarded on rebuild, so engineers must sign in again each time. Claude Code stores its authentication token, user settings, and sessi
The following example mounts the volume and sets `CLAUDE_CONFIG_DIR` for a container whose `remoteUser` is `node`:
To keep the directory and the file, mount a named volume at `~/.claude` and set [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) to the same path so Claude Code writes `.claude.json` insid
+6 −2 lines
Upstream edited 22 Oct 2026 00:33 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
settings-reference
±changed
+38−10
claude-codechanged
settings-reference
| [`sandbox.allowNestedUserNamespaces`](#sandbox-allownestedusernamespaces) | Let [sandboxed](/docs/en/sandboxing#chromium-or-rootless-podman-fails-inside-the-sandbox-on-linux) com
* **Type**: object with `enabled`, `failIfUnavailable`, `autoAllowBashIfSandboxed`, `excludedCommands`, `allowUnsandboxedCommands`, `enableWeakerNestedSandbox`, `enableWeakerNetwor
* **Type**: object with `enabled`, `failIfUnavailable`, `autoAllowBashIfSandboxed`, `excludedCommands`, `allowUnsandboxedCommands`, `enableWeakerNestedSandbox`, `enableWeakerNetwor
### `sandbox.allowNestedUserNamespaces`
+38 −10 lines
Upstream edited 22 Oct 2026 00:17 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
server-managed-settings
±changed
+4−1
claude-codechanged
server-managed-settings
* **Sandbox network and isolation settings**: [sandbox](/docs/en/sandboxing) settings that let the sandbox proxy read, reroute, or authenticate traffic, or that weaken the sandbox'
* **Sandbox network and isolation settings**: [sandbox](/docs/en/sandboxing) settings that let the sandbox proxy read, reroute, or authenticate traffic, or that weaken the sandbox'
* **A `claude plugin` command that prints to a terminal but can't read from the keyboard**: when Claude Code doesn't wait for the settings fetch at startup, the command doesn't app
The command can't read from the keyboard when you pipe or redirect its input and, on macOS and Linux, it also can't open `/dev/tty`. If you pipe or redirect its output too, the r
+4 −1 lines
Upstream edited 22 Oct 2026 00:17 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
sandboxing
±changed
+36−8
claude-codechanged
sandboxing
* When managed settings configure `sandbox.filesystem` at all, or list any `sandbox.credentials.files` entry with `"mode": "deny"`, only managed settings can set the key. This keep
* When managed settings configure `sandbox.filesystem` at all, or list any `sandbox.credentials.files` entry with `"mode": "deny"`, only managed settings can set the key. This keep
There is no way to exempt one of these paths: an `allowWrite` entry or an `Edit` allow rule that covers the path doesn't lift the protection. The only way to turn the protection of
If you add an `allowWrite` entry or an `Edit` allow rule that covers one of these paths, the protection still applies. To turn the protection off, set [`filesystem.disabled`](#disa
+36 −8 lines
Upstream edited 22 Oct 2026 00:17 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
skills
±changed
+2−2
claude-codechanged
skills
* **Skill folder as a plugin**: add a `.claude-plugin/plugin.json` to a skill folder and it loads as a [plugin](/docs/en/plugins/loading#plugins-shared-through-a-repository) named
* **Skill folder as a plugin**: add a `.claude-plugin/plugin.json` to a personal or project skill folder and Claude Code can load it as a [plugin](/docs/en/plugins/loading#plugins-
| `hooks` | No | Hooks that Claude Code registers when the skill is invoked and keeps running for the rest of the session. See [Hooks in skills and agents](/docs/en/hooks#hooks-in-
| `hooks` | No | Hooks that Claude Code registers when the skill is invoked and keeps running for the rest of the session. See [Hooks in skills and agents](/docs/en/hooks#hooks-in-
+2 −2 lines
Upstream edited 22 Oct 2026 00:14 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
hooks-guide
±changed
+1−0
claude-codechanged
hooks-guide
* For a hook in a skill's frontmatter, invoke the skill or ask Claude to, then run `/hooks` again. `/hooks` doesn't list hooks from a skill that hasn't been invoked in the session.
+1 −0 lines
Upstream edited 22 Oct 2026 00:14 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
hooks
±changed
+16−0
claude-codechanged
hooks
#### Limits on skill hooks
When a skill's frontmatter hooks don't fire after you or Claude invoke the skill, run [`/hooks`](#the-%2Fhooks-menu) in that session. If it lists them, see [Hook not firing](/docs/
+16 −0 lines
Upstream edited 22 Oct 2026 00:14 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
debug-your-config
±changed
+1−0
claude-codechanged
debug-your-config
* The hook is in a skill's frontmatter, and neither you nor Claude has invoked the skill yet in this session. Invoke it or ask Claude to, then run `/hooks` again. If the hook still
+1 −0 lines
Upstream edited 22 Oct 2026 00:14 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+11−1
claude-codechanged
self-hosted-environments-deploy
* **A session's branch no longer exists on the remote**: for a git source the session only reads from, the runner skips that source and continues on the remaining ones. For the sou
* **A session fails with `no longer exists on the remote` or `couldn't find remote ref`**: the runner reads git's `couldn't find remote ref` as a deleted branch. The branch can sti
* **The branch is gone**: typically because it was merged and auto-deleted. Restore it, as the message asks.
* **The branch exists and you don't administer the runner**: send the runner's administrator the full message and tell them the branch exists.
+11 −1 lines
Upstream edited 22 Oct 2026 00:13 UTC Recorded here 22 Oct 2026 00:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+3−1
claude-codechanged
self-hosted-environments-configuration
If git's `couldn't find remote ref` appears in roughly the last 4 KB of the hook's stderr, the runner reports a deleted branch instead. The session's error message then says the
When a person starts their own session, Claude Code also downloads the [skills enabled for their claude.ai account](/docs/en/skills#skills-in-cowork-and-cloud-sessions) into that s
When a person starts their own session, Claude Code downloads the [skills enabled for their claude.ai account](/docs/en/skills#skills-in-cowork-and-cloud-sessions) into that sessio
+3 −1 lines
Upstream edited 22 Oct 2026 00:13 UTC Recorded here 22 Oct 2026 00:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.