456 pages for high.

claude-opus-4-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-5 …diction, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… claude-opus-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-6 …lf-harm, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …r. If asked to explain something, Claude's initial response can be a high-level summary explanation rather than an extremely in-depth one unless such a thing is specifically requested. Keep in mind… claude-opus-4-8 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-8 …e on the main answer; when asked to explain something, Claude gives a high-level summary unless an in-depth one is specifically requested. A prompt implying an image is present doesn't mean one is (t… claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …e on the main answer; when asked to explain something, Claude gives a high-level summary unless an in-depth one is specifically requested. If Claude suspects it's talking with a minor, it keeps the c… claude-opus-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5-5 …lf-harm, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism. Claude avoids creating content that could support or reinforce such behavior even if… claude-sonnet-3-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-3-5 …nswers questions about events prior to and after April 2024 the way a highly informed individual in April 2024 would if they were talking to someone from the above date, and can let the human know thi… claude-sonnet-3-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-3-7 …wers questions about events prior to and after October 2024 the way a highly informed individual in October 2024 would if they were talking to someone from the above date, and can let the person whom… claude-sonnet-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4 …diction, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… claude-sonnet-4-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-5 …diction, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… claude-sonnet-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-6 …lf-harm, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… claude-sonnet-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5 …lf-harm, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… claude-sonnet-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5-5 …lf-harm, disordered or unhealthy approaches to eating or exercise, or highly negative self-talk or self-criticism, and avoids creating content that would support or reinforce self-destructive behavior… develop-tests Claude Developer Platform · in the page test-and-evaluate/develop-tests …ly lower signal automated grading is better than fewer questions with high-quality human hand-graded evals. ### Example evals <AccordionGroup> <Accordion title="Task fidelity (sentiment analysis):… increase-consistency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/increase-consistency …update", "Difficulty finding basic features", "Perceived high pricing (new 'premium' tier)" ], "action_items": [ { "team": "Product", "task": "Conduct usabil… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …pt injections, ensuring your Claude-powered applications maintain the highest standards of safety and compliance. reduce-hallucinations Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-hallucinations …e them entirely. Always validate critical information, especially for high-stakes decisions. </Note> reduce-latency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-latency …laude Haiku 5.5** offers the fastest response times while maintaining high intelligence. [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) is its main control for speed and cost.… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …or follows the input caret and, on Claude Code v2.1.218 or later, the highlighted row in menus and panels such as `/config` and `/plugin`. | | [`prefersReducedMotion`](/docs/en/settings-reference#pref… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …de apps gateway](/docs/en/claude-apps-gateway) for gateway sign-ins | Highest | All | | plist / registry policy | macOS: `com.anthropic.claudecode` plist Windows: `HKLM\SOFTWARE\Policies\ClaudeCode` |… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …ssion's main model. Rows run from the lowest-ranked main model to the highest: | Main model | Accepted advisors | | - | - | | Haiku 4.5 | Fable, Opus, Sonnet, Haiku 5.5 | | Sonnet 4.6 | Fable, Opus,… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …`"medium"` | Balanced reasoning | Routine edits, standard tasks | | `"high"` | Thorough analysis | Refactors, debugging | | `"xhigh"` | Extended reasoning depth | Coding and agentic tasks on the [mode… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …ect, and local filesystem settings; only managed policy settings rank higher. The references document the full precedence order under [Settings precedence](/docs/en/agent-sdk/typescript.md#settings-pr… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …_input_tokens`: tokens used to create new cache entries (charged at a higher rate than standard input tokens). * `cache_read_input_tokens`: tokens read from existing cache entries (charged at a reduce… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …nding `PreToolUse` callback. If your callback needs more time, set a higher `timeout` on its `HookMatcher`. In TypeScript, use the `AbortSignal` from the third callback argument to handle cancellatio… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …Best for agents that take autonomous action, serve content, or handle high-volume message streams. Example workloads include an email agent that triages and responds to incoming mail, a site builder… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …ultiple sources are loaded, settings are merged with this precedence (highest to lowest): 1. Local settings (`.claude/settings.local.json`) 2. Project settings (`.claude/settings.json`) 3. User setti… Securely deploying AI agents Claude Code CLI · in the page agent-sdk/secure-deployment …curity boundary separates components with different trust levels. For high-security deployments, you can place sensitive resources (like credentials) outside the boundary containing the agent. If some… Work with sessions Claude Code CLI · in the page agent-sdk/sessions …](/docs/en/agent-sdk/agent-loop.md#handle-the-result)); resume with a higher limit. In a single-shot `query()` call the SDK raises after yielding that error result, so catch the error before resuming.… Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …/streaming-vs-single-mode.md#single-message-input), or set `maxTurns` high enough for the work to complete. ### Compact history with `/compact` The `/compact` command reduces the size of your conver… Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …on: z.string(), estimated_complexity: z.enum(["low", "medium", "high"]) }) ), risks: z.array(z.string()) }); type FeaturePlan = z.infer<typeof FeaturePlan>; // Convert to JSON Schema u… Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …nition) doesn't have this field | | `effort` | `'low' \| 'medium' \| 'high' \| 'xhigh' \| 'max' \| number` | No | Reasoning effort level for this agent | | `permissionMode` | `PermissionMode` | No | P… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …, policyOrigin? }>` | Per-source raw settings, ordered from lowest to highest precedence | #### Example The example below resolves settings for a project directory and prints the source that control… Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …| | **Token cost** | Lower: results summarized back to main context | Higher: each teammate is a separate Claude instance | Use subagents when you need quick, focused workers that report back. Use ag… Manage multiple agents with agent view Claude Code CLI · in the page agent-view …`Tab` | On an empty input, browse all subagents. Otherwise apply the highlighted suggestion | | `Ctrl+S` | Switch grouping between state and directory | | `Ctrl+T` | Pin or unpin the selected session… Claude Code on Amazon Bedrock Claude Code CLI · in the page amazon-bedrock …at is available in your account. > [!WARNING] > > Opus models have a higher per-token price than Sonnet models, so if you don't pin a primary model, you're billed at the Opus rate. To use Sonnet 4.5… Track team usage with analytics Claude Code CLI · in the page analytics …ate of Claude Code's actual impact. Only lines and PRs where there is high confidence in Claude Code's involvement are counted. The dashboard displays these summary metrics at the top: * **PRs with… Share session output as artifacts Claude Code CLI · in the page artifacts …8px scale, 6px border radius ``` Claude treats your design system as higher precedence than its own choices, and your prompt as higher precedence than both. The heading and format above are an exampl… Configure auto mode Claude Code CLI · in the page auto-mode-config …ork. * **Sensitivity slots**: name what the protective rules treat as high-risk. The slots are Sensitive data locations & audiences, Sensitive remote targets, and Protected IaC scopes. Each defaults t… Claude Code changelog Claude Code CLI · in the page changelog …rch:" instead of a symbol VoiceOver read as "telephone recorder", and highlighted prompt text, such as Ctrl+R search matches and "ultrathink", no longer has spaces inside words * Self-hosted runner: F… Channels reference Claude Code CLI · in the page channels-reference …led on main: https://ci.example.com/run/1234', meta: { severity: 'high', run_id: '1234' }, }, }) ``` The event arrives in Claude's context wrapped in a `<channel>` tag. The `source` attribute i… Checkpointing Claude Code CLI · in the page checkpointing …an still reference the details. To guide what the summary focuses on, highlight a **Summarize** option with the arrow keys and type instructions where the row reads **add context (optional)**, then pr… Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry Claude Code CLI · in the page claude-apps-gateway …d while it is on, the managed `allowedMcpServers` list comes from the highest-priority admin source that sets one. The hooks lock and `allowManagedPermissionRulesOnly`'s effect on the developer's own… Claude apps gateway configuration Claude Code CLI · in the page claude-apps-gateway-config …upstreams[].name`](#upstreams), serves for `model`. That includes the higher [fast mode](/docs/en/fast-mode.md#understand-the-cost-tradeoff) rate, so fast and standard requests meter at the same four… Claude apps gateway spend limits Claude Code CLI · in the page claude-apps-gateway-spend-limits …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.md#haiku-5-5-context-window-and-pricing). When Haiku 5.5 ser… Explore the .claude directory Claude Code CLI · in the page claude-directory …'Your personal settings overrides for this project', when: 'Highest of the user-editable settings files; CLI flags and managed settings still take precedence', description: 'Person… Claude Code on Claude Platform on AWS Claude Code CLI · in the page claude-platform-on-aws …`ENABLE_PROMPT_CACHING_1H=1`. The API bills 1-hour cache writes at a higher rate. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing) for the ra… Let Claude coordinate ongoing work with Projects Claude Code CLI · in the page claude-projects …ject settings > General**. A new project runs every thread on Opus at high effort, which draws on your plan fastest; [Choose models and let Claude manage context](#choose-models-and-let-claude-manage-… claude-tag Claude Code CLI · in the page claude-tag …"]) { display: none; } /* Center mode also styles content links at higher specificity than the single-class hl- rules: an accent color on hl-classed anchors, and a border-bottom underline on… CLI reference Claude Code CLI · in the page cli-reference …ust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`. Available levels depend on the model. `ultracode` requests `xhigh` effort with [ultracode](…