618 pages for hold.

multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …} ) ``` </CodeGroup> Then create the session with the vault that holds the GitHub credential: <CodeGroup> ```bash cURL curl --fail-with-body -sS https://api.anthropic.com/v1/sessions \ -… quickstart Claude Developer Platform · in the page managed-agents/quickstart …while a managed session runs the agent loop server-side: the session holds the transcript, runs tools in a sandbox, and streams events that the front end renders. <CardGroup cols={3}> <Card title=… reference Claude Developer Platform · in the page managed-agents/reference …an include a `redacted` content block, `{"type": "redacted"}`: a placeholder for content withheld by Anthropic model policy. The block carries no other fields. Redacted blocks appear only in content t… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …| Which tools and credentials an agent holds when it reads untrusted input | No agent that reads untrusted input has a tool on `always_allow` that writes files, run… secure-deployment-risks Claude Developer Platform · in the page managed-agents/secure-deployment-risks …er enter it. For an environment variable credential, code sees a placeholder | For an MCP credential, the MCP server URL it is for. For an environment variable credential, the hosts the credential all… session-observability Claude Developer Platform · in the page managed-agents/session-observability …snapshot on the session stream and in the event history. The snapshot holds the `usage` (csharp, go: `Usage`) object, plus the session's `budget` (csharp, go: `Budget`) if the session has one. The ev… tools-web-restrictions Claude Developer Platform · in the page managed-agents/tools-web-restrictions …: `BlockedDomains`) on an entry, not both. * **List size:** Each list holds 1 to 64 domains, each 1 to 255 characters. * **No empty lists:** To apply no restriction, omit the field or send `null`. * *… vaults Claude Developer Platform · in the page managed-agents/vaults …nvironment variable name) and stored in the sandbox as an opaque placeholder. When the agent initiates an outbound request, the opaque placeholder is substituted with the real secret at egress. The ag… Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …it sets the level for Claude's reply to that turn. A `user` turn that holds only tool results doesn't count as new input: the change waits for the next `user` turn with new input. The level then holds… whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …s-updates) it does write, and remove any prompt line that tells it to hold findings for the final response. If your UI depends on narration, ask explicitly for an opening line, periodic updates, and a… migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …ing) results are higher for the same text. * A given number of tokens holds less text. * A `max_tokens` limit tuned for Claude Haiku 4.5 might cut off equivalent output. * Cost estimates made from Cla… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …est that omits `effort` now runs at `medium`. Step down where quality holds, and step up for the most demanding work. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort). 2. **R… overview Claude Developer Platform · in the page models/sonnet-5/overview …//platform.claude.com/docs/en/build-with-claude/context-windows"> Holds 1M tokens by default. How the window is counted and managed. </Card> </CardGroup> ## Reference <CardGroup cols={3}> <C… overview Claude Developer Platform · in the page release-notes/overview …https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) in beta, providing server-side context summarization for effectively infinite conversations. Available on Opus 4.6. * We've… claude-fable-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5 …self-harm that use physical discomfort, pain, or sensory shock (e.g. holding ice cubes, snapping rubber bands, cold water exposure, biting into lemons or sour candy) or that mimic the act or appearan… claude-fable-5-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5-1 …self-harm that use physical discomfort, pain, or sensory shock (e.g. holding ice cubes, snapping rubber bands, cold water exposure, biting into lemons or sour candy) or that mimic the act or appearan… claude-haiku-4-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-haiku-4-5 …ample, overdose recognition or emergency response steps — because withholding that information in an acute situation could cost a life. Claude does not write, explain, or work on malicious code (malw… claude-haiku-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-haiku-5-5 …conversation alone, and opens any file whose description suggests it holds something the reply needs. When Claude learns something lasting about the person, it saves it to memory before the turn ends… claude-opus-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-6 …fort, pain, or sensory shock as coping strategies for self-harm (e.g. holding ice cubes, snapping rubber bands, cold water exposure), as these reinforce self-destructive behaviors. In ambiguous cases,… claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …fort, pain, or sensory shock as coping strategies for self-harm (e.g. holding ice cubes, snapping rubber bands, cold water exposure), as these reinforce self-destructive behaviors. When discussing mea… claude-opus-4-8 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-8 …fort, pain, or sensory shock as coping strategies for self-harm (e.g. holding ice cubes, snapping rubber bands, cold water exposure), as these reinforce self-destructive behaviors. When discussing mea… claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …fort, pain, or sensory shock as coping strategies for self-harm (e.g. holding ice cubes, snapping rubber bands, cold water exposure), as these reinforce self-destructive behaviors. When discussing mea… claude-opus-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5-5 …self-harm that use physical discomfort, pain, or sensory shock (e.g. holding ice cubes, snapping rubber bands, cold water exposure, biting into lemons or sour candy) or that mimic the act or appearan… claude-sonnet-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-6 …fort, pain, or sensory shock as coping strategies for self-harm (e.g. holding ice cubes, snapping rubber bands, cold water exposure), as these reinforce self-destructive behaviors. In ambiguous cases,… claude-sonnet-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5 …ample, overdose recognition or emergency response steps — because withholding that information in an acute situation could cost a life. Claude does not write, explain, or work on malicious code (malw… claude-sonnet-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5-5 …self-harm that use physical discomfort, pain, or sensory shock (e.g. holding ice cubes, snapping rubber bands, cold water exposure, biting into lemons or sour candy) or that mimic the act or appearan… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …hat a screen reader such as VoiceOver or NVDA reads in order. You can hold a full conversation, approve tool permissions, and review output end to end. Screen reader mode is opt-in. If you use a scre… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …`max_budget_usd` / `maxBudgetUsd` to cap turns based on a spend threshold. Without limits, the loop runs until Claude finishes on its own, which is fine for well-scoped tasks but can run long on ope… Use Claude Code features in the SDK Claude Code CLI · in the page agent-sdk/claude-code-features …with your claude.ai login. Not loaded when `CLAUDE_CODE_OAUTH_TOKEN` holds a token from [`claude setup-token`](/docs/en/authentication#generate-a-long-lived-token), which can only make model requests… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …s the model that answered each turn. In TypeScript, the prompt stream holds the second message until the setters have run, and the second turn runs on the new model. ```typescript TypeScript theme={n… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …counting from that reset. * **The last result before each `/clear`**: holds the total for the turns since the previous reset. To total the whole call, add the last result from before each `/clear` to… Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …or non-text blocks. * `structuredContent` (optional): a JSON object holding the result as machine-readable data, returned alongside `content`. See [Return structured data](#return-structured-data).… Rewind file changes with checkpointing Claude Code CLI · in the page agent-sdk/file-checkpointing …own check, such as error detection or a validation failure; the placeholder is not defined in the example. ```python Python theme={null} import asyncio from claude_agent_sdk import ClaudeSDKClient,… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …cript#settingsource). If you set that option, include the source that holds the hooks: ```python Python theme={null} options = ClaudeAgentOptions( setting_sources=["project"], # Loads .claude/se… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …use [`ClaudeSDKClient`](/docs/en/agent-sdk/python#claudesdkclient) to hold a session open across turns. Size the container so it can hold the maximum number of concurrent sessions in memory. ### Hyb… Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …te server with a cached tool list supplies them without connecting or holding startup. The init message reports each server's status as of the moment Claude Code sends it. ## Allow MCP tools MCP to… Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …e`](/docs/en/agent-sdk/python#systempromptfile) for the platform thresholds and the Windows behavior. #### Cache the static part of a custom prompt In the TypeScript SDK, you can pass a custom promp… Configure permissions Claude Code CLI · in the page agent-sdk/permissions …n your source files still go to your `canUseTool` callback. Plan mode holds for the subagents you define too, so that handing work to one doesn't get around reviewing the plan first. > > The subagent… Plugins in the SDK Claude Code CLI · in the page agent-sdk/plugins …# MCP server definitions ``` > [!NOTE] > > The `commands/` directory holds skills as flat Markdown files. Use `skills/` for new plugins. Claude Code supports both locations. ## Multiple plugin sourc… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …discards. When set, the CLI refuses the resume if the discarded range holds entries not attributable to that turn. Requires Python Agent SDK 0.2.137 or later and Claude Code v2.1.223 or later; the CLI… Persist sessions to external storage Claude Code CLI · in the page agent-sdk/session-storage …from-the-store)**: the local copy is deleted at run end, so the store holds the only durable copy. If you don't want a fresh session to leave a transcript on local disk, set `CLAUDE_CONFIG_DIR` to a… Work with sessions Claude Code CLI · in the page agent-sdk/sessions …peScript: `continue: true` The TypeScript SDK doesn't have a session-holding client object like Python's `ClaudeSDKClient`. Instead, pass `continue: true` on each subsequent `query()` call and the SD… Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …* **Your skills**: prompt artifacts that you author, each a directory holding a `SKILL.md` file. A user-invocable skill's name joins the surface automatically, so dispatching your own `/security-check… Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …tead and the agent calls `StructuredOutput` again, so your stream can hold several calls for one query. Read the validated data from `structured_output` on the result message rather than from a `tool_… Scale to many tools with tool search Claude Code CLI · in the page agent-sdk/tool-search …conversation](/docs/en/mcp.md#tools-that-stay-deferred-below-the-threshold) even if those definitions later drop below 10%. | | `auto:N` | Same as `auto` with a custom percentage. `auto:5` activates w… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …ervers, and its CLAUDE.md and git context wait for the claim. A spare holds roughly 230 to 260 MB of memory while it waits. If your [`spawnClaudeCodeProcess`](#options) runs Claude Code on another mac… Handle approvals and user input Claude Code CLI · in the page agent-sdk/user-input …uestion"], canUseTool: async (toolName, input) => { // Placeholder that approves every call. The Detect AskUserQuestion step replaces it. return { behavior: "allow", updatedInput: inpu… Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …d updates them as teammates join, go idle, or leave. The team config holds runtime state such as session IDs and tmux pane IDs, so don't edit it by hand or pre-author it: your changes are overwritten… Manage multiple agents with agent view Claude Code CLI · in the page agent-view …terminal, such as `/install-github-app` or the `/mcp` settings list, [holds an unattended session here too](#attach-to-a-session) | | Idle | Dimmed | The session has nothing to do and is ready for you… Run agents in parallel Claude Code CLI · in the page agents …en/agent-teams.md), experimental and disabled by default * A script holds the plan instead of Claude's turn-by-turn judgment: [dynamic workflows](/docs/en/workflows.md). See [how workflows compare t…