1,305 pages for code.

agent-setup Claude Developer Platform · in the page managed-agents/agent-setup …cess to the pre-built agent toolset. The toolset lets the agent write code, read files, search the web, and more. See the [agent tools reference](https://platform.claude.com/docs/en/managed-agents/too… budgets Claude Developer Platform · in the page managed-agents/budgets …`budget` (csharp, go: `Budget`) field when you create the session: <CodeGroup> ```bash cURL curl -sS --fail-with-body https://api.anthropic.com/v1/sessions \ -H "x-api-key: $ANTHROPIC_API_KE… choosing-an-environment Claude Developer Platform · in the page managed-agents/choosing-an-environment …vironment description: Decide whether Claude Managed Agents tools and code run in an Anthropic-managed cloud environment or a self-hosted sandbox, and see what changes if you switch. featureMetadata:… DCF Model Rubric Claude Developer Platform · in the page managed-agents/define-outcomes …me)), or upload it through the Files API for reuse across sessions. <CodeGroup> ```bash cURL curl -fsSL https://api.anthropic.com/v1/files \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "anthr… dreams Claude Developer Platform · in the page managed-agents/dreams …n empty `outputs` (csharp, go: `Outputs`) array. ## Create a dream <CodeGroup> ```bash cURL curl -s https://api.anthropic.com/v1/dreams \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "anthrop… environments Claude Developer Platform · in the page managed-agents/environments …/managed-agents/choosing-an-environment). ## Create an environment <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsS https://api.anthropic.com/v1/environments \ -H "x-api-key: $ANTHRO… event-deltas Claude Developer Platform · in the page managed-agents/event-deltas …URL whenever you build the request in a shell. The examples percent-encode the brackets as `%5B%5D`, which also works. ### Preview events When a previewed event starts, the stream emits an `event_st… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …o open the stream before you send events to avoid a race condition. <CodeGroup> ```bash cURL # Open the stream before you send the first event: only later events are delivered. curl --fail-with… files Claude Developer Platform · in the page managed-agents/files …API](https://platform.claude.com/docs/en/build-with-claude/files): <CodeGroup> ```bash cURL curl --fail-with-body -sS https://api.anthropic.com/v1/files \ -H "x-api-key: $ANTHROPIC_API_KEY"… github Claude Developer Platform · in the page managed-agents/github …agent definition holds the server URL but no authentication token: <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsS https://api.anthropic.com/v1/agents \ -H "x-api-key: $ANTHROPIC_AP… mcp-connector Claude Developer Platform · in the page managed-agents/mcp-connector …CPServerName`) must match the server's `name` (csharp, go: `Name`). <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -sS --fail-with-body https://api.anthropic.com/v1/agents \ -H "x-api-ke… memory Claude Developer Platform · in the page managed-agents/memory …n a memory store request: sending both returns a `400` error. If your code sets beta headers explicitly, replace `managed-agents-2026-04-01` with `agent-memory-2026-07-22` on memory store calls rather… migration Claude Developer Platform · in the page managed-agents/migration …-claude/working-with-messages) or from the [Claude Agent SDK](https://code.claude.com/docs/en/agent-sdk/overview). ## From a Messages API agent loop If you built an agent by calling `client.messages… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …go: `Multiagent`) block to list the agents that it can delegate to: <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsS https://api.anthropic.com/v1/agents \ -H "x-api-key: $ANTHROPIC_AP… onboarding Claude Developer Platform · in the page managed-agents/onboarding …ate on agents visually in the Claude Console, then run them from your code with the API. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/managed-agents… overview Claude Developer Platform · in the page managed-agents/overview …nt where Claude can read files, run commands, browse the web, and run code securely. The harness supports built-in prompt caching, compaction, and other performance optimizations for high-quality, eff… permission-policies Claude Developer Platform · in the page managed-agents/permission-policies …g.permissionPolicy`; csharp, go: `DefaultConfig.PermissionPolicy`): <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsSL https://api.anthropic.com/v1/agents \ -H "x-api-key: $ANTHROPIC_A… quickstart Claude Developer Platform · in the page managed-agents/quickstart …**Prefer an interactive walkthrough?** The latest version of [Claude Code](https://claude.com/product/claude-code) can guide you through the setup and answer your questions: Let Claude Code set up… reference Claude Developer Platform · in the page managed-agents/reference …" (if you have an existing agent name) **Not permitted:** * "Claude Code" or "Claude Code Agent" * "Claude Cowork" or "Claude Cowork Agent" * Claude Code-branded ASCII art or visual elements that mi… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …on-aws-iam-actions#managed-policies) grants `iam:PassRole`. </Note> <CodeGroup defaultLanguage="CLI"> ```bash cURL curl --fail-with-body -sS "https://api.anthropic.com/v1/deployments?beta=true" \… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …gents-and-tools/agent-skills/claude-api-skill) that ships with Claude Code has a `managed-agents-secure` command that checks an agent, its environments, and its vaults against this guide: Let Claude… secure-deployment-monitoring Claude Developer Platform · in the page managed-agents/secure-deployment-monitoring …the agent was granted. For a review prompt, setup steps, and working code, see the [security review recipe](https://platform.claude.com/cookbook/managed-agents-cma-agent-security-review) in the Claud… secure-deployment-risks Claude Developer Platform · in the page managed-agents/secure-deployment-risks …m/docs/en/managed-agents/secure-deployment#approve-risky-actions) | | Code in the sandbox can use a credential | A script the agent was tricked into running sends the agent's key to an outside host, o… spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …-agents-2026-04-01 --- By default, Managed Agents executes tools and code inside [Anthropic-managed cloud sandboxes](https://platform.claude.com/docs/en/managed-agents/cloud-sandboxes-reference). Sel… self-hosted-sandboxes-custom-tools Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-custom-tools …ude.com/docs/en/managed-agents/tools#custom-tools) are tools your own code runs: the agent emits an `agent.custom_tool_use` event and waits for a matching `user.custom_tool_result`. Your worker can be… self-hosted-sandboxes-memory Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-memory …s-memory#prepare-the-host). * **The work item's secret:** If your own code launches the worker, [forward the work item's secret](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxe… self-hosted-sandboxes-operations Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-operations …| <CodeGroup> ```bash cURL curl -sS "https://api.anthropic.com/v1/environments/$ANTHROPIC_ENVIRONMENT_ID/work/stats" \ -H "x-… self-hosted-sandboxes-reference Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-reference …ass a `tools` (go: `ToolsFunc`) factory to customize the tool list: <CodeGroup exclude="shell, csharp, java, php, ruby"> ```python Python EnvironmentWorker(client, ..., tools=lambda env: [beta_ba… self-hosted-sandboxes-security Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-security …e key is scoped to one environment's work queue. If you run untrusted code inside your sandbox, consider provisioning a separate workspace and environment for each trust boundary. This limits each key… self-hosted-sandboxes-workers Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-workers …/self-hosted-sandboxes#run-your-first-session) from the quickstart: <CodeGroup exclude="shell:cURL, csharp, java, php, ruby"> ```bash CLI ant beta:worker poll --workdir /workspace ``` ```pyt… session-observability Claude Developer Platform · in the page managed-agents/session-observability …onsole to inspect what an agent did in a session, without writing any code. Use the session's `usage` (csharp, go: `Usage`) totals to see what that work consumed. ## Inspect a session in the Console… session-operations Claude Developer Platform · in the page managed-agents/session-operations …rrupt-a-session-with-runs-open), or wait until every run has ended. <CodeGroup> ```bash cURL curl -sS --fail-with-body "https://api.anthropic.com/v1/sessions/$SESSION_ID" \ -H "x-api-key: $AN… session-threads Claude Developer Platform · in the page managed-agents/session-threads …ist threads List all threads associated with a session as follows: <CodeGroup> ```bash cURL curl -fsS "https://api.anthropic.com/v1/sessions/$SESSION_ID/threads" \ -H "x-api-key: $ANTHROPIC_… sessions Claude Developer Platform · in the page managed-agents/sessions …) ID as a string creates the session with the latest agent version. <CodeGroup> ```bash cURL curl -fsSL https://api.anthropic.com/v1/sessions \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "an… skills Claude Developer Platform · in the page managed-agents/skills …255 characters and doesn't need to be unique within your workspace. <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -X POST "https://api.anthropic.com/v1/skills" \ -H "x-api-key: $ANTHROP… tools Claude Developer Platform · in the page managed-agents/tools …The following example enables the toolset and disables `web_fetch`: <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsSL https://api.anthropic.com/v1/agents \ -H "x-api-key: $ANTHROPIC_A… tools-web-restrictions Claude Developer Platform · in the page managed-agents/tools-web-restrictions …s. The response echoes the `configs` (csharp, go: `Configs`) array. <CodeGroup defaultLanguage="CLI"> ```bash cURL curl -fsSL https://api.anthropic.com/v1/agents \ -H "x-api-key: $ANTHROPIC_A… vaults Claude Developer Platform · in the page managed-agents/vaults …p, go: `Metadata`) so you can map it back to your own user records. <CodeGroup> ```bash cURL curl --fail-with-body -sS https://api.anthropic.com/v1/vaults \ -H "x-api-key: $ANTHROPIC_API_KEY"… webhooks Claude Developer Platform · in the page managed-agents/webhooks …NG_KEY` to the `whsec_`-prefixed secret shown at endpoint creation. <CodeGroup exclude="shell:cURL, shell:CLI"> ```python Python from flask import Flask, request import anthropic client = an… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …| | `error` with `program_error` | The workflow failed. Its code failed, or it broke a rule for workflows, other than a limit. Or one of the run's threads failed, or couldn't be created, and… 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 …/platform.claude.com/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating… overview Claude Developer Platform · in the page models/fable-5-1/overview …| * **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 20… whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …f you opt into that. Claude Mythos 5.1 doesn't run this check. Claude Code, claude.ai, [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), and the [Claude Agent SDK](… overview Claude Developer Platform · in the page models/fable-5/overview …| * **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 20… overview Claude Developer Platform · in the page models/haiku-4-5/overview …| * **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 20… migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …/platform.claude.com/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating… overview Claude Developer Platform · in the page models/haiku-5-5/overview …n the account that produced them, or in an account linked to it. For code changes, see the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide). For model IDs, pric… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …5, with a link to each feature's guide and to the migration guide for code changes. --- Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction,… overview Claude Developer Platform · in the page models/mythos-5-1/overview …| * **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 20… overview Claude Developer Platform · in the page models/mythos-5/overview …| * **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 20…