992 pages for start.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
Create the app registration that represents the Claude API audience.
Claude Developer Platform · in the page
manage-claude/wif-providers/azure
…rm that `POST /v1/oauth/token` returns a `200` with an `access_token` starting with `sk-ant-oat01-` and an `expires_in` value in seconds. If the exchange fails with the opaque `401` `authentication_er…
gcp
Claude Developer Platform · in the page
manage-claude/wif-providers/gcp
…the previous section. A successful exchange returns an `access_token` starting with `sk-ant-oat01-` and an `expires_in` value in seconds. If the exchange fails with the opaque `401` `authentication_er…
github-actions
Claude Developer Platform · in the page
manage-claude/wif-providers/github-actions
…## Verify the setup A successful exchange returns an `access_token` starting with `sk-ant-oat01-` and an `expires_in` value in seconds. A denied exchange returns an opaque `401` `authentication_erro…
kubernetes
Claude Developer Platform · in the page
manage-claude/wif-providers/kubernetes
…## Verify the setup A successful exchange returns an `access_token` starting with `sk-ant-oat01-` and an `expires_in` value in seconds. If the exchange fails with the opaque `401` `authentication_er…
okta
Claude Developer Platform · in the page
manage-claude/wif-providers/okta
…## Verify the setup A successful exchange returns an `access_token` starting with `sk-ant-oat01-` and an `expires_in` value in seconds. If the exchange fails with the opaque `401` `authentication_er…
Replace NODE_UID with the node's UID:
Claude Developer Platform · in the page
manage-claude/wif-providers/spiffe
…e first time? Deploy SPIRE Server and Agent following the [SPIRE quickstart](https://spiffe.io/docs/latest/try/), then add the [OIDC Discovery Provider](https://github.com/spiffe/spire/blob/main/suppo…
wif-reference
Claude Developer Platform · in the page
manage-claude/wif-reference
…` claim. A trailing `*` makes it a prefix match (the `sub` value must start with the characters before the `*`). Case-sensitive. | | `audience` | stri…
workload-identity-federation
Claude Developer Platform · in the page
manage-claude/workload-identity-federation
…fore each refresh. A refresh that re-reads an unrotated token, or a restarted process that re-presents a token it already exchanged, is rejected the same way. Rotating the token well within the minted…
workspaces
Claude Developer Platform · in the page
manage-claude/workspaces
…l "https://api.anthropic.com/v1/organizations/usage_report/messages?\ starting_at=2025-01-01T00:00:00Z&\ ending_at=2025-01-08T00:00:00Z&\ workspace_ids[]=wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ&\ group_by[]=w…
agent-setup
Claude Developer Platform · in the page
managed-agents/agent-setup
…ent once as a reusable resource and reference it by ID each time you [start a session](https://platform.claude.com/docs/en/managed-agents/sessions). Agents are versioned and easier to manage across ma…
budgets
Claude Developer Platform · in the page
managed-agents/budgets
…Deployments accept the same budget and apply it to each session they start; see [Budgets on deployments](https://platform.claude.com/docs/en/managed-agents/budgets#budgets-on-deployments). ## Set a…
choosing-an-environment
Claude Developer Platform · in the page
managed-agents/choosing-an-environment
….com/docs/en/managed-agents/agent-setup), not on the environment. ## Start with a cloud environment If you're not sure which to choose, or you're new to Claude Managed Agents, start with a [cloud en…
DCF Model Rubric
Claude Developer Platform · in the page
managed-agents/define-outcomes
…ften produces better results than writing criteria with no example to start from. </Accordion> Example rubric: ```markdown # DCF Model Rubric ## Revenue Projections - Uses historical revenue data f…
dreams
Claude Developer Platform · in the page
managed-agents/dreams
…eam's `outputs` (csharp, go: `Outputs`) array shortly after the dream starts `running`, once the workflow has cloned the input store; a `running` dream can briefly report an empty `outputs` (csharp, g…
environments
Claude Developer Platform · in the page
managed-agents/environments
…. You create an environment once, then reference its ID each time you start a session. Multiple sessions can share the same environment, but each session gets its own isolated sandbox (a fresh Linux c…
event-deltas
Claude Developer Platform · in the page
managed-agents/event-deltas
…5B%5D`, which also works. ### Preview events When a previewed event starts, the stream emits an `event_start` carrying the upcoming event's type and `id`: ```json { "type": "event_start", "even…
events-and-streaming
Claude Developer Platform · in the page
managed-agents/events-and-streaming
…ion sends events back to you. * **Events you send:** `user.*` events start a session and steer it as it progresses. [`system.message`](https://platform.claude.com/docs/en/managed-agents/events-and-st…
files
Claude Developer Platform · in the page
managed-agents/files
…nt directories are created automatically. * Paths should be absolute (starting with `/`). * Files the agent writes to `/mnt/session/outputs/` become available through the Files API, scoped to the sess…
github
Claude Developer Platform · in the page
managed-agents/github
…ositories are cached, so future sessions that use the same repository start faster. ## GitHub MCP and session resources First, create an agent that declares the GitHub MCP server. The agent definiti…
mcp-connector
Claude Developer Platform · in the page
managed-agents/mcp-connector
…tent from there. ## Provide authentication at session creation When starting a session, pass `vault_ids` (java: `vaultIds`; php: `vaultIDs`; csharp: `VaultIds`; go: `VaultIDs`) to provide credential…
memory
Claude Developer Platform · in the page
managed-agents/memory
…betaHeader: agent-memory-2026-07-22 --- Each Managed Agents session starts with a fresh context by default. When a session ends, any state the agent built up is gone. Memory stores let the agent car…
multiagent-orchestration
Claude Developer Platform · in the page
managed-agents/multiagent-orchestration
…plete sooner than if one agent did each piece in turn. * **How a run starts:** You describe the work in a `user.message`. From that, the agent determines whether and when to start a run, so there's n…
onboarding
Claude Developer Platform · in the page
managed-agents/onboarding
…de Console](https://platform.claude.com/workspaces/default/agent-quickstart/) provides a visual interface for creating and configuring agents. It lets you iterate on configuration interactively before…
overview
Claude Developer Platform · in the page
managed-agents/overview
…aged-agents) guide. </Note> <CardGroup cols={3}> <Card title="Quickstart" icon="play" href="https://platform.claude.com/docs/en/managed-agents/quickstart"> Create your first agent session </C…
reference
Claude Developer Platform · in the page
managed-agents/reference
…ow_run.status_running` | A workflow run is running. Sent when the run starts to execute, which can be a while after `workflow_run.created`, and again when it resumes after a pause at the budget. A res…
scheduled-deployments
Claude Developer Platform · in the page
managed-agents/scheduled-deployments
…t](https://platform.claude.com/docs/en/managed-agents/agent-setup) to start [sessions](https://platform.claude.com/docs/en/managed-agents/sessions) autonomously, so the agent can complete tasks on a p…
secure-deployment
Claude Developer Platform · in the page
managed-agents/secure-deployment
…and set up the `ant` CLI for the agent's workspace, as the [CLI quickstart](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) shows. ## Choose where the agent runs Where the ag…
secure-deployment-monitoring
Claude Developer Platform · in the page
managed-agents/secure-deployment-monitoring
…| | Scheduled runs that fail to start a session | The `deployment_run.failed` and `deployment.paused` webhooks…
spawn.sh: called once per claimed work item
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes
…or a **webhook-triggered handler** that wakes on `session.status_run_started` and starts polling. The CLI and SDK both ship pre-built workers. The `ant` CLI supports the always-on pattern only; the…
self-hosted-sandboxes-custom-tools
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-custom-tools
…rve the tools from the worker"> Connect to the same MCP server at startup, convert its tools with `async_mcp_tool()` (typescript: `mcpTools()`; go: `mcp.NewBetaTools()`), and register them alongsi…
self-hosted-sandboxes-memory
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-memory
…on self-hosted environments. </Note> ## Prepare the host Before you start the worker, create the parent directory and make it writable by the user the worker runs as: ```bash sudo mkdir -p /mnt/mem…
self-hosted-sandboxes-reference
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-reference
…ers that serve a `self_hosted` environment. For task-oriented guides, start with [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) and [Deploy self-host…
self-hosted-sandboxes-workers
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-workers
…status: beta betaHeader: managed-agents-2026-04-01 --- The [quickstart](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#quickstart) runs one `ant` CLI worker that polls c…
session-operations
Claude Developer Platform · in the page
managed-agents/session-operations
…ts, use these operations to read, update, archive, or delete it. See [Start a session](https://platform.claude.com/docs/en/managed-agents/sessions) for creating a session and sending it work. ## Sess…
session-threads
Claude Developer Platform · in the page
managed-agents/session-threads
…s/multiagent-orchestration#delegate-to-subagents), but you do see the start and end of their work, and blocking events such as tool permission requests. **Session threads** are where you examine a sp…
sessions
Claude Developer Platform · in the page
managed-agents/sessions
--- title: Start a session url: https://platform.claude.com/docs/en/managed-agents/sessions description: Create a session to run your agent and start running tasks. featureMetadata: topic: title…
skills
Claude Developer Platform · in the page
managed-agents/skills
…more skills increases the time it takes for the session's sandbox to start. Attach only the skills each agent needs for its task. </Note> Each entry in the `skills` (csharp, go: `Skills`) array uses…
tools
Claude Developer Platform · in the page
managed-agents/tools
…every tool in the set, and per-tool `configs` entries override it. To start with everything off and enable only what you need, set `default_config.enabled` to `false`: ```json { "type": "agent_tool…
tools-web-restrictions
Claude Developer Platform · in the page
managed-agents/tools-web-restrictions
…`; csharp, go: `AllowedHosts`) entry matches one exact host unless it starts with `*.`. For example, the tool entry `docs.example.com` is not within an `allowed_hosts` (java, php: `allowedHosts`; csha…
vaults
Claude Developer Platform · in the page
managed-agents/vaults
…r, not the real value: clients that validate the credential format at startup might reject it, and clients that compute a request signature from the secret (for example, AWS SigV4) produce an invalid…
webhooks
Claude Developer Platform · in the page
managed-agents/webhooks
…ing` correspond to the `session.status_idled` and `session.status_run_started` webhook events. | Event | Trigger…
workflow-runs
Claude Developer Platform · in the page
managed-agents/workflow-runs
…ic-workflows)** is the feature that lets an agent write workflows and start runs. You turn it on or off with the `workflows` (csharp, go: `Workflows`) setting in the agent's `multiagent` (csharp, go:…
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
…`tool_removal` blocks. A tool that wasn't declared in `tools` at the start can be [defined inside the `tool_addition` block](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-sys…
overview
Claude Developer Platform · in the page
models/fable-5-1/overview
…earch, and document, spreadsheet, and slide work. For most workloads, start with Claude Opus 5.5 (see [Choosing a model](https://platform.claude.com/docs/en/about-claude/models/choosing-a-model)). Use…
whats-new-fable-5-1
Claude Developer Platform · in the page
models/fable-5-1/whats-new-fable-5-1
…earch, and document, spreadsheet, and slide work. For most workloads, start with Claude Opus 5.5 (see [Choosing a model](https://platform.claude.com/docs/en/about-claude/models/choosing-a-model)). Use…
migration-guide
Claude Developer Platform · in the page
models/haiku-5-5/migration-guide
…ttings that return errors, thinking changes, and a checklist for each starting model. --- <Note> This guide covers migrating [Messages API](https://platform.claude.com/docs/en/build-with-claude/wor…
whats-new-haiku-5-5
Claude Developer Platform · in the page
models/haiku-5-5/whats-new-haiku-5-5
…| | [Responses can start with thinking blocks](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5#responses-can-begin-with-thin…
migration-guide
Claude Developer Platform · in the page
models/opus-5-5/migration-guide
…n errors, thinking blocks in every response, and a checklist for each starting model. --- <Note> This guide covers migrating [Messages API](https://platform.claude.com/docs/en/build-with-claude/wor…
whats-new-opus-5-5
Claude Developer Platform · in the page
models/opus-5-5/whats-new-opus-5-5
…has measured results for choosing a level. Because every response can start with one or more `thinking` blocks (returned with an empty `thinking` field at the default `display: "omitted"`), select con…
Models overview
Claude Developer Platform · in the page
models/overview
…meQuickChip> ## Compare models If you're unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5…