# Claude Code with the Automation Platform

> Run Claude Code with the Automation Platform. Strong at code review, deep bug investigation, large feature planning, and frontend or UI work.

- 网址：https://funcoding.ai/agents/warp/platform/harnesses/claude-code/
- 来源：Warp 官方文档原文（英文），MIT 许可，同步于 2026-10-11
- 官方原文：https://docs.warp.dev/platform/harnesses/claude-code/

---
Claude Code is Anthropic's agentic coding tool. Running it with the Automation Platform puts Claude Code inside a Warp-managed environment and connects it to the rest of the Automation Platform — including triggers, environments, secrets, observability, and governance — while still behaving like the Claude Code your team already uses.

<div class="callout callout-note">

This page covers Claude Code as a **cloud** harness, dispatched and orchestrated by the Automation Platform. To run Claude Code locally in your Warp terminal, see [Claude Code in Warp](https://funcoding.ai/agents/warp/agents/cli-agents/claude-code/) instead.

</div>

## Key features

* **Cloud orchestration** - Launch Claude Code from any Automation Platform trigger: the Warp app, the Oz web app, the Oz CLI, the REST API, [schedules](https://funcoding.ai/agents/warp/platform/triggers/scheduled-agents/), [Slack](https://funcoding.ai/agents/warp/platform/integrations/slack/) mentions, Linear issues, or GitHub Actions.
* **Claude model picker** - Choose the Claude model the harness uses, including the latest pinned Opus, Sonnet, and Haiku releases, the `best`/`opus`/`sonnet`/`haiku` aliases, and 1M-context variants.
* **First-class subagent** - A Warp Agent parent can dispatch Claude Code subagents to handle steps that require code review or nuanced judgment within a larger [multi-agent orchestration](https://funcoding.ai/agents/warp/platform/orchestration/).

## Available models

The Claude Code harness exposes Anthropic's coding-tuned model lineup. Common choices include:

* `best` - Resolves to the current top-of-line Claude model.
* `opus`, `sonnet`, `haiku` - Aliases that resolve to the current default for that family.

For the full list — including 1M-context variants for very large codebases and planning-tuned models — open the model picker in the Warp app's Cloud Mode or the **Model** field on the Oz web app's new-run pane.

## Credentials and billing

Claude Code calls Anthropic directly using credentials your team provides. The Automation Platform supports three Anthropic credential types, stored as [Warp-managed secrets](https://funcoding.ai/agents/warp/platform/secrets/):

* **Anthropic API key** - For direct Anthropic API access.
* **Anthropic Bedrock API key** - For Bedrock-routed inference using an API key.
* **Anthropic Bedrock access key** - For Bedrock-routed inference using AWS access credentials.

Anthropic bills your account directly for inference. Warp still meters [compute credits](https://funcoding.ai/agents/warp/support-and-community/plans-and-billing/credits/#compute-credits) for the run's sandbox and [platform credits](https://funcoding.ai/agents/warp/support-and-community/plans-and-billing/platform-credits/) for the orchestration layer.

For setup steps, see [Connecting Claude Code credentials](https://funcoding.ai/agents/warp/platform/harnesses/authentication/#connecting-claude-code-credentials).

## Starting a Claude Code run

* **Warp app** - In Cloud Mode, click the **Agent harness** dropdown above the input and choose **Claude Code**.
* **Oz web app** - On the new run or new schedule pane, choose **Claude Code** in the **Harness** field. A **Claude Code auth secret** field appears below it; pick one of your stored Anthropic secrets.
* **API and SDK** - Set the agent config `harness` to `claude` — the [harness identifier](https://funcoding.ai/agents/warp/platform/harnesses/#harness-identifiers) is `claude`, not `claude-code` — and the Anthropic secret name on the matching auth-secret field. See the [API reference](https://funcoding.ai/agents/warp/factories/api-and-sdk/).

## Related pages

* [Harnesses in the Automation Platform](https://funcoding.ai/agents/warp/platform/harnesses/) — choose between Warp Agent, Claude Code, and Codex.
* [Authentication](https://funcoding.ai/agents/warp/platform/harnesses/authentication/) — store Anthropic credentials as Warp-managed secrets.
* [Warp Agent with the Automation Platform](https://funcoding.ai/agents/warp/platform/harnesses/warp-agent/) — the Automation Platform's default harness, the only one that can orchestrate Claude Code subagents.
* [Multi-agent orchestration](https://funcoding.ai/agents/warp/platform/orchestration/) — coordinate a Warp Agent parent with Claude Code children across local and cloud runs.
* [Managing cloud agents](https://funcoding.ai/agents/warp/platform/managing-cloud-agents/) — inspect Claude Code cloud runs in the Agent Management Panel and the Runs page.
* [Codex with the Automation Platform](https://funcoding.ai/agents/warp/platform/harnesses/codex/) — Codex as a cloud harness.
* [Claude Code in Warp](https://funcoding.ai/agents/warp/agents/cli-agents/claude-code/) — Claude Code in your local Warp terminal.
* [Factory agents](https://funcoding.ai/agents/warp/factories/factory-agents/#configuring-a-third-party-harness) — configure Claude Code as a factory agent's harness.