> ## Documentation Index
> Fetch the complete documentation index at: https://ade-app.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Code

> Claude Code runs inside ADE through the bundled Claude Agent SDK — scoped to a lane, with permission modes and transcripts handled for you.

![Claude](https://mintcdn.com/ade-ac1c6011/lmMpn49wx_3bhn_c/media/logos/models/claude-color.svg?fit=max\&auto=format\&n=lmMpn49wx_3bhn_c\&q=85\&s=9316e007802cfb2096811229986f09c2)

Claude Code runs inside ADE through the **bundled Claude Agent SDK** and ADE's own copy of Claude Code, downloaded for each machine the first time it is needed — there's no separate `claude` CLI to install, and your existing `claude` sign-in is reused. ADE keeps its copy at a tested version and turns Claude Code's self-update off. Pick a Claude model in any chat and ADE starts the session in the selected lane's worktree, applies your permission mode, streams tool calls live, and records the transcript to History.

## Setup

**1. Connect Claude in Settings → AI**

Sign in with a Claude subscription or paste an Anthropic API key. A green status means Claude is ready.

**2. Pick a Claude model in chat**

Open the model picker in the chat header and choose a Claude model. That session now runs on Claude.

## What ADE handles for you

> [card] Lane-scoped worktree
>
> Every session runs in the active lane's worktree, so Claude edits and runs commands against that task's isolated checkout.

> [card] Live transcripts
>
> Tool calls, thinking, and diffs stream into chat and are saved to History.

> [card] Permission gates
>
> A native permission mode decides what Claude can do without asking.

> [card] In-context links
>
> Changes attribute to Files and Git, and link out to PRs, Linear issues, and proof when used.

## Permission modes

Claude Code uses Claude's native permission model. Pick a stricter mode when exploring an unfamiliar repo, and a more permissive one only when you trust the lane and task.

> [accordion] The Claude permission modes
>
> | Mode | Behavior |
> | - | - |
> | `default` | Claude's built-in permission flow — asks before risky operations. |
> | `plan` | Read-only. Writing and executing are blocked until you approve a plan. |
> | `acceptEdits` | File writes allowed; shell commands still require approval. |
> | `bypassPermissions` | Proceeds without asking. |
>
> The mode can change mid-session from the permission picker. See [Permissions](https://ade-app.dev/docs/configuration/permissions.md) for how modes map across providers.

> [accordion] Where Claude runs
>
> Claude is also one of the providers you can launch as a CLI session in the Work tab, and as a CTO worker backend. Wherever it runs, it's the same bundled Claude Agent SDK against the same lane worktree — desktop, the web client, and your phone all see the session.

> [card] [AI providers](https://ade-app.dev/docs/configuration/ai-providers.md)
>
> Connect each agent and set defaults.

> [card] [Agent chat](https://ade-app.dev/docs/chat/overview.md)
>
> Run Claude in a lane and watch tool calls stream.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.