> ## Documentation Index
> Fetch the complete documentation index at: https://ade-ac1c6011-ade-mobile-chat-stability-54bd7ef0.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Permissions and security

> How ADE keeps agent work scoped, reviewable, and local-first.

ADE agents can edit files and run commands, so permissions matter. The goal is to keep work scoped to the right lane and make risky actions visible before they happen.

## Main controls

<CardGroup cols={2}>
  <Card title="Lane scope" icon="code-branch">
    Sessions run inside a selected lane worktree.
  </Card>

  <Card title="Provider permissions" icon="robot">
    Claude, Codex, Cursor, and OpenCode each expose provider-specific approval modes.
  </Card>

  <Card title="Command trust" icon="terminal">
    Shared command definitions may require local approval before they run.
  </Card>

  <Card title="Secrets" icon="key">
    Credentials stay in local encrypted stores or gitignored files.
  </Card>
</CardGroup>

## Practical defaults

* Use worktree lanes for agent edits.
* Keep the primary checkout for inspection or manual commands.
* Review diffs before committing or pushing.
* Use stricter provider approval modes for unfamiliar repositories.
* Do not store provider keys in committed files.
* Treat shared command changes like CI or Dockerfile changes: review them carefully.

## Provider modes

Permission names vary by provider. In general:

| Mode style       | Meaning                                                                         |
| ---------------- | ------------------------------------------------------------------------------- |
| Read-only / plan | The agent can inspect and propose, but cannot freely edit.                      |
| Default / edit   | The agent can work in the lane with normal guardrails.                          |
| Full access      | The agent can run with fewer prompts. Use only when the environment is trusted. |

## Sensitive actions

Be extra careful with:

* Force pushes.
* Commands outside the repository.
* Secret files and `.env` files.
* Scripts pulled from unreviewed branches.
* Networked deployment or release commands.

<Warning>
  ADE helps enforce boundaries, but it is still running tools on your machine. Review what agents ask to do, especially in new repositories.
</Warning>