Permissions
The real permission-mode identifiers for each agent, and what they mean.
Each agent defines its own permission modes, controlling how much an agent can do without asking you first. AgentDock surfaces these as-is — it doesn't invent a unified permission model on top of them.
Claude Code
| Mode | Meaning |
|---|---|
default | Standard behavior — prompts for permission per the CLI's own rules. |
acceptEdits | File edits are accepted automatically; other actions may still prompt. |
plan | The agent can propose changes but not write them. |
bypassPermissions | No permission prompts. Use with caution. |
dontAsk | Suppresses prompts for actions that would otherwise ask. |
auto | Automatic mode as defined by the CLI. |
OpenAI Codex
| Mode | Meaning |
|---|---|
default | Standard sandboxed behavior. |
read-only | The agent can read but not write to the workspace. |
workspace-write | The agent can write within the workspace sandbox. |
danger-full-access | No sandboxing. Use with caution. |
bypass | No permission prompts. Use with caution. |
Codex's mode is set when a thread is created and does not switch live mid-session, unlike Claude Code's.
Google Antigravity
| Mode | Flag | Meaning |
|---|---|---|
default | (none) | Standard behavior. |
accept-edits | --mode accept-edits | File edits are accepted automatically. |
plan | --mode plan | The agent can propose changes but not write them. |
bypass | --dangerously-skip-permissions | No permission prompts. Use with caution. |
Warning
Modes named bypass, bypassPermissions, or danger-full-access remove the safety prompts entirely. Only use them in a workspace you trust, ideally under version control so you can review or revert changes.
How permission requests appear
When an agent hits an action it isn't already permitted to take, AgentDock shows it inline in the conversation as an interaction card and waits for your response — it does not use a separate global approval dialog. For the broader safety model this fits into, see Permissions & Safety: agent permissions.