droid exec uses tiered autonomy to control what operations the agent can perform. Only raise access when the environment is safe.
Level
Intended for
Notable allowances
(default)
Read-only reconnaissance
File reads, git diffs, environment inspection
--auto low
Safe edits
Create/edit files, run formatters, non-destructive commands
--auto medium
Local development
Install dependencies, build/test, local git commits
--auto high
CI/CD & orchestration
Git push, deploy scripts, long-running operations
--skip-permissions-unsafe
Isolated sandboxes only
Removes all guardrails (⚠️ use only in disposable containers)
Examples:
Copy
Ask AI
# Default (read-only)droid exec "Analyze the auth system and create a plan"# Low autonomy - safe editsdroid exec --auto low "Add JSDoc comments to all functions"# Medium autonomy - development workdroid exec --auto medium "Install deps, run tests, fix issues"# High autonomy - deploymentdroid exec --auto high "Run tests, commit, and push changes"
--skip-permissions-unsafe removes all safety checks. Use only in isolated environments like Docker containers.
Custom models configured via BYOK use the format: custom:<alias>See Choosing Your Model for detailed guidance on which model to use for different tasks.
The /mcp command manages Model Context Protocol servers:
Copy
Ask AI
/mcp list # List all configured servers/mcp add <name> <command> # Add stdio-based server/mcp add --type http <url> # Add HTTP-based server/mcp remove <name> # Remove a server/mcp get <name> # Show server details/mcp enable <name> # Enable a disabled server/mcp disable <name> # Temporarily disable a server
# Investigationdroid exec "Analyze failing tests and explain root cause"# Fix and verifydroid exec --auto medium "Fix failing tests and run test suite"