Skip to content
rn-dev-agent

run-action

Replay a saved action — login, navigate to a screen, complete a multi-step flow — in seconds. Counterpart to /list-learned-actions, which discovers what’s available.

Usage

Section titled “Usage”
/rn-dev-agent:run-action <name> [-e KEY=VALUE ...] [--platform ios|android] [--dry-run]

Examples

Section titled “Examples”
/rn-dev-agent:run-action wizard-create-task -e TITLE="Buy milk" -e PRIORITY=high
/rn-dev-agent:run-action user-login --platform android
/rn-dev-agent:run-action mark-all-done --dry-run

How match works

Section titled “How match works”

The first argument is matched against action filenames in .rn-agent/actions/ (substring, case-insensitive). If the match is unique, replay starts immediately. If multiple actions match, the plugin prints the candidates and asks for disambiguation. If none match, it offers the closest alternatives.

Parameters

Section titled “Parameters”
  • -e KEY=VALUE — fills ${KEY} placeholders inside the action body. Repeatable.
  • --platform ios|android — picks a target platform when both are booted. Auto-detected if only one is running.
  • --dry-run — print the resolved replay command without executing.

Self-repair

Section titled “Self-repair”

If a step fails because a testID was renamed, the plugin uses the live UI to find the new name, patches the action YAML, and retries.

When to run

Section titled “When to run”
  • The agent uses this internally when it detects a known starting state (e.g., logged-in home) is needed before doing new work
  • You can also call it directly to validate an action still works after a code change
  • During development, to skip past login or onboarding when iterating on a downstream screen

See also

Section titled “See also”