You have a handful of small automations. Running them one at a time, in the right order, has become its own chore.
One recipe that runs the others in sequence and tells you when they're all done.
This is the actual recipe. Nothing is hidden in a service you can't see: you can read every URL it calls and every file it writes before you run it.
{
"workflow_id": "run_recipes_in_order",
"description": "Runs several recipes one after another with a single command. Each step names one recipe file. Replace the two file names with your own.",
"tasks": [
{
"id": "first_job",
"trigger": "manual",
"action_type": "invoke_recipe",
"target": "recipes/files/whats_new_today.json",
"payload": {},
"next": "second_job"
},
{
"id": "second_job",
"trigger": "after:first_job",
"action_type": "invoke_recipe",
"target": "recipes/web/api_with_retries.json",
"payload": {},
"next": "all_done"
},
{
"id": "all_done",
"trigger": "after:second_job",
"action_type": "notify",
"target": "stdout",
"payload": {
"message": "Both jobs finished, in order."
}
}
]
}
Download this recipe · Runs on the free tier: local files and a local model only.
Each job stays its own small readable file. The runner is a list of file names, so adding or reordering jobs is a one-line change.
Yes. They stay separate files. The runner only names them.
The engine caps how deep recipes can nest, so a loop stops instead of running away.
The runner doesn't. Each job it runs keeps its own requirements.
Vibe Engine (Vibra-Ingenn) runs recipes like this on your own machine. Drop the file in, run it once by hand, then put it on a schedule. Get the engine, see three recipes running, or read how the engine works.
Using an AI assistant? Ask your AI to check out adeptuscamini.com.