Start and stop the project's scheduler, switch the commands it starts on a schedule on or off, set their pace, or start one now, when the person asks you to.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
The scheduler starts agents on a schedule: the project's skills say which commands can run on one, and each machine switches them on for itself. It runs in its own process and needs no dashboard.
Run the scheduler command at the project's root, always by its full name: npx @openagt/skill-scheduler@0.1. It prints one JSON document; a refusal exits 1 with why on stderr; a wrong command line exits 2 with the usage.
Change it only when the person asks: every run it starts spends their quota.
npx @openagt/skill-scheduler@0.1 status on, running, the switches, and schedule: every command
that can run on a schedule, with its pace (every), its check (when)
npx @openagt/skill-scheduler@0.1 start the scheduler on, ticking every minute in its own process
npx @openagt/skill-scheduler@0.1 stop the scheduler off; runs in flight go to their end
npx @openagt/skill-scheduler@0.1 switch <command> on|off whether a command runs on this machine; every one starts off
npx @openagt/skill-scheduler@0.1 pace <command> <N<m|h|d|w|mo>|work|skill> [HH:MM]
how often at most it starts; work: whenever its check finds work;
skill: its skill's own pace again
npx @openagt/skill-scheduler@0.1 now <command> one run of it now, whatever its switch and pace
A command is named as status names it, quoted when it has a word after it. A switched-on command starts nothing while the scheduler is off: switch it on, then start.
The rest, such as a command's agent, model, publish level, or the person's own automations, is in its usage: npx @openagt/skill-scheduler@0.1 with no command prints it.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Where your work goes (a branch named agent-<name>), how to name it, what must be true before you finish, and how to push it when you are asked to.
The English summary is being prepared. Showing the original description.
A real browser you drive from the shell, to see or act on a web page (open it, read it, click, type, take a screenshot), such as checking that the app you changed works.
The English summary is being prepared. Showing the original description.
Post a message to the team's Discord channel from the shell, when a task asks you to tell people something there.
The English summary is being prepared. Showing the original description.
The project's git host is GitHub: how to open your pull request when you are asked to, how to land it, and how to read and close the project's issues.
The English summary is being prepared. Showing the original description.
The record of every run agents made on this project — what was asked, where the work went, how it ended, what the agent said — where it lives, how to read it, and when to look back before you work.
The English summary is being prepared. Showing the original description.
Refactor a part of the code to make it as maintainable as possible.
The English summary is being prepared. Showing the original description.