
Self Scheduling
Define durable work and scheduled/headless execution with `.alice/issues/<id>.md`...
Install
npx skills add TraderAlice/OpenAlice --skill self-scheduling -g -a claude-code -y- Repository
- TraderAlice/OpenAlice7.4k
- Category
- AI and agents
- Updated
- 12d ago
- License
- AGPL-3.0
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Define durable work and scheduled/headless execution with `.alice/issues/<id>.md`: structured ownership and optional `when` frontmatter plus one canonical markdown What. Use for creating or editing an Issue, choosing its assignee, schedule, prompt, delivery behavior, or health state. Use the `alice` skill instead when the goal is to ask another Session for an answer.
Issues & self-scheduling, .alice/issues/<id>.md
OpenAlice treats an issue as a collaboration object, not just a timer. It is the
durable place to put trading follow-up, monitoring work, open questions,
handoffs, and scheduled checks. Status, priority, and assignee tell humans and
agents what deserves attention; when is the extra field that lets an issue
summon a headless agent run.
This workspace owns its work as one markdown file per issue in .alice/issues/
at its own root. Each file is YAML frontmatter (the structured fields) plus a
markdown What (the human-visible work definition and exact scheduled prompt).
- An issue without
whenis a plain tracked work item, it appears on the Issue board for you and the user to see, but the scanner never fires it. - An issue with
whenself-schedules: a launcher scanner reads the dir (it never interprets the work) and fires a headless run of this workspace when the issue is due, exactly like a recurring job.
The filename stem is the issue id (morning-scan.md → id morning-scan).
Two ways to manage issues, the CLI (agent surface) or the file
You have two equivalent paths, and both write the same
.alice/issues/<id>.md files:

