Agent skill · alirezarezvani
run-without-you
Use when a graded managed agent should run on a schedule, on an event trigger or on demand ('run it every morning'). Validates cron with cron_validator.py and builds the deployment with deployment_builder.py.
What it needs
About 2k tokens when loaded.
What this skill does
Phase 4 — Run Without You (the recurring loop) A scheduled deployment fires a fresh session on a cron cadence — the agent runs without you. Each firing can carry its own outcome, nesting the bounded grade→iterate loop inside every recurring run. See ../../references/loops-and-workflows.md. Choose the trigger Answer Shape Tool --- --- --- "every morning / weekly / nightly" recurring cron deployment deploymentbuilder.py + cronvalidator.py "when X happens" event-driven curl (documented, not scheduled) deploymentbuilder.py (message only) "only when I ask" on-demand (no deployment) none — just re-send a user.message Workflow (recurring) 1. Validate the schedule. Invalid cron/timezone → exit 1. Read the DST note: wall-clock semantics mean spring-forward times are skipped and fall-back times fire twice — avoid 02:00–03:00 in DST zones if exactly-once matters. 2. Build the deployment payload. --nest-outcome includes the rubric so each firing self-grades. The tool prints the BYOK curl to create it and to test it once with the manual run endpoint before trusting the schedule. 3. Test before you trust. Fire one manual run, read the verdict, only then leave the cron in place. Pin the agent version in the deployment once it passes. 4. Finalize the roadmap. 5. Advance + hand to wrap-up. goalstate.py set --phase wrap-up, then invoke the wrap-up skill. Hard rules Test with a manual run first. Never commit a schedule you haven't fired once. Safety rails on by default. alwaysask MCP, limited networking where you can, readonly untrusted memory, maxiterations per firing, workspace spend limit. There is no spend cap inside CMA. DST is wall-clock. Surface the note; pick safe times. ≤1,000 deployments/org. Forcing-question library (recommend + cite) 1. "Cadence, event, or on-request?" Recommend: on-request v0 → cadence once graded. Cite: loops-and-workflows.md. 2. "Should each firing self-grade?" Recommend: yes — nest the outcome. Cite: loops-and-workflows.md (nesting rule). 3. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/run-without-you--fa08e2