Run scheduled autonomous agent Hands with OpenFang
Use OpenFang to run packaged autonomous agent workflows on schedules with manifests, dashboards, reporting, and guardrails for sensitive actions.
npx skills add agentskillexchange/skills --skill run-scheduled-autonomous-agent-hands-with-openfang
Approve OpenFang as a concrete operator workflow for running packaged autonomous agent Hands, not as a generic Agent OS listing. The operator installs the single OpenFang binary, initializes a workspace, starts the local dashboard, configures a Hand such as lead research, OSINT collection, or clip production, and reviews outputs plus approval gates for sensitive actions. Invoke it when a user wants a scheduled, repeatable agent workflow that wakes up, runs a defined procedure, reports results, and exposes operational controls instead of manually prompting a chatbot each time. The scope boundary is the scheduled Hand lifecycle—install, configure, run, monitor, approve sensitive steps, and collect reports—not the entire framework or every possible autonomous-agent use case.
What this skill actually does
Inputs and prerequisites: OpenFang CLI/binary, local dashboard, workflow-specific provider credentials or integrations as needed.
Setup notes: Follow upstream quick start: install the OpenFang binary from the official installer, run `openfang init`, then `openfang start` and use the local dashboard to configure and monitor Hands.
Source and verification boundary: use https://www.openfang.sh/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.