Run multi-harness coding-agent workflows with Oh My OpenAgent
Install and operate Oh My OpenAgent as a reusable coding-agent harness for long-running, multi-model development sessions across agent clients.
npx skills add agentskillexchange/skills --skill run-multi-harness-coding-agent-workflows-with-oh-my-openagent
Use Oh My OpenAgent when the operator wants an agent to set up and run a repeatable coding-agent harness instead of manually wiring prompts, commands, model choices, and session conventions in each client. The workflow is concrete: install the documented package, follow the agent-facing installation guide, configure the target agent client, then invoke Oh My OpenAgent workflows such as ultrawork for extended implementation runs. The scope boundary is the harnessed operator workflow around coding agents; this is not a general listing for every feature in the project or a replacement for ordinary one-off chat use.
What this skill actually does
Inputs and prerequisites: Node.js or npm-compatible runtime, target coding-agent client such as OpenCode, Codex, AmpCode, Cursor, or Claude-compatible tooling, model/provider credentials as required by the selected client.
Setup notes: Install the oh-my-openagent package or follow the upstream agent-facing installation guide, then have the target coding agent fetch and apply the documented configuration instructions from the repository before invoking the desired workflow command.
Source and verification boundary: use https://github.com/code-yeongyu/oh-my-openagent/blob/dev/docs/guide/installation.md 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.