Oh My OpenCode

Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prometheus planning, background tasks, category-based task routing, model resolution, tmux integration, or any oh-my-opencode feature. Covers installation, configuration, all agents (Sisyphus, Oracle, Librarian, Explore, Atlas, Prometheus, Metis, Momus), all categories, slash commands, hooks, skills, MCPs, and troubleshooting.

This skill appears to do what it says: configure and run an OpenCode multi-agent plugin. Before installing or running scripts, verify the upstream project (the SKILL.md cites https://github.com/code-yeongyu/oh-my-opencode), and be cautious about running network-install commands (curl | bash, bunx/npx) since they will fetch and run code from the network. Confirm you trust the package source and that your OpenCode provider credentials remain managed by the opencode CLI (not embedded in this skill). If you need stronger assurance, inspect the remote repository and any installer package before executing the installer or doctor commands.

Type: OpenClaw Skill Name: oh-my-opencode Version: 1.0.0 The skill bundle describes a highly autonomous multi-agent system with extensive capabilities including arbitrary bash execution, file editing, network access, and background task execution, as detailed in `SKILL.md` and `references/configuration.md`. While these features are presented as necessary for its stated purpose of advanced software development, they represent significant high-risk behaviors. The ability to load skills from remote URLs (e.g., `https://example.com/skill.yaml` in `references/configuration.md`) also introduces a supply chain risk. There is no clear evidence of intentional malicious behavior in the provided files, but the broad permissions and autonomous nature make it suspicious due to the potential for misuse or misconfiguration.