Skill Detail

Run OpenCode specialist-agent workflows with Oh My Opencode Slim

Install an OpenCode orchestration plugin that routes codebase work across specialist agents, background tasks, model presets, bundled skills, and live terminal multiplexers.

Templates & WorkflowsMulti-Framework
Templates & Workflows Multi-Framework Security Reviewed
⭐ 7k GitHub stars ⬇ 24.2k/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill run-opencode-specialist-agent-workflows-with-oh-my-opencode-slim Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
OpenCode, Bun or Node.js/npx, optional tmux, zellij, herdr, cmux, or kitty for live multiplexer viewing
Install & setup
Run bunx oh-my-opencode-slim@latest install or npx oh-my-opencode-slim@latest install, then configure the generated OpenCode plugin presets, model mappings, skills, MCP permissions, and project-local overrides as needed.
Author
alvinunreal
Publisher
Individual
Last updated
Jul 18, 2026
Quick brief

Use Oh My Opencode Slim when an OpenCode session needs a repeatable specialist-agent operating model rather than one general chat loop. The operator installs the plugin, lets the Orchestrator plan and dispatch Explorer, Oracle, Council, Librarian, Designer, Fixer, and other specialist lanes, watches background agents through supported multiplexers, and reconciles their results before implementation or review continues. Invoke this instead of using OpenCode normally when work needs parallel codebase scouting, fresh documentation lookup, architecture review, UI implementation, verification planning, or model-specific routing inside one governed OpenCode setup. A strong run starts by choosing the team preset, checking which specialists may use MCPs or write tools, and deciding which tasks should run in the background. The boundary is the OpenCode plugin workflow: install, configure presets and permissions, run bundled skills, and supervise delegated specialists. It is not a generic OpenCode listing or a broad multi-agent framework card. Keep the run anchored to reviewable outputs and explicit handoffs.