igorwarzocha/opencode-workflows

An ever evolving repository of Opencode workflow examples that might enhance your experience with it. I only left the stuff that actually works. YMMV.

57 stars7 forksUpdated Jan 25, 2026
npx skills add igorwarzocha/opencode-workflows

README

Opencode Workflows

A collection of Opencode-based command templates, global agent prompts, and workflow patterns for building sophisticated command-driven projects.

opencode-workflows


Start Here: Opencode Configurator

The Opencode Configurator (agents/opencode-configurator/) is a meta-configuration system that makes setting up OpenCode effortless. Just ask naturally:

  • "Is there a plugin for reducing token usage?"
  • "Set up permissions so destructive commands require approval"
  • "Create a /review command that analyzes code without making changes"
  • "I want to build a skill for working with our internal API"
  • "Find an MCP server for filesystem access"

The configurator agent draws on seven specialized skills:

SkillWhat it does
plugin-installerFind and install community plugins, maintain a local catalog
opencode-configEdit opencode.json with guided setup for models, permissions, providers
command-creatorBuild custom /slash commands through interactive Q&A
skill-creatorScaffold new skills with proper structure, scripts, and references
agent-architectDesign agents with research-backed prompt engineering patterns
mcp-installerFind, install, and configure Model Context Protocol (MCP) servers
model-researcherResearch and configure new/custom AI models not yet in models.dev, with verified specifications

Installation: Drop the skill/ and agent/ folders into ~/.config/opencode/.

See agents/opencode-configurator/README.md for full details.


The Ralph Wiggum Loop (KISS Method)

The Ralph Wiggum Loop (/loop) is a high-intensity, autonomous "black box" orchestrator that follows the KISS (Keep It Simple, Stupid) principle: The technique is deterministically bad in an undeterministic world.

It puts a specialized task tool subagent in an evolving while-loop, pushing it through repeated layers of implementation and hyper-detailed verification until the task is 100% complete.

See commands/.opencode/command/loop.md for full details.


Create OpenCode Plugin

The Create OpenCode Plugin (agents/create-opencode-plugin/) is a workflow bundle for AI-assisted plugin development in OpenCode. Describe what you want your plugin to do, and the workflow guides you through design, testing, and publishing.

Usage: Run /create-plugin [your idea].

See agents/create-opencode-plugin/README.md for full details.


Plugins

  • Gemini/GLM Focused Mode (plugins/gemini-glm-focused-mode/) – Injects a rigorous system prompt for GLM-4.7 and Gemini models to enforce precise, grounded, and persistent coding behavior.

Security Reviewer

The Security Reviewer (agents/security-reviewer/) is a specialized agent for auditing codebases against vibecoding vulnerabilities. It bundles 10 framework-specific security skills.

See agents/security-reviewer/README.md for full details.


Configuration Examples

  • Thinking Levels Variants (thinking-variants config/thinking-levels-opencode.json) – OpenCode configuration with model variants for Ctrl+T thinking level switching.

included Packs

Agent Catalog

To optimize model usage, we recommend disabling the legacy generic general subagent in your opencode.json and using the fast/smart split instead:

"subagents": {
  "general": {
    "disable": true
  }
}

Agents are organized under agents/:

  • generic/ – Reusable global agents that belong in ~/.config/opencode/agent/:
    • fast – High-speed workhorse for trivial edits and file lookups.
    • smart – Senior developer for complex bug hunting and refactoring.
    • subagent-orchestrator – Dispatches specialists and enforces scope isolation.
    • openspec-orchestrator – Enforces strict OpenSpec formatting/validation and orchestrates subagents.
  • repo-navigator/ – Full pack for repository documentation. Unified /init command with argument routing:
    • /init – Full AI navigation AGENTS.md + skill recommendations
    • /init basic – Minimal AGENTS.md structure only
    • /init user – User assistance docs (setup, install, troubleshoot)
  • parallel-PRD/ – Parallel PRD planning kit with planner subagents and an orchestrator.
  • component-engineer/ – Expert architecture package for professional React components.
  • opencode-configurator/ – Meta-configuration system for OpenCode.
  • security-reviewer/ – Specialized agent for auditing vulnerabilities.
  • create-opencode-plugin/ – Workflow bundle for AI-assisted plugin development.
  • vite-react-ts-convex-tailwind/ – Stack-specific experts for the modern Vite + React 19.2 + TS 5.9 + Tailwind 4.1 + Convex stack.

See agents/README.md for full tables, usage details, and the complete directory tree.

Commands Catalog

The `

...

Read full README

Publisher

igorwarzochaigorwarzocha

Statistics

Stars57
Forks7
Open Issues0
CreatedNov 17, 2025