Timmy6942025

opencode-agents

Complete guide to OpenCode's agent system. Use this skill when configuring, creating, or managing OpenCode agents — including primary agents (Build, Plan), subagents (General, Explore, Scout), hidden agents (Compaction, Title, Summary), custom agents via JSON config or Markdown files, agent permissions (allow/ask/deny with glob patterns), task permissions for subagent invocation, session navigation keybinds, multi-agent workflows, and agent creation via CLI. Covers all agent options: description, mode, model, temperature, steps, disable, prompt, tools (deprecated), permission (with object syntax for bash commands), color, top_p, hidden, and provider-specific pass-through options.

opencode-builder

Use this skill when the user is building extensions, plugins, integrations, or custom developer tools on top of OpenCode (opencode.ai). This includes: creating plugins with custom AI tools and lifecycle hooks, using the SDK for programmatic session control and multi-agent workflows, building model providers or MCP integrations, configuring opencode.json, and implementing advanced orchestration like checkpoint/resume, parallel execution, or adversarial review. Trigger for any development work that extends or automates OpenCode. Do NOT trigger for general usage questions, troubleshooting, UI theming, or tool comparisons.

Data & Documents Listed

opencode-config

Use this skill when configuring OpenCode's opencode.json or tui.json files, setting up config precedence, managing provider credentials, using variable substitution, deploying managed settings via MDM, or troubleshooting configuration issues. Covers all config options, schema validation, remote/global/project config layers, environment variables, file references, and enterprise managed preferences.

opencode-mcp

Use this skill when adding Model Context Protocol (MCP) servers to OpenCode, configuring local or remote MCP servers, setting up OAuth authentication for MCP, managing MCP server permissions per agent, or troubleshooting MCP connection issues. Covers local/remote server types, OAuth flows, tool management, overriding remote defaults, and common MCP server examples.

opencode-permissions

Use this skill when configuring OpenCode's permission system — controlling which tools require approval, setting granular bash command rules, managing external directory access, configuring per-agent permissions, or understanding the allow/ask/deny permission model. Covers wildcards, pattern matching, doom loop detection, and the complete permission key reference.

opencode-plugins

Use this skill when building OpenCode plugins, hooking into OpenCode's lifecycle events, intercepting tool execution, injecting environment variables, adding custom tools via plugins, understanding plugin loading order and dependencies, or debugging plugin issues. Covers all plugin hooks, event types, TypeScript support, npm/local loading, custom tool creation, and real-world plugin patterns.

opencode-providers

Use this skill when configuring LLM providers in OpenCode, setting up API keys, connecting providers via /connect, configuring custom OpenAI-compatible providers, setting up local models (Ollama, llama.cpp, LM Studio), or troubleshooting provider authentication issues. Covers all 75+ supported providers, OpenCode Zen, OpenCode Go, provider-specific options, and environment variable configuration.

opencode-sdk

Use this skill when using the OpenCode JavaScript/TypeScript SDK (@opencode-ai/sdk) to programmatically control OpenCode, create sessions, send prompts, manage files, control the TUI, stream events, or build external integrations. Covers both full lifecycle (server+client) and client-only modes, all API methods, structured output, and type safety.

API & Backend Listed

opencode-server

Use this skill when running, configuring, connecting to, or extending the OpenCode HTTP server. Covers opencode serve, opencode web, authentication, mDNS discovery, CORS, the full OpenAPI 3.1 spec, all REST endpoints (sessions, messages, config, providers, files, tools, LSP, MCP, agents, TUI control, events, docs), the SDK generated from the spec, connecting clients, attaching terminals, IDE plugin integration, and real-time SSE event streaming.

Data & Documents Listed

opencode-skills

Create, configure, and troubleshoot OpenCode agent skills (SKILL.md definitions). Covers file locations, discovery, frontmatter spec, permissions, per-agent overrides, and publishing.

opencode-tools

Use this skill when working with OpenCode's built-in tools (bash, read, write, edit, grep, glob, lsp, apply_patch, skill, todowrite, webfetch, websearch, question), creating custom tools in TypeScript/JavaScript, configuring tool permissions, understanding MCP tool integration, or understanding tool internals like ripgrep integration, .ignore files, and tool precedence.

opencode-troubleshooting

Use this skill when diagnosing and resolving issues with OpenCode Desktop or CLI. Covers log inspection, storage locations, desktop app troubleshooting (plugins, cache, server connection, Wayland/X11, WebView2, notifications, storage reset), common errors (startup failures, authentication, model not found, ProviderInitError, AI_APICallError, copy/paste on Linux), and CLI debugging tools. Trigger on: troubleshooting, debugging, logs, won't start, error, crash, blank screen, connection failed, provider error, auth error, copy paste linux.