opencode plugin that prepends a synthetic user message when a compacted conversation would otherwise start with an assistant tool-call, avoiding the Anthropic `tool_use` without `tool_result` error.
AnthraCode — AI coding agent for the terminal
Get the npm global path prefix.
A dynamic skills plugin for OpenCode that provides tools for loading and using reusable AI agent skills.
OpenCode plugin that optimizes token usage by pruning obsolete tool outputs from conversation context
Intelligently detects and recovers stalled OpenCode sessions using abort+continue with status polling and progress tracking
Three-layer memory architecture for OpenCode with workspace memory and hot session state
OpenCode plugin for Morph SDK - fast apply, WarpGrep codebase search
OpenCode goal plugin that adds Codex-style long-running goal mode, /goal commands, persistence, and TUI status for AI coding agents.
OpenCode plugin for persistent memory via Graphiti knowledge graph
Base OpenCode agent rules for execution discipline, verification, CLI-first scaffolding, and context window management.
Advanced fallback plugin for OpenCode agents — model switching, retry with backoff, and context overflow handling
OpenCode TUI plugin bundle with a SQLite-backed server recall target
Active Context Management plugin for OpenCode — pin, prune, scan, compact, and manage context with surgical precision
Prefix all CSS rules with a selector
OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers.
OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment
loglevel plugin that adds colored level prefix (node only)
OpenCode 插件：参考 VibeGuard 的占位符格式（__VG_...__）在发送给 LLM 前脱敏、在响应完成后自动还原、在工具执行前还原参数
AI SDK v6 provider for OpenCode via @opencode-ai/sdk
Recursive-Length Prefix (RLP) coder.
Letta-style editable memory blocks for OpenCode.
A simple method that will strip a valid hex prefix off a string, if present.
OpenCode plugin that prefixes shell commands with snip to reduce LLM token consumption