OpenCode TUI plugin that displays real-time LLM output token speed (tok/s)
Measure + analyse the speed of your webpack loaders and plugins
OpenTelemetry telemetry plugin for opencode CLI
GitLab OAuth authentication plugin for OpenCode
Lightweight agent orchestration plugin for OpenCode - a slimmed-down fork of oh-my-opencode
OpenCode plugin that exposes subagent session statusline state
Downloading and running time plugin for Size Limit
OpenCode plugin that optimizes token usage by pruning obsolete tool outputs from conversation context
OpenCode plugin that uses your Claude Code credentials — no separate login needed.
Poe OAuth authentication plugin for OpenCode
Opinionated OpenCode agent harness — PRIME, plan, build, QA, skills, MCP wiring, hashline editing.
OpenCode plugin for detailed token usage analysis with breakdowns by category, visual charts, and subagent cost tracking
TypeScript definitions for speed-measure-webpack-plugin
Langfuse observability plugin for OpenCode - LLM tracing, prompt versioning, and cost tracking
Automatically trace OpenCode conversations to Braintrust. Captures user messages, assistant responses, and tool calls for observability.
OpenCode quota & tokens usage with zero context window pollution. Supports GitHub Copilot, OpenAI (Plus/Pro), Qwen Code, Chutes AI, Synthetic, Google Antigravity, Z.ai coding plan and more.
Speed Insights is a tool for measuring web performance and providing suggestions for improvement.
Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials
OpenCode plugin for Telegram notifications - get notified when tasks complete, respond to permission requests via Telegram
OpenCode plugin that prefixes shell commands with snip to reduce LLM token consumption
Track Core Web Vitals in Gatsby projects with Vercel Speed Insights.
🌈 Light, fast, and easy to use, dependencies free javascript syntax highlighter, with automatic language detection
 
Control and monitor OpenCode from Telegram with notifications, question replies, and subagent-aware completion.