Install Agent-Native Research Artifact (ARA) skills — compiler, research-manager, rigor-reviewer — into Claude Code, Cursor, OpenCode, Gemini CLI, Codex, and more.
OpenCode plugin for Context-Driven Development workflow
Native napi-bridge module for MCP Server
Quick setup for SuperPawers skills and markdown agents for OpenCode
Behavioral eval runner for AI coding agents — snapshot a workspace, hand it to a runner with a task prompt, score the resulting filesystem/git state.
Project-configurable startup preflight prompts for OpenCode.
Turn backlog into reviewed PRs with an OpenCode issue-to-PR orchestration plugin.
OpenCode plugin to strip or replace emojis from agent outputs
Agent Package Management - Universal package manager for AI agent skills
Assistant-first CLI for running, inspecting, and debugging local testkit suites
OpenCode plugin that converts pasted clipboard data URLs to temp files for GLM models
CLI for configuring local OpenClaw, Claude, and Codex settings
Unified LLM API with automatic model discovery and provider configuration
Give OpenCode a soul — personality injection and long-term memory for your AI agent
A Vite plugin that bridges React applications with Kulp.AI, providing error reporting, route tracking, component tagging, and more
<h1 align="center">Backlog.md</h1> <p align="center">Markdown‑native Task Manager & Kanban visualizer for any Git repository</p>
OpenCode plugin that automatically redacts API keys, tokens, passwords and other secrets from all data sent to LLMs
OpenCode plugin that automatically summarizes conversation context into structured session memory and injects it back into the system prompt every few turns.
Bootstrap and audit AGENTS.md, ARCHITECTURE.md, ADRs, skills, and subagents for engineering production code with LLMs
OpenCode TUI sidebar plugin for context usage progress
LLxprt Code
Bootstrap installer for the ControlKeel native CLI - a control plane for agent-generated software delivery.
OpenCode plugin that shows ChatGPT/OpenAI usage in the sidebar and command palette.
Open-source, agent-agnostic CLI for visual verification. Your AI coding agent builds a feature — ProofShot records video proof it works.