16 boosters for "harness" — open source, verified from GitHub, ready to install
  
Oh My Opencode is an AI agent harness that provides multi-model orchestration, parallel background agents, and advanced code analysis tools for Claude Desktop and Claude Code. It benefits developers building sophisticated AI-powered applications who need orchestrated agent coordination and deep code understanding capabilities.
Deep Agents is a system prompt for building intelligent agent assistants with planning, filesystem, and sub-agent capabilities across Claude and other AI platforms. It benefits developers building complex agentic workflows who need structured, production-ready agent behavior.
"description": "Agent Team & Skill Architect — Meta-skill that designs agent teams, defines specialized agents, and generates skills for your domain/project. 도메인/프로젝트에 맞는 하네스를 구성하고, 전문 에이전트를 정의하며, 에이전트가 사용할 스킬을 생성하는 메타 스킬.", "url": "https://github.com/revfactory" "homepage": "https://github.com/revf
"name": "memsearch-plugins", "email": "support@zilliz.com" "description": "Semantic memory search plugin for Claude Code — markdown-first, backed by Milvus",
This project uses a portable brain in . It is authoritative for memory, skills, and protocols. For deploy / ship / release / migration / schema / timestamp / timezone /
"name": "claude-code-harness", "version": "3.17.1", "description": "Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.",
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "description": "Governance framework for software projects — RFCs, ADRs, work items with lifecycle enforcement", "name": "govctl-org",
"name": "claude-harness", "description": "Long-running agent harness with 5-layer memory architecture, GitHub integration, autonomous batch processing, Agent Teams with ATDD, 9 hooks (safety, quality gates, team coordination), and 6 Agent Skills", "name": "panayiotis"
"description": "Harness Engineering plugin exposing executable fitness functions for architecture quality, change-aware validation, and MCP-powered review context.", "version": "0.1.14", "homepage": "https://github.com/phodal/entrix",
에이전트 기반 작업 오케스트레이션 스킬. Plan→Work→Review 사이클로 구조화된 작업 수행. 브릿지가 에이전트 상태를 실시간으로 추적하고 채널에 알림을 전송합니다. 에이전트 프롬프트를 읽어서 에 전달:
"name": "harness-mcp-v2", "description": "Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools", "main": "build/index.js",
Spec-Driven RE mit skalierbarer Governance. Specs sind Verträge, keine Vorschläge. Enforcement ist automatisch, nicht optional. SpecForge arbeitet ausschließlich mit: 1. Session-Kontext — aktuelle Konversation
"name": "nonstop-agent", "description": "Generate 24/7 autonomous coding agents with Anthropic best practices", "name": "seolcoding"
"name": "alphaagent-team", "email": "support@answeragent.ai" "description": "AlphaAgent Team Plugin Marketplace - Claude Code plugins for autonomous coding assistance",
"id": "ai.bringyour/portable", "name": "BringYour", "description": "Move your AI agent harness between 13 tools, or bootstrap one from GitHub. $49 lifetime."
