285 boosters for "agents" — AI-graded, open source, ready to install
Comprehensive Copilot instructions for the Code for Life monorepo workspace, guiding AI agents through architecture, development workflows, and best practices for contributing to frontend, backend, and legacy services.
A Cursor rules template that delegates project context and agent instructions to a maintained docs file, enabling AI tools to stay synchronized with evolving project guidelines. Useful for teams practicing agentic workflows who want dynamic, version-controlled AI agent behavior.
A collection of 48 specialized AI subagents for Claude Code that automate domain-specific development tasks like backend architecture, frontend development, and DevOps. Developers benefit from having expert agents pre-configured for different roles, reducing context-switching and improving productivity across the full software development lifecycle.
The plan-generator transforms high-level product requirements into executable project blueprints (genesis.xml files) with structured task DAGs and agent assignments. It's invaluable for cofounders and product teams who need to bridge strategic vision with concrete execution plans.
AGENTS.md-Templates provides ready-to-use templates and best practices for documenting multi-agent AI systems with clear role definitions, capabilities, and collaboration patterns. Developers building multi-agent applications benefit from standardized documentation that ensures reusability and clarity across projects.
A lightweight MCP server that enables AI agents to send real-time progress updates directly to Telegram, supporting text, images, and files. Ideal for developers who want instant notifications from long-running AI tasks without polling or complex integrations.
Agent Chatroom MCP Server enables real-time communication and coordination between parallel Claude Code agents, allowing developers to build collaborative multi-agent systems with synchronized messaging and task distribution.
Enables AI coding agents to control and test Compose Desktop applications via HTTP, automating UI interactions like clicks, text entry, and screenshots. Developers building or testing Compose Desktop apps with AI assistance benefit most.
lucid-toolkit enables developers to quickly reference official Claude Cookbook examples and implementation patterns for common tasks like tool use, agents, and multimodal processing. It's ideal for developers building with Claude who need practical, production-ready code samples.
UltraThink activates a structured single-agent development methodology using linear task execution and TodoWrite planning, designed for developers building Claude-based agents who need organized, step-by-step task management.
This skill helps developers discover and understand all installed plugins by displaying their triggers, commands, and available agents in one place. It's essential for users working with Claude Code who need to explore plugin capabilities without manual searching.
Copilot Instructions for dft-agent provides AI coding agents with concise, actionable guidance on architecture, conventions, and patterns for safely extending a FastAPI-based DFT (Density Functional Theory) workflow system. Developers working on this repository benefit from clear rules on agent routing, tool integration, state management, and workspace organization.
PageFlash provides AI agents and GitHub Copilot with comprehensive WordPress plugin development guidelines covering coding standards, security, accessibility, and best practices to ensure high-quality, standards-compliant plugin code.
A Node.js MCP server that executes JavaScript code safely in isolated Docker containers with on-demand npm dependency installation. Developers and AI agents benefit from secure, sandboxed code execution capabilities integrated into Claude.
A voice-controlled multi-agent framework for spawning and orchestrating AI workers across machines via CLI, SDK, and Telegram. Useful for developers building complex distributed AI workflows.
A comprehensive guide to customizing Orxa agents across three methods—configuration overrides, YAML files, and custom agent creation—enabling developers to adapt agents to specific workflow needs. Ideal for teams using Claude Code or Claude Desktop who need flexible, governance-focused agent customization.
PrismBench enables developers to create specialized LLM agents through YAML configuration for comprehensive benchmarking and evaluation of language model capabilities. Teams building AI evaluation systems and ML testing pipelines benefit from its systematic Monte Carlo Tree Search approach and containerized deployment.
Project: platform-agents is a production deployment initiative for an OSSA v0.3.5-compliant agent registry containing 18 canonical agents for orchestration, analysis, and automation tasks. It enables platform teams to enable agent marketplace revenue and streamline multi-agent deployments across claude_code and claude_desktop environments.
A Model Context Protocol Server facade that simplifies building AI agents by providing a streamlined implementation layer for MCP. Developers building agentic systems with Claude will benefit from reduced complexity in MCP server setup.
Cursor Rules for tonkbook that guide AI agents in building data processing pipelines and workspace structures using the Tonk framework. Useful for developers building conversational data platforms with CLI-driven workflows.
A security-hardened Chrome DevTools Protocol MCP server enabling safe browser automation with post-quantum encryption and credential vault protection. Ideal for developers building AI agents that need secure, automated browser control.
Agent-AI — Copilot Instructions provides Laravel developers with expert guidance for building email agents while maintaining their existing workflows and adhering to Laravel best practices. It benefits Laravel teams using GitHub Copilot who want AI-assisted development with framework-specific conventions.
Clawgram is a photo-first social network designed for AI agents to share images and interact within a secure, sandboxed environment. It benefits AI developers building multi-agent systems that need safe social collaboration features.
A system prompt for automating browser-based tasks using AI agents with Playwright and Gemini, enabling developers to build automated workflows for web interactions like job searches and email management across multiple AI platforms.
