763 boosters for "agent" — AI-graded, open source, ready to install
lucid-toolkit provides guidance for efficient multi-agent coordination using schema.org vocabulary and token budget optimization, helping developers structure complex subagent invocations on Claude Code. Best for teams managing resource-constrained agentic 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.
Scout is a specialized agent that rapidly locates relevant files across large codebases using parallel search strategies, helping developers navigate complex projects during feature development, debugging, and refactoring tasks.
Covalt provides Cursor-specific coding rules inspired by tinygrad principles, guiding developers to write clean, composable, and maintainable code through practical patterns like small functions, context managers, and helper extraction.
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.
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.
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 code review agent that validates TypeScript projects against internal conventions, including vendor encapsulation, test patterns, and permission decorators. Useful for teams maintaining strict code quality standards across AWS Lambda and infrastructure projects.
The ops agent automates infrastructure management, deployment, and cloud operations for DevOps teams. Developers and DevOps engineers use it to streamline CI/CD pipelines, monitor systems, and maintain production reliability.
BMAD — Cursor Rules is a developer agent system that activates via @dev commands to organize tasks, templates, and checklists through a file resolution system. It helps Cursor IDE users structure and automate development workflows using persona-based agent activation.
QA agent that generates pytest tests and improves test coverage for da_vinci packages, helping developers ensure code quality and reduce manual testing effort.
A production-ready Python development agent that enforces PEP 8 standards, type hints, design patterns, and security best practices across projects. Developers building Python applications benefit from automated guidance on code quality and maintainability.
A QA Engineer agent that creates and validates comprehensive test suites with structured coverage analysis, prioritized test case identification, and enforced quality gates. Developers and QA teams benefit from automated test scaffolding and coverage verification across projects.
Augure is a proactive AI agent MCP server that integrates with Claude Desktop and Claude Code, enabling automation through Telegram, email, Docker, and scheduled tasks. It's designed for developers and power users who need an intelligent agent to automate workflows and manage integrations across multiple platforms.
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.
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.
Jules is a comprehensive system prompt that transforms Claude/Gemini into an architecture-aware code completion agent capable of multi-file synchronization, schema coherence, and full-stack refactoring. It's designed for developers using Claude Code, Cursor, Windsurf, and similar platforms who need intelligent, cross-file code generation with architectural consistency.
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.
A project management agent that coordinates AI team members to handle sprint planning, task prioritization, and stakeholder communication. Useful for teams looking to automate PM workflows with AI agents.
Node Code Sandbox MCP enables AI agents and LLMs to safely execute JavaScript code, install npm packages, and test implementations in real-time. Developers building coding assistants, automated testing tools, and interactive AI applications benefit from this secure, MCP-compliant execution environment.
A governance skill that automates code review and standards enforcement through delegated agent execution, delivering 70-90% token savings for engineering teams managing code quality at scale.
