1,054 boosters for "agent" — open source, verified from GitHub, ready to install
An agent that automates end-to-end testing tasks with library-first constraints, helping teams execute comprehensive test scenarios while reusing existing components and patterns. Useful for QA engineers and developers integrating testing into their Claude-powered workflows.
A technical-debt-manager agent that helps teams identify, track, and manage technical debt across projects using library-first principles and reusable patterns. Developers working in Claude Code or Claude Desktop environments benefit from automated technical debt assessment and refactoring guidance.
A Claude agent specialist designed to assist with stakeholder communication tasks across enterprise projects. Helps teams manage and streamline interactions with multiple stakeholders using library-first patterns and reusable components.
A topology-optimizer agent that enforces library-first development practices by checking existing components and patterns before generating new code. Useful for teams implementing reusable, standardized agent workflows across projects.
An agent designed to evaluate other agents and tasks, with library-first constraints and multi-tool integration across Claude platforms. Useful for teams building quality assurance workflows into their Claude-based systems.
An autonomous coding agent that delegates tasks to Codex CLI with configurable risk modes (full-auto, sandbox, YOLO) to iteratively debug and test code until it passes. Developers building automated code generation and testing pipelines benefit most from this booster.
A risk-manager agent designed to assist with financial risk assessment and management tasks across Claude Code and Claude Desktop platforms. Useful for finance teams and developers building risk analysis workflows.
A Claude agent designed to facilitate database migrations across projects by automating code search, adaptation, and execution tasks. Developers managing schema changes and data transfers benefit from its library-first approach and integrated bash capabilities.
A coding agent that enforces library-first development by searching existing components and patterns before building new code, helping teams reuse and standardize implementations across projects.
An ethics-focused agent designed for research tasks that enforces library-first development patterns and component reuse across Claude projects.
An agent that generates architecture diagrams by leveraging Claude's code execution capabilities and a library-first approach to reuse existing components and patterns. Useful for developers and architects who need to quickly create system architecture visualizations.
tdd-london-swarm is an agent that enforces test-driven development practices with a library-first constraint, helping teams reuse existing components and patterns before writing new code. It benefits development teams adopting TDD methodologies who want to maintain code consistency and reduce duplication.
"name": "a2asearch-mcp", "mcpName": "io.github.tadas-github/a2asearch-mcp", "description": "MCP server for searching and discovering AI agents, MCP servers, CLI tools and agent skills via A2ASearch",
A CLI tool for orchestrating AI agents at scale to analyze code repositories, manage GitHub collaborators, and conduct bulk research across multiple data sources including Notion and CSV. Ideal for developers and teams automating large-scale code analysis, data processing, and repository management tasks.
Automates creating and merging pull requests with validation checks, allowing developers to ship code changes without leaving their IDE. Essential for teams using GitHub and automated CI/CD workflows.
"name": "everything-claude-code", "description": "Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use", "name": "Affaan Mustafa",
"description": "ODIN (Outline Driven INtelligence) - Advanced code agent with 46 specialized agents, diagram-first engineering, and atomic commit workflows for surgical precision in software development", "name": "cognitive-glitch" "license": "Apache-2.0",
BioMCP is an MCP server enabling agent-based biomedical research and development through Claude integration. It benefits biomedical researchers and developers automating computational biology workflows.
"description": "A curated collection of AI coding agent skills for browser automation, frontend design, performance auditing, task tracking, and structured problem-solving workflows.", "repository": "https://github.com/wunki/amplify", "browser-automation",
"description": "Spec-Driven Development: specifications compiled into executable, verifiable behavior", "url": "https://github.com/Dowwie" "homepage": "https://github.com/Dowwie/tasker",
Docs & Links automates documentation consistency checks, Markdown linting, and link validation to keep repository documentation in sync with actual code. Teams managing multiple projects benefit from automated enforcement of documentation quality standards.
Agentic MCP enables AI assistants to interact with MCP servers through socket-based communication, allowing discovery and execution of external tools with progressive disclosure. Developers and AI builders benefit by gaining structured access to MCP server capabilities without manual integration.
Skill-Based Agents provides documentation for 6 autonomous agent skills (archon-manager, framework-orchestrator, multi-agent-architect, codex-review-workflow, design-system-architect, security-architect) that handle strategic coordination, orchestration, and governance across projects. Developers building multi-agent systems or requiring automated governance workflows benefit from understanding these reusable agent patterns.
"description": "AI application security for Claude — generate an AI Bill of Materials (AI-SBOM), run static analysis, behavioral validation, and adversarial red-team testing for AI agents and LLM-powered applications.", "email": "info@nuguard.ai", "url": "https://nuguard.ai"
