54 boosters for "agentic" — open source, verified from GitHub, ready to install
"description": "Spec-Driven Development: specifications compiled into executable, verifiable behavior", "url": "https://github.com/Dowwie" "homepage": "https://github.com/Dowwie/tasker",
Goals is a Rust-based agentic CLI that enables Claude to delegate isolated tasks to subagents via the `invoke_subagent` tool, keeping the main agent's context lean and focused. Developers building multi-step AI workflows benefit from cleaner task decomposition and reliable single-request subagent execution.
Spotdb is an ephemeral data sandbox for AI workflows that provides secure, isolated database environments for agentic AI systems. It's useful for developers building AI agents and LLM applications that need safe data isolation and guardrails.
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.
"name": "inclusive-design-skills", "description": "Agentic skills for designing accessible, inclusive products — from cognitive accessibility to adaptive interfaces, inclusive research, and accessibility decision-making.", "cognitive-accessibility",
"name": "agentic-jumpstart-marketplace", "name": "Agentic Jumpstart", "email": "webdevcody@gmail.com"
AgentAsJudge is an agentic evaluation framework that enables AI systems to critically review educational introductions by validating them against specified quality metrics and providing constructive feedback. It benefits educators, instructional designers, and developers building AI-assisted learning platforms who need reliable, fair assessment of educational content.
AgentAsJudge is an agentic evaluation framework that enables AI to systematically assess and compare the quality of multiple-choice questions across educational value, clarity, and answerability. It benefits educators, content creators, and assessment teams looking to automate quality control of exam and quiz questions.
"name": "beastmode", "description": "Agentic workflow skills for Claude Code. Activate beastmode.", "version": "0.43.0",
"name": "agent-lint", "description": "Check how well your repo supports AI coding agents.", "homepage": "https://github.com/0xmariowu/agent-lint",
Lár Windsurf Rules is a cursor ruleset that guides developers in building graph-based AI agents using the Lár framework with strict typing, explicit node linking, and auditable patterns. It benefits developers building complex, self-correcting agentic systems who need clear structural guidelines.
"name": "publishing-astro-websites-agentic-skill", "name": "Richard Hightower", "email": "rhightower@spillwave.com"
"name": "north-starr", "description": "Agentic development workflow for Claude Code — skills, agents, and project context from your codebase", "name": "Selcuk Yucel",
"name": "maker-framework", "description": "Massively Decomposed Agentic Processes (MAD) - Break complex tasks into atomic steps with near-zero errors", "name": "MAKER Framework Team",
A migration guide for transitioning from deprecated hardcoded agents to a dynamic ConfigurableAgent system in a Rust-based agentic chatbot server. Developers maintaining or upgrading agent-based systems benefit from clear configuration patterns and best practices for multi-provider LLM setups.
Copilot instructions for the Agentic RAG Demo project that provides context about an Azure-based RAG system with SharePoint integration, helping developers understand the codebase architecture and key components. Developers working on or extending this enterprise document processing system benefit from having immediate project context available.
"name": "abstract-to-concrete-design", "description": "Agentic workflow for designers — from abstract problem space to evidence-based design brief. Research, competitive analysis, and UX critique run in parallel to produce a design brief before you open Figma.", "author": { "name": "rizkiridha", "ur
A debate judge agent that objectively evaluates arguments using zero-sum scoring across Toulmin structure, evidence strength, and logical rigor. Ideal for researchers, educators, and developers building computational debate systems.
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.
"name": "silver-bullet", "description": "Agentic Process Orchestrator for AI-native Software Engineering & DevOps. Combines GSD, Superpowers, Engineering, and Design plugins into enforced 20-step (app) and 24-step (DevOps) workflows with 10-layer technical compliance.", "version": "0.13.2",
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.
SkillGuard is a security reviewer for Claude/Cursor Skills that detects prompt injection, tool injection, data exfiltration, and unsafe automation risks. It's essential for developers and organizations installing or developing AI skills to ensure safe, policy-compliant code execution.
Cursor-Demo provides a comprehensive set of development rules and workflows (SPARC methodology) designed to guide AI-assisted coding in Cursor with emphasis on code quality, security, and structured collaboration between human developers and autonomous agents.
PocketFlow-PHP-Template provides Cursor-specific agentic coding rules to bootstrap rapid PHP development with the PocketFlow framework, ideal for developers building AI-driven applications with structured node-based workflows.
