953 boosters for "agent" — open source, verified from GitHub, ready to install
"description": "Parallel agent infrastructure for Claude Code. Modeled after the OS process model, it distributes, monitors, and reaps issues via independent Workers.", "name": "clonable-eden" "repository": "https://github.com/clonable-eden/cekernel",
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.
A Windsurf-specific coding guidelines booster that enforces Python best practices including documentation standards, absolute imports, early returns, and design patterns for maintainable code. Ideal for Python developers using Windsurf who want to maintain consistent code quality across their projects.
"description": "LLM observability tooling for agent development and Claude Code", "url": "https://comet.com" "repository": "https://github.com/comet-ml/opik-claude-plugin",
Agent-studio provides structured self-reflection patterns to help AI agents validate their reasoning and decisions. It's useful for developers building agent systems who need built-in verification and structured thinking frameworks.
agent-studio invokes architecture-review validation to help developers identify design flaws and anti-patterns in their code. It's useful for architects and senior engineers seeking automated design feedback.
"name": "super-publisher", "description": "Super Publisher plugin for automated content publishing, multi-platform support.", "email": "guanyangsunlight@gmail.com",
"description": "Turn agent answers into self-contained HTML artifacts and presentation decks (htmlify + deckify skills, plus an optional long-answer Stop hook).", "name": "Zak El Fassi", "url": "https://github.com/zakelfassi"
"name": "beastmode", "description": "Agentic workflow skills for Claude Code. Activate beastmode.", "version": "0.43.0",
"description": "Dual-scope knowledge base for LLM workflows with hybrid full-text + semantic search, typed relations, and publishing.",
A technical decision-making agent that researches latest specifications and documentation to inform design and configuration choices during development. Developers benefit from automated best-practice guidance based on current standards rather than static knowledge.
"description": "Full-stack development team orchestrator: 8 specialized agents with 11 Superpowers framework skills for automated workflow from requirements to deployment. 🆕 v6.6.0: Complete workflow automation with auto/interactive modes, Git worktree for seamless project creation, and Callstack R
A specialized documentation agent for the Statifier SCXML library that leverages the Diataxis framework to create and manage tutorials, guides, references, and explanations. Ideal for developers maintaining technical documentation or building documentation systems for state machine libraries.
  <!-- upstream-badges-start -->
"name": "git-workflow", "version": "1.12.0", "description": "Git workflow best practices with commit validation hooks",
"version": "5.10.0", "description": "Memory → Evaluation → Credential → Access Control for AI agents. Persistent memory with W3C Verifiable Credentials, capability-based access control, drift detection, and FSRS-6 spaced repetition.", "name": "kobie3717",
"name": "cms-cultivator", "description": "14 specialist agents + 24 commands + 14 skills for Drupal/WordPress. Agents orchestrate comprehensive quality checks with parallel execution. Design-to-code workflows with browser validation. CSV export for PM tools. Drupal.org contribution integration. Drup
"name": "claude-swe-workflows", "description": "Software engineering workflow with deliberation, planning, implementation, and quality skills plus specialist agents", "name": "Chris Allen Lane"
Real Browser MCP enables AI agents to control and automate real Chrome browser sessions with existing logins and state, eliminating the need to re-authenticate or recreate context. Developers building AI coding assistants and autonomous agents benefit from seamless browser automation with full session persistence.
"description": "Agent identity framework - don masques to adopt temporary cognitive identities"
Heuristic scoring (no AI key configured).
A Cursor-specific agent rule that automatically creates code snapshots after each diff, helping developers track and review code changes in real-time. Developers using Cursor for version control and change tracking would benefit from automated snapshot management.
"name": "nonstop-agent", "description": "Generate 24/7 autonomous coding agents with Anthropic best practices", "name": "seolcoding"
Launches a ShadCN UI builder agent to help developers design and implement modern interfaces using the ShadCN component library. Useful for frontend developers and UI designers working with Claude Code.
