96 plugins that ship subagents, ranked by GitHub stars gained in 7 days, as of . Together they ship 2,212 subagents.
Design guidance for AI coding agents that helps shape, critique, polish, and improve frontend interfaces such as websites, landing pages, and dashboards. It includes live browser iteration and rules that catch common issues in AI-generated frontend design.
+9,401this week
94.1k stars in total4 subagents
An open-source SEO analysis plugin for Claude Code covering technical SEO, content quality, Schema.org markup, AI search optimization, local SEO and e-commerce, with specialist skills for keyword data, backlinks, image generation and site crawling.
+4,042this week
23.7k stars in total20 subagents
A visual, step-by-step tutorial set that takes Claude Code users from basic use to orchestrating agents, hooks, skills, and MCP servers, with copy-paste templates. It includes a lesson quiz and a self-assessment to gauge skill level.
+3,453this week
46.0k stars in total9 subagents
A Claude Code plugin from ruvnet for WiFi-based sensing, using channel state information to detect presence and vital signs for smart home and edge machine learning work. It adds skills for AgentDB vector search, memory patterns, optimization, and reinforcement learning agents.
+2,336this week
101.4k stars in total94 subagents
Gives Claude Code and Codex a coordination layer so multiple AI agents can split up a task, share memory across sessions, and work together instead of running one at a time. Also covers vector search and reinforcement learning for building agents that remember and improve.
+1,747this week
80.1k stars in total169 subagents
A Claude Code plugin that sets up a game development studio structure, with AI agents for different roles and workflow skills for tasks such as architecture decisions, art direction, asset audits and migration planning. It coordinates the agents in a hierarchy that mirrors a real studio.
+1,490this week
28.6k stars in total49 subagents
Turns a codebase into an interactive knowledge graph you can explore, search, and ask questions about, with skills for diff impact analysis, explanations, and business domain mapping.
+1,246this week
88.8k stars in total10 subagents
Gives Claude Code access to the prompts.chat library, letting you search, retrieve and improve AI prompt templates, and find and install Agent Skills from its registry.
+1,139this week
175.0k stars in total2 subagents
Helps researchers move a project through the academic pipeline, from literature search and citation handling to drafting, reviewing and checking a paper, with you confirming each stage. You stay the author of every claim.
+1,052this week
54.5k stars in total42 subagents
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by running routine tasks, explaining complex code, and handling git workflows through natural language commands.
+990this week
153.8k stars in total14 subagents
Fair-code platform to build and deploy AI agents and workflows. Combine a visual canvas with custom code, run it self-hosted or in the cloud, and connect to 1500+ integrations. AI automation you can trust with real work, from prototype to production.
+686this week
209.0k stars in total9 subagents
Lets Claude Code inspect DBX-managed database connections, explore schemas, run bounded read-only queries, generate DBML or schema docs, and open tables in DBX Desktop.
+614this week
28.2k stars in total6 subagents
Skills for working on Playwright itself, covering development of new APIs and CLI commands, CI failure analysis, cherry-picking to release branches, triaging bug reports, and querying test results. Aimed at Playwright contributors and maintainers.
+532this week
98.8k stars in total7 subagents
Gives developers one set of agents, skills and commands that works across several AI coding tools, with ready-made help for accessibility audits, parallel code review, and debugging competing causes. Each harness gets its own adapted install.
+446this week
42.0k stars in total137 subagents
Gives you a ready Linux desktop setup with Hyprland theming and config, plus help customizing its files, diagnosing program crashes from core dumps, and building new desktop apps for it.
+432this week
45.9k stars in total16 subagents
Helps you build a Claude Managed Agent in your own Anthropic account, guiding you from an interview about its one job through launch, testing against a graded rubric, and running it on a schedule or on events.
+420this week
28.9k stars in total121 subagents
Fetches up-to-date documentation and code examples for libraries, frameworks, SDKs, CLI tools and cloud services, so an AI agent can answer API questions and generate code against current references.
+406this week
63.9k stars in total2 subagents
Breaks a complex task into steps and hands each one to a specialized agent for research, coding, design or unattended automation. It also carries memory across sessions so the working setup can improve itself over time.
+349this week
5.9k stars in total11 subagents
+335this week
35.2k stars in total1 subagent
Plugin for the Cal.com scheduling platform, with skills for its API and webhook signature checks, React and Next.js performance guidelines, and web interface design review.
+287this week
49.5k stars in total95 subagents
Audits paid ad accounts across platforms such as Google, Meta, Amazon, and Apple, plus budget planning and attribution checks. Built for agencies, consultants, and in-house marketing teams using Claude Code.
+256this week
10.6k stars in total25 subagents
Gives you ready-made Copilot agents, instructions and skills for common tasks, such as mapping an unfamiliar codebase or checking a repository's readiness for AI agents, so you start from tested guidance instead of writing prompts yourself.
+247this week
40.5k stars in total200 subagents
A spec-driven development workflow for Claude Code that guides a project through planning, phases, milestone audits and fixes. Includes skills to generate tests from UAT criteria and to audit completed work.
+215this week
11.0k stars in total64 subagents
Configures AI coding agents such as Claude Code, Cursor, and Codex with persistent memory, skills, MCP servers, and personas. Includes skills for writing pull requests, collaboration comments, and design docs.
+196this week
8.1k stars in total11 subagents
A distributed graph issue tracker for AI coding agents, powered by Dolt. It gives agents persistent, structured task memory across sessions, with support for dependencies and blockers.
+187this week
28.3k stars in total10 subagents
Audits a website for Generative Engine Optimization, scoring how likely AI assistants like ChatGPT, Claude, Perplexity and Gemini are to cite its content. Covers AI crawler access, schema markup, brand authority and content quality, with monthly progress comparisons for clients.
+181this week
11.3k stars in total5 subagents
Relay lets Claude Code agents message each other and coordinate work through workflow patterns like fan-out, pipeline, and hub-spoke, instead of copying output between sessions. It also bundles skills for browser testing with screenshots and for creating agents, hooks, and rules.
+164this week
1.1k stars in total39 subagents
Rewrites Korean text that was drafted by an AI so it reads like human writing. It changes only style, rhythm and phrasing, leaving facts, claims and figures untouched. Includes a quick scan and a commit-message variant.
+151this week
6.3k stars in total9 subagents
Gives your AI agent long-term memory that it can search across past sessions, so it recalls earlier context and preferences instead of starting from scratch. Works with DeepSeek Harness and includes a local viewer for browsing what it has stored.
+148this week
12.2k stars in total5 subagents
A lightweight framework for building multi-agent workflows that works with OpenAI's Responses and Chat Completions APIs as well as many other LLM providers.
+146this week
30.4k stars in total5 subagents
Ready-made configurations for Claude Code, with AI agents, custom commands, hooks, MCP integrations, and skills for agent management, agent messaging, documentation search, code graph queries, and memory search.
+138this week
33.0k stars in total200 subagents
Lets you control Claude Code sessions remotely from a mobile app, with end-to-end encryption, push notifications and sync across devices. Open source under the MIT license.
+133this week
24.4k stars in total1 subagent
A Claude Code plugin for long-running web novels that keeps settings, plot threads and outlines consistent across many chapters. It covers project setup, volume and chapter planning, writing-pattern memory, a project health check, and a read-only dashboard.
+131this week
7.7k stars in total4 subagents
Skills, agents and an MCP server for Phoenix, an AI observability tool. Helps build evaluators, run dataset experiments, manage prompts in the playground and query the Phoenix API.
+108this week
12.1k stars in total17 subagents
A Claude Code plugin of skills for writing, scoring, auditing, and localizing blog posts. It covers SEO and E-E-A-T checks, site-wide audits for orphan pages and stale content, brand and voice guides, content briefs, and optional paid text-to-speech audio.
+107this week
2.6k stars in total20 subagents
Indexes a codebase into a knowledge graph of symbols, calls and dependencies, so your coding agent can answer how code works, what a change will break and why a bug happens. Ask in plain language instead of grepping through files.
+99this week
48.1k stars in total7 subagents
A Pi-native shell for controlled development with skills for opening review-sized pull requests, writing clear docs and collaboration comments, and delegating work to focused subagents with test-first habits.
+98this week
1.5k stars in total10 subagents
Skills for building iterated agentic coding loops, designing control loops for a codebase, improving CLAUDE.md instruction files, narrowing React prop types, and running a structured research-plan-implement workflow.
+92this week
5.5k stars in total5 subagents
A toolkit that audits websites for AI search visibility and citability, checking whether ChatGPT, Perplexity, Gemini and Google AI Overviews cite them. Available as a skill, an agent and an MCP server.
+83this week
1.2k stars in total10 subagents
Helps users find NVIDIA NemoClaw documentation for installing, configuring, operating and troubleshooting the open source stack that runs AI agents inside OpenShell sandboxes, and can set up a documentation MCP server.
+82this week
22.9k stars in total1 subagent
Plugin for github/gh-aw, GitHub Agentic Workflows, which lets you write repository automation as markdown workflows that run AI agents in sandboxed GitHub Actions. It includes a Playwright skill for browser automation and web page testing.
+76this week
5.5k stars in total2 subagents
Lets Claude and other AI assistants design KiCAD schematics and PCBs directly, covering circuit capture, board layout and routing, design review checks, part sourcing, and export for manufacturing. It runs as a native KiCAD plugin, so the assistant works inside your existing project.
+75this week
1.4k stars in total2 subagents
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
+72this week
6.2k stars in total31 subagents
Beautiful, fast and modern React UI library. (Previously NextUI)
+71this week
31.1k stars in total5 subagents
A study hub for AI agent engineer job interviews, with interview questions and reference answers, company and role resources, hands-on practice exams, and a structured study roadmap.
+71this week
864 stars in total2 subagents
A set of agents, skills, commands and hooks for Claude Code, covering areas such as accessibility, API design, authentication and AWS cloud patterns.
+59this week
2.8k stars in total138 subagents
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read.
+57this week
6.3k stars in total15 subagents
Runs multiple coding agents in parallel, each in its own git worktree, with support for remote SSH, pull request review and issue ingestion. Works with any provider.
+56this week
6.1k stars in total33 subagents
Runs multi-AI workflows in Claude Code that split research, requirements scoping, implementation and review across several external AI providers, such as Codex, Gemini-style CLIs, Copilot, Ollama and OpenRouter, to cover each model's blind spots.
+51this week
4.3k stars in total49 subagents
An AI native API gateway that routes, proxies and hosts MCP servers for AI traffic, built on Envoy with Wasm plugins and Kubernetes ingress support. Useful for teams running AI services behind a unified gateway.
+45this week
9.7k stars in total3 subagents
A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations.
+42this week
23.2k stars in total8 subagents
Gives you one terminal that shows every running, waiting or finished AI coding agent session across your projects, so you can switch between them with a single keystroke. It also records what each session was for, so you can find and hand off past conversations.
+42this week
1.2k stars in total2 subagents
Archon is a workflow engine for AI coding that runs repeatable YAML-defined workflows on a git repo, with tools to inspect, approve, cancel and resume runs. It also ships skills for browser testing, release creation and rule checking.
+38this week
23.8k stars in total13 subagents
Runs structured deliberation across several reasoning perspectives, so a user can weigh a hard decision from multiple angles before settling on one path.
+37this week
4.7k stars in total18 subagents
A structured research workflow for Claude Code. It builds a research outline for a topic, adds items and fields to it, runs a deep research agent per item, and summarizes the results into a markdown report.
+37this week
2.4k stars in total7 subagents
Marketing skills for Claude Code that audit a website, write and score copy, build email sequences and content calendars, analyze competitors, and produce client-ready PDF reports from the terminal.
+36this week
2.8k stars in total5 subagents
Offline credential import: shunt import opencodex --dry-run previews compatible API keys and Cursor/Command Code access tokens. Exports create new private snapshots without changing existing settings or copying refresh tokens. See credential import.
+34this week
385 stars in total16 subagents
Turns a rough feature idea into a written spec through guided questions, then has the agent build it and checks the result against that spec. Instead of hand-checking whether the work is finished, you get an automatic evaluation gate that runs in your coding agent.
+33this week
6.3k stars in total22 subagents
A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.
+32this week
306 stars in total20 subagents
PYA (Protect Your Ass): security audit plugin for Claude Code. 9 specialist agents, a dated threat feed, verified findings, offline by default.
+28this week
265 stars in total10 subagents
Runs SEO audits on websites, blog posts, and GitHub repositories, covering technical SEO and content checks. Built for users of Claude Code and other AI coding assistants who want repeatable, evidence-based audit results.
+26this week
1.0k stars in total10 subagents
Gives sales teams AI-driven help inside Claude Code: researching prospects, qualifying leads with BANT and MEDDIC, finding decision makers, writing outreach and follow-up sequences, and drafting objection responses and competitor battle cards.
+24this week
1.5k stars in total5 subagents
An Android app that runs as an MCP server, letting AI models remotely control an Android device through accessibility services and screenshot capture.
+24this week
760 stars in total2 subagents
A Claude Code plugin that generates, edits, and compares images with current Google Gemini image models. It covers product and character visuals, reference-based consistency, and text in images, with prompt guidance from a creative director skill.
+23this week
1.1k stars in total2 subagents
Lets developers run several AI coding agents in parallel, each in its own git worktree, across multiple projects and chat sessions, on a laptop or your own server.
+22this week
1.4k stars in total5 subagents
Helps you write novels, short stories and serial fiction. It drafts scenes in your own voice, tracks continuity across the story, and gives you structured critique and simulated reader reactions before you revise.
+22this week
550 stars in total11 subagents
AI trading research engine for Claude Code. Analyze stocks (technical, fundamental, sentiment, risk, thesis), options strategies, sector rotation, portfolio analysis, and PDF reports. 16 skills, 5 parallel agents. Research tool only, not financial advice.
+21this week
296 stars in total5 subagents
Turn any business idea into a complete, sellable offer, using Alex Hormozi's frameworks. A skill library for coding agents.
+21this week
254 stars in total6 subagents
Hands penetration testing work to specialist subagents for recon, web and network testing, exploit development and security audits, and returns structured findings you can act on without running each tool yourself.
+19this week
2.4k stars in total52 subagents
A Claude Code plugin marketplace offering agent-based tools for development workflows, code analysis, code comparison, and code grading, plus skills for research, content, and residential floor plan searches.
+19this week
1.5k stars in total3 subagents
Claude Code plugin with skills, agents, commands and MCP servers for orchestrating coding-agent CLIs, auditing plans against implementations, managing MCP servers, and running CSS design-token checks.
+19this week
881 stars in total6 subagents
A bug bounty agent framework for Claude Code that automates reconnaissance, vulnerability hunting and exploit chaining, with skills for analyzing recon output, running autonomous hunt loops and correlating findings into attack chains.
+18this week
1.0k stars in total50 subagents
Gives Claude ready-made workflows for everyday office work such as contracts, invoices, proposals, HR documents, reports, presentations and emails, so you skip writing the instructions yourself. Covers data analysis and document processing too.
+18this week
548 stars in total1 subagent
A multi-agent orchestration system that coordinates specialized AI agents through a real-time Kanban dashboard, with workflow approval, model configuration and full audit trails.
+16this week
17.0k stars in total4 subagents
An open-source desktop AI agent for data analysis, slide and document creation, video and web research, and scheduled tasks. It runs tools on your computer and accepts commands from your phone through WeChat, Feishu, DingTalk, or Telegram.
+16this week
6.2k stars in total3 subagents
Browse, search, and analyze past conversations from Claude Code and other AI coding assistants such as Gemini CLI, Codex CLI, Cursor, and Aider. Available as a desktop app or a headless server.
+16this week
2.3k stars in total9 subagents
Agent skills for building with ElevenLabs developer products, covering voice agent configuration, outbound calls, widget embedding and the procedure API. Works with any AI coding assistant that supports the Agent Skills specification.
+16this week
517 stars in total7 subagents
A Claude Code plugin that runs a team of agents to help you write a novel, from worldbuilding and character design to chapter planning and drafting. It works for starting a new novel or importing one already in progress.
+15this week
848 stars in total19 subagents
Lets an AI agent drive a local Firefox browser to read pages, fill forms and walk through multi-step website flows. It can also open the page you are building and inspect its console, network requests and performance so you can debug it without leaving your chat.
+15this week
529 stars in total2 subagents
Gives a codebase and a grader to a team of autonomous coding agents that run experiments in isolated workspaces, share notes, and keep improving the solution, so you do not manage each run by hand.
+13this week
1.1k stars in total4 subagents
Writ turns supported workflow requirements into executable checks and acceptance gates for Claude Code, instead of relying on the model to follow written instructions.
+13this week
243 stars in total5 subagents
Skills for analyzing and comparing Xcode builds, test runs, app bundles and cache runs with Tuist, including selective testing and cache invalidation diagnosis. Useful for iOS developers tracking build regressions.
+12this week
5.9k stars in total40 subagents
Reviews contracts, generates NDAs and business agreements, flags missing clauses, compares contract versions, and audits websites for compliance gaps, with PDF reports for Claude Code users doing legal work.
+12this week
1.8k stars in total5 subagents
A collection of agents for academic writing, covering peer review, literature review and paper revision. It grew out of the author's own paper-writing workflow.
+12this week
525 stars in total21 subagents
Mirrors the visual style of a reference paper figure onto your own data. Give it messy data and a figure screenshot, and it produces a matching plot for scientific papers.
+11this week
551 stars in total5 subagents
Zenith is an agent harness for long-running work that may last days or weeks, with skills for browser-based user-flow validation, benchmark and scrutiny validation, and mission playbooks for engineering and optimization tasks.
+11this week
384 stars in total4 subagents
Autonomous coding agent that turns a task or issue into a pull request and checks it against the repo's tests. Its loki-seal skill blocks declaring a task done while tests newly fail or test or CI config was deleted.
+10this week
1.1k stars in total3 subagents
Gives your coding agent skills to author, maintain, validate and visualize Open Knowledge Format bundles, portable markdown knowledge that both your team and your agents can read. Includes a backfill skill for building a bundle from an existing repository's git history and session transcripts.
+10this week
433 stars in total2 subagents
Security skills for auditing Solidity smart contracts, built by Pashov Audit Group. Includes tools to convert English properties into fuzz test assertions and to reconcile a fuzz harness with a changed source tree.
+9this week
1.3k stars in total10 subagents
Gives coding agents ready-made workflows for full stack work, from front end and back end to mobile, DevOps and design-to-code, so common tasks follow proven steps instead of being built from scratch.
+9this week
717 stars in total2 subagents
A Claude Code plugin that interviews you about what to build, designs the architecture, and writes a self-contained blueprint another Claude Code instance can build from with no prior context. Each build step includes acceptance criteria and a verify command.
+9this week
568 stars in total3 subagents
Gives Claude Code and other AI coding agents a design system, with skills for applying brand context, fetching free placeholder assets, and critiquing UI quality. Free and open source under the MIT license.
+9this week
551 stars in total21 subagents
Build responsive, accessible UI with Chakra UI, migrate projects from the previous major version, and refactor plain HTML, Tailwind, CSS Modules or styled-components code into Chakra components and themes.
+8this week
40.7k stars in total2 subagents
Gives AI agents a way to connect to outside tools and services through MCP servers, so they can act on your accounts and data without you wiring each integration by hand. Also includes a documentation lookup skill that answers questions about libraries and frameworks with code examples.
+8this week
5.8k stars in total1 subagent
A Claude Code plugin for developing and maintaining module-federation/core in the style of its original designer, covering plugin architecture, container and sharing, runtime, caching, and reviews. Built for developers working on Module Federation.
+8this week
2.7k stars in total2 subagents
GSD Pi is a local-first coding agent for planning, implementing, verifying, and tracking project work from the command line.
+8this week
1.3k stars in total13 subagents
Nothing in this list is paid.
