The 5 Best Claude Code Marketplace Alternatives in 2026

The Claude Code Marketplace is Anthropic's official way to discover and install plugins for Claude Code. Anthropic describes plugins as bundles that can include skills, agents, hooks, MCP servers, and other capabilities, and the marketplace lets you install those extensions without building them yourself. The official marketplace, claude-plugins-official, is automatically available when you start Claude Code: you run /plugin, browse the Discover tab, or install directly with /plugin install. If a plugin is missing you refresh with /plugin marketplace update. Third-party marketplaces can be added too. The catch for small businesses is the underlying cost: Claude Code has no free tier, Pro is $20/month and gets tight with heavy agent use, and sustained use pushes you toward $100 or $200/month Max tiers. It also locks you into Anthropic's models and a terminal-first workflow.

pricing 20/month

• + Official, Anthropic-managed directory of high quality Claude Code plugins
• + Automatically available inside Claude Code with no extra setup
• + Rich plugin model covering skills, agents, hooks, MCP servers, and LSPs
• + Simple install flow: /plugin install from the Discover tab

• − No free tier for Claude Code; Pro is $20/month and heavy use pushes to $100 or $200/month Max plans
• − Locked to Anthropic's models and a terminal-first workflow
• − Rate limits during peak hours frustrate heavy users
• − No independent security scanning or benchmarking of plugins

https://github.com/anthropics/claude-plugins-official

SkillzBench is AIQ Labs' free, independent directory of AI agent skills, plus a free MCP tool that connects any agent to the skills you choose. Agent skills (SKILL.md instruction packages for Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents) are everywhere, but nobody can tell which ones actually help and which are risky: published research found roughly 26% of skills carry at least one vulnerability. SkillzBench continuously crawls and dedupes skills from GitHub, pins every version to a commit SHA, validates, license-checks, security-scans, and quality-judges each one. It then benchmarks every skill in a sandbox with the same model, with and without the skill, and publishes the Lift in percentage points. A trust score from 0 to 100 combines security, quality, license, maintenance, and community signals, and Lift is always shown separately from ratings. Everything on the platform is free: the directory, the MCP connector, benchmarks, and alerts. Revenue comes from advertising around blog articles, and ad money never influences scores or listings.

pricing 0

• + Everything is free: directory, MCP connector, benchmarks, and alerts
• + Independent verification: security scans, license checks, and commit-SHA pinning on every skill
• + Published Lift benchmarks show whether a skill actually helps, separately from ratings
• + Works across Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents
• + Per-agent loadouts stop context bloat by exposing only chosen skills and tools
• + Money never touches scores; revenue is advertising only

• − It's a skills layer, not a plugin marketplace with hooks, commands, and LSP bundles
• − As an independent directory, it doesn't replace Claude Code's official plugin install flow
• − Trust scores and Lift help you choose, but you still install and run skills in your own agent

https://skillzbench.com

Awesome Claude Plugins is Composio's free, open-source third-party marketplace: a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code. You add it with /plugin marketplace add or clone the repo directly, and it includes Composio Connect MCP, which lets Claude Code securely access apps like Jira, Linear, and GitHub from a single MCP. The collection sits inside a broader ecosystem the Composio guide covers: LSP plugins for TypeScript, Python, Rust, and Go; MCP integration plugins for GitHub, Linear, Slack, Vercel, Sentry, and Supabase; code review plugins; and security plugins like Security Guidance and Semgrep. The guide's honest caveat applies to any MCP-heavy setup: installing many MCP servers at once loads all their tools into the context window and can choke it. Composio's answer is dynamic tool loading, loading tools only as context requires.

pricing See pricing

• + Free and open source
• + Bundles Composio Connect MCP so one MCP covers many apps
• + Dynamic tool loading addresses the context-window bloat of multiple MCP servers
• + Part of a well-documented ecosystem covering LSP, review, and security plugins

• − Community curation only; no security scanning or benchmarking of listed plugins
• − MCP-heavy setups can still choke the context window if you install many servers
• − Claude Code focused, so you still pay for Claude Code itself

https://github.com/composiohq/awesome-claude-plugins

Claude Plugins Official is Anthropic's own managed repository of high quality Claude Code plugins, listed with 32k stars in community tracking. It's the same official marketplace that's automatically available when you start Claude Code, covering skills, agents, commands, hooks, and LSPs. Anthropic also maintains adjacent repos like Knowledge Work Plugins, intended for knowledge workers in Claude Cowork, which matters for small businesses using AI beyond pure coding. Because it's Anthropic-managed, quality is curated by the vendor itself, which is a real signal but not independent verification. If a plugin seems missing you refresh with /plugin marketplace update claude-plugins-official. For teams fully inside the Claude ecosystem, this is the default source; for teams wanting cross-agent skills or third-party vetting, it's the starting catalog rather than the whole picture.

pricing See pricing

• + Vendor-managed quality curation from Anthropic itself
• + Zero setup: automatically available when Claude Code starts
• + Broad capability coverage including LSPs
• + Companion repos extend it to knowledge-work use cases

• − Claude Code only; skills don't port to Codex, Cursor, or Gemini CLI
• − No independent security scanning or performance benchmarks
• − Quality is Anthropic's own judgment, not third-party verified

https://github.com/anthropics/claude-plugins-official

The Superpowers Marketplace is a curated Claude Code plugin marketplace maintained by obra, listed with 1.1k stars in community tracking. It's a leaner, opinionated collection of commands, MCPs, and skills, installable through the standard /plugin marketplace add flow. Its appeal is curation with a point of view: rather than trying to catalog everything, it surfaces a smaller set of plugins the maintainer actually endorses. That's also its limitation. One person's curation is not a security review, and there's no sandboxed benchmarking to tell you whether a plugin measurably improves your agent's output. For a small business, it works well as a second marketplace alongside the official one, adding hand-picked workflow plugins without much overhead. It won't tell you which skills are risky, and it won't help if your team runs agents other than Claude Code.

pricing See pricing

• + Free and lightweight to add alongside the official marketplace
• + Opinionated curation means less noise to sift through
• + Standard install flow, no new tooling to learn

• − Single-maintainer curation, not systematic vetting
• − No security scanning or benchmarks
• − Small catalog compared to the official or community mega-collections

https://github.com/obra/superpowers-marketplace

Claude Code Plugins Plus Skills is an open-source marketplace by jeremylongshore, listed with 2.5k stars in community tracking, offering 425 plugins, 2,810 skills, and 200 agents for Claude Code through tonsofskills.com, plus a ccpi CLI package manager for installation. It's the volume play among the alternatives: if the official marketplace and smaller curated collections don't have what you need, this catalog probably does, spanning engineering, marketing, product, and business-operations territory. The trade-off is exactly what you'd expect from a mega-collection. Volume is not vetting. With thousands of skills from many sources, there's no systematic security scanning, license checking, or benchmarking to tell you which entries actually help and which are risky, which matters given published research finding roughly 26% of skills carry at least one vulnerability. Treat it as a discovery source, then verify what you find before deploying it to a business agent.

pricing See pricing

• + Free and open source
• + Huge catalog: 425 plugins, 2,810 skills, 200 agents
• + Dedicated ccpi CLI for package management
• + Spans business and productivity skills, not just engineering

• − Volume over vetting: no systematic security scanning or quality benchmarks
• − More noise to sift through than curated collections
• − Claude Code focused, and you still pay for Claude Code itself

https://tonsofskills.com