The 5 Best Claude Code Marketplace Alternatives in 2026

The Claude Code Marketplace is Anthropic's built-in system for discovering and installing plugins, which are packages that can bundle skills, agents, hooks, MCP servers, slash commands, and LSP servers. Anthropic's docs say the official marketplace (claude-plugins-official) is automatically available when you start Claude Code, so there's nothing to set up: you run /plugin, browse the Discover tab, and install. Before plugins existed, teams shared scattered CLAUDE.md files, hook scripts, and MCP configs by hand; the marketplace turned all of that into installable packages. The official directory is Anthropic-managed and quality-focused, and third-party marketplaces can be added with a single command (/plugin marketplace add owner/repo-name). It's the path of least resistance if you already pay for Claude Code, but it's Claude-only, and it curates rather than verifies: you get Anthropic's editorial judgment, not per-skill security scans or measured performance data.

pricing 20/month

• + Zero setup: the official marketplace is available the moment you start Claude Code
• + Anthropic-managed official directory focused on quality (32k stars)
• + Plugin packaging replaces scattered CLAUDE.md files, hook scripts and MCP configs
• + LSP plugins add jump-to-definition, references, diagnostics and type-error awareness

• − Requires a paid Claude Code plan; heavy agent use pushes you toward $100-$200/month Max tiers
• − Claude Code only; nothing here transfers to Codex, Cursor or Gemini CLI
• − Curated listings, not verified ones: no per-skill security scans or benchmark results
• − Installing many MCP-loading plugins can choke the LLM context window

https://code.claude.com/docs/en/discover-plugins

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. Its premise is simple: SKILL.md instruction packages for Claude Code, Codex, Cursor, Gemini CLI and chat-app agents are everywhere, but nobody could tell which ones actually help and which are risky, and published research found roughly 26% of skills carry at least one vulnerability. SkillzBench runs five pillars: it continuously crawls and dedupes skills from GitHub (Discover), pins every version to a commit SHA and runs validation, license checks, security scans and quality judging (Verify), tests every skill in a sandbox with the same model with and without the skill and publishes the Lift in percentage points (Benchmark), offers one free MCP server plus per-agent loadouts where the agent only sees what you toggled on (Equip), and tracks upstream changes with re-scans, re-benchmarks and notifications. A 0-100 trust score combines security, quality, license, maintenance and community signals, with Lift always shown separately and money never touching scores. Everything is free, funded by ads around its blog articles.

pricing 0

• + Everything is free, and ad revenue never influences scores or listings
• + Security scanning addresses the ~26% of skills found to carry at least one vulnerability
• + Lift benchmarks show measured impact, not just a rating
• + Works across Claude Code, Codex, Cursor, Gemini CLI and chat-app agents through one free MCP server
• + Per-agent loadouts limit what each agent can see, a real context-window and safety win

• − It's a separate destination rather than something built into your editor
• − Smaller catalog than the biggest community mega-collections
• − Benchmark results depend on the model used, so your mileage can differ

https://skillzbench.com

Awesome Claude Plugins is Composio's curated, open-source marketplace for Claude Code plugins, addable directly with /plugin marketplace add owner/repo-name or by cloning the GitHub repo. Composio is an established developer-tools company, and the collection leans into integrations: its Connect MCP lets Claude Code securely access apps like Jira, Linear, GitHub and more from a single MCP server. The repo sits alongside Composio's broader Claude Code plugin guide, which walks through LSP plugins, MCP integration plugins, code review plugins and security plugins by category. It's a strong second stop after the official marketplace, especially if your work starts from tickets, PRs and external services. The trade-off is the same one that applies to most community lists: curation by a trusted maintainer, but no per-skill security scanning, version pinning or measured benchmark data.

pricing See pricing

• + Maintained by Composio, a known developer-tools vendor
• + Strong integration focus (Jira, Linear, GitHub, Slack, Vercel, Sentry, Supabase)
• + Dynamic tool loading addresses the context-window problem of stacking MCPs

• − No per-skill security scanning or benchmarking
• − Claude Code focused
• − Quality depends on the maintainer's editorial judgment

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

This is Anthropic's own GitHub repository backing the built-in marketplace, described as the official, Anthropic-managed directory of high-quality Claude Code plugins, with about 32k GitHub stars. It covers skills, agents, commands, hooks and LSPs, and it's the directory your /plugin Discover tab reads from by default. Because Anthropic maintains it, the bar for inclusion is higher than on community mega-repos, and it's the safest default when you want a plugin that just works with Claude Code's update cycle (a /plugin marketplace update command refreshes it). Anthropic also publishes a separate Knowledge Work Plugins repository aimed at knowledge workers in Claude Cowork, showing the official ecosystem extends beyond pure coding. The limits are structural: it's deliberately a quality-first, smaller set, it only serves Claude Code, and it doesn't publish security scan results or performance benchmarks for individual plugins.

pricing See pricing

• + Highest-trust curation available, straight from Anthropic
• + Zero setup inside Claude Code
• + Refreshable so new official plugins appear without reconfiguration

• − Smaller, quality-first selection versus community collections
• − Claude Code only
• − No published per-plugin security scans or benchmarks

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

Buildwithclaude, by davepoon, is a single hub for finding Claude Skills, Agents, Commands, Hooks, Plugins and Marketplace collections, covering Claude Code, Claude Desktop, the Agent SDK and OpenClaw. At roughly 3.2k GitHub stars it's a mid-sized collection, but its value is breadth of resource types in one place: if you're setting up a Claude-powered workspace and need a hook here, a skill there and a marketplace to browse, this saves you hopping between repos. It's community-maintained rather than vendor-backed, so expect the usual variance in individual item quality and no published vetting. For small teams exploring the Claude ecosystem beyond the editor itself, especially Claude Desktop and the Agent SDK, it's one of the more complete maps available.

pricing See pricing

• + Broad coverage of resource types in one place
• + Extends beyond Claude Code to Desktop and the Agent SDK
• + Simple to browse

• − No security scanning or benchmarking
• − Smaller community than the mega-collections
• − Aggregator model means uneven item quality

https://github.com/davepoon/buildwithclaude

This collection packs 345 Claude Code skills and agent skills into one repo: 30+ agents, 70+ custom commands, 330+ skills, plus customizable references and scripts. What sets it apart is functional breadth beyond engineering. Skills are organized for marketing, product, compliance, C-level advisory, research, business operations, commercial and finance, and daily productivity, alongside the usual coding categories. It explicitly supports Claude Code, Codex, Gemini CLI, Cursor and 8 more coding agents, which makes it one of the more portable collections on this list. At about 22k stars it's well established. The catch is the same as any mega-collection: with hundreds of items, individual quality and safety vary, and there's no per-skill security scanning or benchmarking to tell you which of the 345 actually pull their weight.

pricing See pricing

• + Rare breadth outside engineering: marketing, compliance, finance and operations skills
• + Cross-agent support across 12+ coding agents
• + Large, active community (22k stars)

• − No per-skill security scanning or benchmarking
• − Volume makes finding the right skill slow
• − Quality varies across 345 items

https://github.com/alirezarezvani/claude-skills

Maintained by jeremylongshore, this is one of the largest collections available: 425 plugins, 2,810 skills and 200 agents for Claude Code, backed by an open-source marketplace at tonsofskills.com and its own ccpi CLI package manager. At about 2.5k stars it's a smaller community than the mega-repos, but the raw inventory dwarfs most alternatives, and the ccpi CLI gives you a package-manager workflow for installing rather than manual repo browsing. If your goal is to experiment widely and cheaply, this is the buffet. The downside is inherent to scale without vetting: with 2,810 skills and no published security scans, version pinning or benchmark data, you're on your own to figure out what's safe and what actually helps, which matters given research showing roughly 26% of skills carry at least one vulnerability.

pricing See pricing

• + Enormous inventory: 2,810 skills and 200 agents
• + Own CLI package manager streamlines installation
• + Free and open source

• − No security scanning, version pinning or benchmarks
• − Uneven quality at this scale
• − Primarily Claude Code focused

https://github.com/jeremylongshore/claude-code-plugins-plus-skills