The 5 Best Claude Code Marketplace Alternatives in 2026

Anthropic's official plugin marketplace for Claude Code, available automatically when you start the tool. Anthropic describes plugins as bundles that can include skills, agents, hooks, MCP servers, and other capabilities, and the marketplace lets you discover and install those extensions without building them yourself. You browse it in Claude Code with /plugin, install directly with /plugin install, and refresh it with /plugin marketplace update. Before plugins existed, teams shared scattered CLAUDE.md files, hook scripts, and MCP configs; the marketplace makes those pieces installable and shareable. The official repo (anthropics/claude-plugins-official) is described as an Anthropic-managed directory of high quality Claude Code plugins, covering skills, agents, commands, hooks, and LSP servers. It's the convenience default, but it doesn't publish per-plugin security scans or performance benchmarks.

pricing See pricing

• + Zero setup: the official marketplace is automatically available when you start Claude Code.
• + Official Anthropic curation, described as a directory of high quality plugins.
• + Covers the full extension surface: skills, agents, commands, hooks, and LSPs.
• + Standardized install flow that also supports adding third-party marketplaces.

• − No published security scanning or vulnerability data for listed plugins.
• − No performance benchmarks showing whether a plugin actually improves agent output.
• − Smaller than community collections; the official repo shows 32k stars against 229k for the largest community collection.
• − Anthropic-ecosystem only; it doesn't help you vet skills for Codex, Cursor, or other agents.

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 and license-checks each one, security-scans it, and quality-judges it. 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 0-100 trust score combines security, quality, license, maintenance, and community signals, and Lift is always shown separately from ratings because money never touches scores. Per-agent loadouts let you toggle skills and tools per agent so each agent only sees what you chose, and SkillzBench tracks upstream changes, re-scans, re-benchmarks, and notifies you. Everything on the platform is free, funded by advertising in and around blog articles that never influences scores or listings.

pricing 0

• + Only option here that independently security-scans and benchmarks skills, with published Lift results.
• + Works across Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents, not just one ecosystem.
• + Version pinning to a commit SHA means you always know exactly what you installed.
• + Per-agent loadouts stop context bloat by showing each agent only what you chose.
• + Everything is free, and ad money never influences scores or listings.

• − It's a vetting and delivery layer, not a plugin authoring platform; you'll still browse community collections for raw volume.
• − Benchmarking every skill in a sandbox takes effort, so coverage depends on continuous crawling rather than instant inclusion.
• − Younger than Anthropic's official directory, so brand recognition is lower.

https://skillzbench.com

A large community-curated list maintained by Composio, described as a collection of awesome Claude Code plugins: slash commands, subagents, MCP servers, and hooks for Claude Code. It's one of the third-party marketplaces you can add to Claude Code with /plugin marketplace add owner/repo-name, and you can also clone the repo and install directly. Composio's own Connect MCP plugin, installable from this collection, lets Claude Code securely access apps like Jira, Linear, and GitHub from a single MCP server, with dynamic tool loading that only loads tools as needed to avoid choking the LLM context window. The collection is a good place to find MCP integration plugins (GitHub, Linear, Slack, Vercel, Sentry, Supabase), code review plugins, and security plugins like Security Guidance and Semgrep. Curation is by listing, though; there's no independent security scanning or benchmarking of what's included.

pricing See pricing

• + Broad community collection spanning MCP integrations, code review, and security plugins.
• + Can be added directly as a marketplace inside Claude Code.
• + Includes context-management tooling that addresses the multi-MCP context-window problem.
• + Free and open on GitHub.

• − Curation is a listing exercise; no security scanning or performance benchmarks.
• − Quality varies across the list and you evaluate plugins yourself.
• − Maintained by a vendor (Composio) whose own tooling is featured prominently.

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

A dedicated directory of Claude Code plugin collections, skill registries, and component marketplaces on GitHub, indexing 34 collections with popularity stats. Highlights include Ecc by affaan-m (229k stars), an agent harness performance optimization system with skills, instincts, memory, and security features for Claude Code, Codex, Opencode, and Cursor; Claude Mem by thedotmack (87k), which captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions across Claude Code, Codex, Gemini, Copilot, and more; Claude Skills by alirezarezvani (22k) with 345 skills across engineering, marketing, product, compliance, and finance; and Claude Code Plugins Plus Skills by jeremylongshore (2.5k), an open-source marketplace at tonsofskills.com with 425 plugins, 2,810 skills, and 200 agents plus the ccpi CLI package manager. The directory is a discovery layer: it points you at collections with star counts, but the vetting is entirely yours.

pricing See pricing

• + The broadest discovery view of the ecosystem, spanning 34 collections.
• + Popularity signals (star counts) help you find what the community actually uses.
• + Tags by capability type make it easy to find exactly the kind of plugin you need.
• + Free to browse.

• − Popularity is not quality: star counts say nothing about security or effectiveness.
• − No benchmarks, scans, or license checks on anything listed.
• − You still have to visit and evaluate each GitHub collection separately.

https://www.aitmpl.com/plugins/

A curated Claude Code plugin marketplace by obra (Jesse Vincent), a well-known figure in the Claude Code community. It's listed among the notable collections on aitmpl.com's directory with 1.1k stars, tagged with commands, MCPs, and skills. As a third-party marketplace, you add it to Claude Code with /plugin marketplace add and browse its plugins through the standard Discover tab, so the install experience is identical to the official marketplace. Its value proposition is human curation: a smaller, opinionated selection rather than an everything-and-anything list. Like other community marketplaces, though, curation means selection, not verification; there's no published security scanning or benchmark data for what it lists.

pricing See pricing

• + Human-curated by a recognized community author.
• + Smaller selection means less noise to filter through.
• + Installs through the same standard marketplace flow as official plugins.

• − Much smaller than the big collections (1.1k stars vs 229k for the largest).
• − No security scanning or benchmark data on listed plugins.
• − Curation quality depends on one maintainer's judgment.

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

A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections, designed to extend Claude Code, Claude Desktop, the Agent SDK, and OpenClaw. It's listed on aitmpl.com's directory with 3.2k stars and tagged across skills, agents, commands, and hooks. Its pitch is consolidation: instead of bookmarking a dozen separate GitHub repos, you get one place that aggregates the different extension types and points you at marketplace collections. That makes it a useful starting point for small teams that find the ecosystem fragmented. As with the other community directories, it's a discovery layer without independent security scanning, license checks, or benchmarks, so what you install from it is your responsibility to evaluate.

pricing See pricing

• + Consolidates multiple extension types and collections into one hub.
• + Covers Claude Desktop and the Agent SDK, not just Claude Code.
• + Free and community-maintained.

• − Aggregator, not a verifier: no scans or benchmarks.
• − Smaller community footprint (3.2k stars) than the leading collections.
• − Maintenance depends on one maintainer.

https://github.com/davepoon/buildwithclaude