The 5 Best Claude Code Marketplace Alternatives in 2026

Anthropic's official plugin directory for Claude Code, available as the claude-plugins-official repo. Plugins are bundles that can include skills, agents, hooks, MCP servers, and other capabilities, and the marketplace lets you discover and install them without building them yourself. The official docs say the marketplace is automatically available when you start Claude Code: open the Discover tab with /plugin, or install directly with /plugin install github@claude-plugins-official. If a plugin is missing, refresh with /plugin marketplace update claude-plugins-official. It's an Anthropic-managed directory of high-quality Claude Code plugins, which means a baseline level of curation, though it doesn't independently benchmark or security-scan plugins the way third-party verification services do.

pricing 0

• + Zero setup: ships inside Claude Code and is available by default
• + Anthropic-managed, so a quality baseline you don't get from random GitHub repos
• + One-command installs and marketplace refresh

• − Smaller selection than the big community collections
• − No independent security scanning or benchmarking of listed plugins
• − Tied to the Claude Code ecosystem only

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 addresses that across five pillars: Discover (continuously crawl and dedupe skills from GitHub), Verify (pin every version to a commit SHA, validate, license-check, security-scan, quality-judge), Benchmark (test every skill in a sandbox with the same model, with and without the skill, and publish the Lift in percentage points), Equip (one free MCP server plus per-agent loadouts, where the agent only sees what you chose for it), and Stay current (track upstream changes, re-scan, re-benchmark, notify). A 0-100 trust score combines security, quality, license, maintenance, and community signals, and money never touches scores.

pricing 0

• + Independent verification: security scans, license checks, and quality judging on every listed skill
• + Actual performance data via sandboxed Lift benchmarks, shown separately from ratings
• + Works across Claude Code, Codex, Cursor, Gemini CLI and chat-app agents, not just one tool
• + Everything is free, and ad revenue never influences scores or listings

• − Newer than the established community repos, so its catalog is still growing
• − Independent directory, so it's a companion to (not a replacement for) in-app marketplaces
• − Benchmarking adds a vetting pipeline, so brand-new skills won't appear instantly

https://skillzbench.com

A curated community list of Claude Code plugins maintained by Composio, covering slash commands, subagents, MCP servers, and hooks. You add it as a third-party marketplace with /plugin marketplace add, or clone the repo and point Claude Code at it directly. The collection doubles as a distribution channel for Composio's Connect MCP, which lets Claude Code securely access apps like Jira, Linear, and GitHub from a single MCP server. Composio's write-up also catalogs plugins by type: LSP code-intelligence plugins (TypeScript, Pyright, Rust Analyzer, Go), MCP integration plugins for Linear, Slack, Vercel, Sentry, and Supabase, code review plugins, and security plugins like Security Guidance and Semgrep. It's a genuinely useful map of the ecosystem, though curation here means human selection, not security scanning or benchmarking.

pricing 0

• + Broad, well-organized catalog organized by plugin type
• + Installs with a single marketplace add command
• + Includes practical guidance on which plugin types to install first

• − Curation only: no security scanning or performance benchmarking
• − Loading many MCP servers at once can choke the LLM context window, a caveat Composio itself flags
• − Vendor-maintained, so the list skews toward Composio's own tooling

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

aitmpl.com indexes 34 Claude Code plugin collections, skill registries, and component marketplaces on GitHub, making it the broadest single view of the ecosystem. Its listings include the biggest repos in the space: Ecc by affaan-m (229k), Claude Mem by thedotmack (87k), the official Anthropic directory (32k), Claude Hud by jarrodwatts (26k), Compound Engineering Plugin by EveryInc (23k), Knowledge Work Plugins by anthropics (23k), and Claude Skills by alirezarezvani (22k). Each entry is tagged by what it contains (skills, agents, commands, hooks, MCPs, LSPs) and shows star counts, so you can filter by what you need. It's a directory of directories: great for discovery, but it doesn't verify, scan, or benchmark anything it lists, and quality varies widely between collections.

pricing 0

• + Widest discovery surface: 34 collections in one place
• + Star counts and content tags help you triage quickly
• + Covers niche collections (HashiCorp, Airtable, Timescale) you'd never find otherwise

• − Pure directory: no vetting, scanning, or benchmarking
• − Quality varies sharply between collections
• − You still have to evaluate each collection yourself

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

One of the largest single skill collections on GitHub, with 22k stars per aitmpl.com's index. It packages 345 Claude Code skills, agent skills, and plugins, including 30+ agents, 70+ custom commands, and 330+ skills with customizable references and scripts. What sets it apart from most developer-focused collections is its business coverage: engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial and finance, and daily productivity skills. It works across Claude Code, Codex, Gemini CLI, Cursor, and eight more coding agents, which makes it a practical pick for small businesses running more than one agent. Like every community repo, though, it's published as-is: no independent security scanning, license verification, or benchmarking comes with the download.

pricing 0

• + Rare business-oriented skill coverage, not just developer tooling
• + Cross-agent compatibility across 12+ coding agents
• + Large volume in one repo

• − No security scanning or benchmarking
• − Volume over curation: quality will vary across 330+ skills
• − Single maintainer, so upkeep depends on one person

https://github.com/alirezarezvani

A curated Claude Code plugin marketplace from obra, listed on aitmpl.com with 1.1k stars and tagged with commands, MCPs, and skills. It installs through the standard third-party marketplace flow (/plugin marketplace add), so it slots into your existing Claude Code setup without any extra tooling. As a smaller, hand-curated collection, it's the opposite of the mega-repos: fewer items, more deliberate selection. That makes it a reasonable pick if the big collections feel overwhelming and you'd rather start from a short list someone has already filtered. The trade-off is the same one every community marketplace carries: curation here is a human's judgment call, not a security scan or a benchmark, and there's no independent verification of what's inside.

pricing 0

• + Small, deliberate catalog rather than an overwhelming dump
• + Standard one-command install
• + Cuts discovery time if big collections feel noisy

• − Much smaller than the major collections (1.1k stars vs 229k for the biggest)
• − No security scanning or benchmarking
• − Single maintainer's taste defines the whole catalog

https://github.com/obra