The 5 Best Claude Code Marketplace Alternatives in 2026

The Claude Code Marketplace is Anthropic's official directory of plugins for its Claude Code coding agent. Plugins are packaged bundles that can include skills, agents, hooks, MCP servers, slash commands, and LSP servers, so teams no longer share scattered CLAUDE.md files and hook scripts by hand. The marketplace is automatically available when you start Claude Code: run /plugin, browse the Discover tab, and install directly, for example with /plugin install github@claude-plugins-official. Anthropic manages the official claude-plugins-official repo, and third-party marketplaces can be added with /plugin marketplace add owner/repo-name. The catalog covers code intelligence (TypeScript, Pyright, Rust Analyzer, Go LSP plugins), MCP integrations for GitHub, Linear, Slack, Vercel, Sentry, and Supabase, code review plugins like CodeRabbit and PR Review Toolkit, and security plugins like Security Guidance and Semgrep. It's the default choice because it's built in, but it lists and installs plugins without publishing security scans, version pinning, or benchmark results for individual entries.

pricing See pricing

• + Zero setup: the official marketplace is automatically available when Claude Code starts
• + Officially managed by Anthropic with a curated quality bar for the claude-plugins-official repo
• + Deep integration with Claude Code's plugin system, including LSP and MCP plugin types
• + Simple refresh workflow (/plugin marketplace update) keeps the catalog current

• − No published security scans, version pinning, or benchmark results for listed plugins, despite research finding ~26% of agent skills carry at least one vulnerability
• − Locks you into the Claude Code ecosystem; plugins don't transfer to Codex, Cursor, or Gemini CLI
• − Claude Code itself has no free tier, and heavy agent use pushes costs toward the $100-$200/month Max tiers
• − Loading many MCP plugins at once can choke the LLM context window

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. It exists because agent skills (SKILL.md instruction packages for Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents) have exploded in number while quality and safety stay opaque; published research found roughly 26% of skills carry at least one vulnerability. SkillzBench runs five pillars today: Discover continuously crawls and dedupes skills from GitHub; Verify pins every version to a commit SHA, validates it, checks the license, runs a security scan, and judges quality; Benchmark tests every skill in a sandbox with the same model, with and without the skill, and publishes the Lift in percentage points; Equip gives you one free MCP server plus per-agent loadouts, so you toggle skills and tools per agent and the agent only sees what was chosen; and Stay current tracks upstream changes, re-scans, re-benchmarks, and notifies you. A 0-100 trust score combines security, quality, license, maintenance, and community signals, and Lift is always shown separately from ratings. Money never touches scores; the platform is funded by blog advertising, and everything, including the directory, MCP connector, benchmarks, and alerts, is free.

pricing 0

• + Completely free, including the MCP connector and benchmarks; ad-funded with no paid placement
• + Directly addresses the ~26% vulnerability rate with security scans and commit-SHA version pinning
• + Lift benchmarks show whether a skill actually helps, measured with and without it in a sandbox
• + Works across Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents, not just one ecosystem
• + Per-agent loadouts prevent context-window bloat by exposing only chosen skills

• − Not an official Anthropic product, so it sits alongside the built-in marketplace rather than replacing it inside the CLI
• − Catalog size depends on continuous crawling rather than Anthropic's curated official list
• − Benchmark and trust-score methodology is its own; teams standardized on Anthropic's tooling may prefer native plugins

https://skillzbench.com

Awesome Claude Plugins is Composio's open-source, curated collection of Claude Code plugins, installable as a third-party marketplace with /plugin marketplace add composiohq/awesome-claude-plugins or by cloning the repo directly. It curates slash commands, subagents, MCP servers, and hooks across the categories that matter for working developers: code intelligence LSP plugins, MCP integrations for services like GitHub, Linear, Slack, Vercel, Sentry, and Supabase, code review plugins such as CodeRabbit and PR Review Toolkit, and security plugins like Security Guidance and Semgrep. Its standout bundled capability is Composio Connect MCP, which lets Claude Code securely access apps like Jira, Linear, and GitHub from a single MCP server, with dynamic tool loading that only pulls tools into context as needed. That matters because installing many separate MCP servers otherwise loads every available tool into the context window and chokes it. The collection is free and community-driven, with curation as its quality mechanism; it does not publish per-plugin security scans or benchmark results.

pricing 0

• + Free and open source, cloneable straight from GitHub
• + Composio Connect solves the multi-MCP context-window problem with dynamic tool loading
• + Well-organized by plugin type, so picking an LSP or security plugin is straightforward
• + Backed by an active vendor (Composio) with documented setup in under a minute

• − No published security scans or benchmark Lift data for individual plugins
• − Claude Code focused; the collection doesn't serve Codex, Cursor, or Gemini CLI workflows
• − Requires a manual marketplace-add step rather than being preloaded

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

Claude Skills by alirezarezvani is one of the largest multi-agent skill collections on GitHub, with 345 Claude Code skills and agent skills, 30+ agents, 70+ custom commands, and 330+ skills with customizable references and scripts. Its main differentiator is breadth of coverage across both job functions and tools: the collection spans engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial and finance, and daily productivity skills, and it works with Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents. For a small business, that breadth is the appeal: one repo can supply a marketing skill for one teammate and a finance skill for another, regardless of which coding agent each person runs. The tradeoff is that a collection this large is uneven by nature, and the repo doesn't publish per-skill security scans, license checks, or benchmark results, so you're relying on the maintainer's curation and your own review. It sits among the most-starred collections in the ecosystem at roughly 22k stars.

pricing 0

• + Widest job-function coverage of any collection here, useful for non-engineering small-business teams
• + Cross-agent compatibility with 12+ coding agents
• + Free and open source with a large community (22k stars)
• + Includes hooks and commands alongside skills for fuller workflow coverage

• − No published security scanning, version pinning, or benchmarking despite the ~26% industry vulnerability rate
• − Quality varies across 345 skills; you vet each one yourself
• − No per-agent loadout mechanism, so managing what each agent sees is manual

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

Buildwithclaude by davepoon is a single hub for finding Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections that extend Claude Code, Claude Desktop, the Agent SDK, and OpenClaw. Rather than being one giant skill dump, it organizes the ecosystem's scattered resources into one browsable place, which is its core value: if you're new to the skills ecosystem and don't know whether you need a skill, a plugin, a hook, or an MCP server, the hub lays out the categories side by side. It lists around 3.2k stars' worth of community traction and covers Claude Desktop and the Agent SDK alongside the CLI, which most collections ignore. Like the other community hubs, it doesn't publish security scans, version pinning, or benchmark results for what it lists, and it's oriented around the Claude ecosystem rather than cross-agent workflows. It's free and open source, and it works well as a discovery layer you pair with a vetting tool.

pricing 0

• + Good discovery starting point that explains the ecosystem's categories
• + Covers Claude Desktop and the Agent SDK, which most skill repos skip
• + Free and lightweight with no install required to browse

• − A directory of links rather than a vetted catalog; no security scans or benchmarks
• − Claude-centric, so limited value if your team runs Codex or Gemini CLI
• − Smaller community than the biggest collections

https://github.com/davepoon/buildwithclaude

Claude Code Plugins Plus Skills by jeremylongshore is the highest-volume collection in this comparison: 425 plugins, 2,810 skills, and 200 agents for Claude Code, distributed as an open-source marketplace at tonsofskills.com with its own ccpi CLI package manager. The ccpi CLI is the practical differentiator; instead of hand-editing marketplace configs, you install and manage plugins through a package-manager workflow, which feels more familiar if you're used to npm or pip. The raw numbers dwarf most rivals, and the collection carries the skills, agents, commands, and hooks tags that Claude Code's plugin system supports. The tradeoff mirrors the other large community repos: nothing in the research indicates per-skill security scanning, commit-level version pinning, or benchmark testing, so with 2,810 skills the burden of spotting a risky one falls entirely on you. It sits at roughly 2.5k stars, a solid but smaller community than the top collections.

pricing 0

• + Largest raw catalog here by a wide margin (2,810 skills)
• + ccpi CLI gives package-manager-style installs instead of manual config
• + Free and open source

• − No published security scans, version pinning, or benchmarks across 2,810 skills
• − Claude Code only; no cross-agent support
• − Smaller community (2.5k stars) than the leading collections

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