The 5 Best Claude Code Marketplace Alternatives in 2026

The Claude Code Marketplace is Anthropic's official directory for Claude Code plugins, managed under the anthropics/claude-plugins-official repository. 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. The official marketplace is automatically available when you start Claude Code: you run /plugin, use the Discover tab to browse, and install directly with a single command. If a plugin is missing, refreshing the marketplace keeps the catalog current. Before plugins, teams shared scattered CLAUDE.md files, hook scripts, MCP configs and custom slash commands; the marketplace packages those pieces into installable, shareable units. Popular categories include code intelligence and LSP plugins (TypeScript, Pyright, Rust Analyzer, Go), MCP integration plugins for GitHub, Linear, Slack, Vercel, Sentry and Supabase, code review plugins, and security plugins such as Security Guidance and Semgrep. The trade-off is scope: it's Claude Code-centric and curated rather than exhaustive, and it doesn't publish per-skill benchmark data.

pricing See pricing

• + Officially managed by Anthropic, the highest-trust source for Claude Code extensions
• + Zero setup: the marketplace is available the moment you start Claude Code
• + Clean install flow through /plugin and the Discover tab
• + Plugins package skills, agents, hooks and MCP servers into one shareable unit

• − Curated catalog is smaller than large community collections
• − Claude Code-centric; community collections cover Codex, Cursor, Gemini CLI and more
• − No published per-skill benchmark or Lift data

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 published research found roughly 26% of them carry at least one vulnerability, and nobody could tell which ones actually help. SkillzBench runs five pillars: Discover continuously crawls and dedupes skills from GitHub; Verify pins every version to a commit SHA and validates, license-checks, security-scans and quality-judges each one; 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 you chose; 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. Everything on the platform is free, funded by advertising around its blog articles; ad money never influences scores or listings.

pricing 0

• + Completely free, including the MCP connector, benchmarks and alerts
• + Only option here that measures whether a skill actually helps, via published Lift scores
• + Security scanning matters given research showing ~26% of skills carry a vulnerability
• + Works across Claude Code, Codex, Cursor, Gemini CLI and chat-app agents
• + Per-agent loadouts stop skills and tools from leaking into agents that shouldn't see them

• − It's a separate platform, so it doesn't replace the built-in /plugin flow inside Claude Code
• − Focused on skills rather than full plugin bundles with hooks and commands
• − Ad-supported model means blog advertising appears around its content

https://skillzbench.com

Claude Skills by alirezarezvani is one of the largest community collections of agent skills, listed on the aitmpl plugin directory with 22k stars. It packages 345 Claude Code skills and agent skills, 30+ agents, 70+ custom commands and 330+ skills with customizable references and scripts. Coverage is unusually broad in two senses: it targets Claude Code, Codex, Gemini CLI, Cursor and 8 more coding agents, and it spans job functions beyond engineering, including marketing, product, compliance, C-level advisory, research, business operations, commercial and finance, plus daily productivity skills. That makes it a good fit for small teams where the same agent toolkit has to serve developers and non-technical staff. The trade-offs are typical of big community repos: curation is community-driven rather than vendor-managed, there's no published security scanning or benchmarking, and quality varies skill by skill, so you're trusting the maintainer's judgment and community signals rather than measured results.

pricing See pricing

• + Very large catalog covering both coding and business functions
• + Cross-agent support beyond Claude Code
• + Open-source and free

• − No published security scanning or benchmarking per skill
• − Community curation means uneven quality across 345 skills
• − Requires adding it as a third-party marketplace

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

Claude Code Plugins Plus Skills by jeremylongshore is the volume leader among community marketplaces, with 425 plugins, 2,810 skills and 200 agents for Claude Code, and 2.5k stars on the aitmpl directory. It's an open-source marketplace hosted at tonsofskills.com and ships its own package manager, the ccpi CLI, so you can install from it the way you'd use a package registry rather than hand-copying files. The sheer scale is the pitch: if you want to browse a deep catalog of ready-made plugins, skills and agents instead of building your own, this collection has more units than any other entry here. The usual community-repo caveats apply in force at this scale. There's no published per-skill security scanning, benchmarking or quality scoring, and with thousands of skills the variance between excellent and mediocre entries is real. It's also Claude Code-focused, so teams running Codex or Cursor agents get less from it than from cross-agent collections.

pricing See pricing

• + Largest catalog of any collection listed here
• + Dedicated CLI package manager (ccpi) simplifies installs
• + Free and open-source

• − No published vetting, scanning or benchmark data at this scale
• − Claude Code-focused rather than cross-agent
• − Quality varies widely across thousands of entries

https://github.com/jeremylongshore/Claude-Code-Plugins-Plus-Skills

Awesome Claude Code Plugins by ccplugins is a curated list in the classic 'awesome' format, collecting slash commands, subagents, MCP servers and hooks for Claude Code. It sits in the middle of the pack on size with 875 stars on the aitmpl directory, but its value is different from the big volume repos: someone has already filtered the field down to a working set of extensions, which saves you from trawling GitHub yourself. The Composio guide references it as a third-party marketplace you can add directly with /plugin marketplace add, so installation stays inside Claude Code's native flow. Because it's a curated list rather than a tested catalog, it doesn't publish security scans, quality scores or benchmark results, and its coverage is Claude Code-specific. It's a solid middle path: more selective than the thousand-entry collections, broader in format coverage than a skills-only repo, and light enough to review by hand.

pricing See pricing

• + Human-curated, so less noise than raw volume repos
• + Covers multiple extension formats: commands, subagents, MCPs, hooks
• + Installs through Claude Code's native marketplace command

• − Smaller catalog than the big collections
• − No testing, scanning or benchmark data
• − Claude Code only

https://github.com/ccplugins/awesome-claude-code-plugins

Buildwithclaude by davepoon is a discovery hub rather than a single marketplace: one place to find Claude Skills, Agents, Commands, Hooks, Plugins and Marketplace collections that extend Claude Code, Claude Desktop, the Agent SDK and OpenClaw. With 3.2k stars on the aitmpl directory, it works well as a starting point when you don't yet know which collection or format you need, because it indexes across all of them instead of committing to one. That breadth across Claude surfaces (including Claude Desktop and the Agent SDK, which most plugin repos ignore) is its main differentiator. The flip side of being a hub is that it's directory-style: it points you to resources rather than vouching for them, with no security scanning, quality scoring or benchmarking of its own, and you'll often end up installing from another repo anyway. Treat it as a map, not a destination.

pricing See pricing

• + Broadest surface coverage, including Claude Desktop and the Agent SDK
• + Good discovery starting point across formats and collections
• + Free and open-source

• − Directory-style, so it doesn't vet what it lists
• − You usually install from a third repo anyway
• − No quality or security data

https://github.com/davepoon/buildwithclaude

Superpowers Marketplace by obra is a curated Claude Code plugin marketplace with 1.1k stars on the aitmpl directory, covering commands, MCP servers and skills. Its identity is selectivity: rather than aggregating everything, it curates a set of plugins the maintainer considers worth installing, in the spirit of a quality-first marketplace. That makes it a reasonable second marketplace to add alongside the official one when you want options beyond Anthropic's catalog without dropping into a 2,800-skill dump. Installation follows the standard third-party pattern via /plugin marketplace add. As with the other community entries, there's no published security scanning, quality scoring or benchmarking, and the catalog is Claude Code-centric, so it won't serve teams running skills across Codex, Cursor or Gemini CLI. Its smaller size is either the point or the limitation, depending on whether you're shopping for quality or coverage.

pricing See pricing

• + Quality-first curation over raw volume
• + Installs via the standard marketplace add command
• + Free and open-source

• − Small catalog
• − No verification or benchmark layer
• − Claude Code only

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