The 5 Best Claude Code Marketplace Alternatives in 2026

Anthropic's official plugin marketplace for Claude Code. 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. It's automatically available when you start Claude Code: you run /plugin, browse the Discover tab, and install. Anthropic describes the official directory as a managed collection of high-quality Claude Code plugins. Third-party marketplaces can be added too, via /plugin marketplace add owner/repo. The marketplace solved a real packaging problem: before plugins, teams shared scattered CLAUDE.md files, hook scripts, and MCP configs, and plugins made those pieces installable and shareable. The catch for a small business is that it's a distribution channel with curation, not an independent verification layer, and it only exists inside the Claude Code ecosystem.

pricing 20/month

• + Zero friction: it's automatically available when you start Claude Code, no extra setup.
• + Official Anthropic curation on the claude-plugins-official directory.
• + Plugins package whole workflows (skills, hooks, MCP configs, commands) instead of scattered files.
• + Works with the same /plugin command for third-party marketplaces, so it's extensible.

• − No independent security scanning or benchmarking of listed skills.
• − Locks you into Anthropic's models and a terminal-first workflow.
• − Requires a Claude subscription; heavy agent use pushes toward $100-200/mo Max plans.
• − The official directory is one collection among dozens; the broader ecosystem lives on GitHub where quality varies wildly.

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. Where marketplaces hand you install commands, SkillzBench answers the question they skip: does this skill actually help, and is it risky? Published research found roughly 26% of skills carry at least one vulnerability, and SkillzBench is built around that problem. It 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. Then it 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 so money never touches scores. The free MCP connector plus per-agent loadouts means your agent only sees the skills and tools you toggle on, and SkillzBench tracks upstream changes, re-scans, re-benchmarks, and notifies you when something shifts. Everything on the platform is free; revenue comes from advertising around blog articles, never from users.

pricing 0

• + The only option here that independently security-scans, license-checks, and benchmarks skills before you use them.
• + Lift is measured in a sandbox and shown separately from ratings, so you know a skill actually helps.
• + Works across Claude Code, Codex, Cursor, Gemini CLI, and chat-app agents, not just one ecosystem.
• + Per-agent loadouts stop context bloat by letting the agent see only what you chose.
• + Everything is free: directory, MCP connector, benchmarks, and alerts.

• − It's a verification and delivery layer, not a plugin authoring platform; you still discover some raw collections elsewhere.
• − Newer than the official marketplace, so brand recognition is lower.
• − Ad-supported blog model means you'll see advertising around articles (though it never touches scores).

https://skillzbench.com

Composio's Awesome Claude Plugins is one of the most widely referenced third-party collections, installable as a Claude Code marketplace via /plugin marketplace add or a direct git clone. It's organized by plugin type: code intelligence and LSP plugins (TypeScript, Pyright, Rust Analyzer, Go), MCP integration plugins (GitHub, Linear, Slack, Vercel, Sentry, Supabase), code review plugins (Code Review, PR Review Toolkit, CodeRabbit, Code Simplifier), and security plugins (Security Guidance for real-time warnings on risky edits, Semgrep for scan-based checks). The collection is genuinely useful for figuring out what to install first, and the Composio team notes a real problem it solves: installing many MCP servers at once can choke the LLM context window, which their Connect MCP addresses with dynamic tool loading. As a curated list, though, it's a starting point for discovery, with no security scanning or benchmarking of the skills it points to.

pricing 0

• + Well-organized by use case, which makes it easy to pick the right plugin type for your workflow.
• + Includes practical guidance, like installing one LSP plugin for your main language before adding integrations.
• + Free and open-source.
• + Flags a real problem: stacking MCP servers can exhaust the context window.

• − Curation only; no security scanning or performance benchmarks.
• − Tied to Composio's ecosystem pitch for its Connect MCP.
• − Being a list, it can go stale between updates.

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

aitmpl.com is a discovery directory that indexes 34 Claude Code plugin collections, skill registries, and component marketplaces on GitHub in one browsable place. It covers the big names, including the official anthropics directory, Ecc (229k stars, an agent harness performance optimization system), Claude Mem (87k stars, persistent context across sessions), Claude Hud (26k stars, showing context usage and running agents), Compound Engineering Plugin by EveryInc, HashiCorp's Agent Skills, and many niche entries like the Playwright browser-automation skill and Timescale's Postgres MCP. Each entry lists what it contains (skills, agents, commands, hooks, MCPs) and its star count. For a small business trying to see the whole ecosystem at a glance, it's the best map available. What it doesn't do is verify anything: stars are a popularity signal, and popularity has never been a security check.

pricing See pricing

• + The broadest single view of the plugin ecosystem, including collections the official marketplace doesn't surface.
• + Content tags help you find, say, only MCP servers or only skills quickly.
• + Covers cross-agent collections that work with Codex, Cursor, and Gemini CLI, not just Claude Code.

• − Pure index: no vetting, scanning, or testing of anything it lists.
• − Star counts reward hype as much as quality.
• − You still have to leave the site to actually install anything.

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

This single-maintainer collection is one of the most popular skill bundles in the ecosystem, with 22k stars on GitHub. It packs 345 Claude Code skills, agent skills, and plugins, including 30+ agents, 70+ custom commands, and 330+ skills with customizable references and scripts. What makes it interesting for a small-business reader is the range beyond engineering: the collection spans marketing, product, compliance, C-level advisory, research, business operations, commercial and finance, and general productivity skills. It also works across 12+ coding agents, including Claude Code, Codex, Gemini CLI, and Cursor, so it travels with you if you switch tools. The trade-off is structural: it's one maintainer's bundle with no external validation, so you're trusting a single source for hundreds of skills at once, and there's no security scanning or benchmarking to back the quality claims.

pricing 0

• + Unusual breadth into business domains, not just engineering tasks.
• + Cross-agent compatibility across 12+ tools.
• + Free and open-source with a large community following (22k stars).

• − Single-maintainer bundle: one source of truth for hundreds of skills.
• − No security scanning, license checking, or benchmarks.
• − Big bundles can bloat agent context if you install wholesale.

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

Claude Code Plugins Plus Skills, by jeremylongshore, is the volume play of the ecosystem: an open-source marketplace at tonsofskills.com listing 425 plugins, 2,810 skills, and 200 agents for Claude Code, with its own ccpi CLI package manager for installation. For a small business that wants maximum choice, it's hard to beat on sheer numbers, and the dedicated CLI makes installs scriptable rather than menu-driven. The obvious counterweight is that volume and quality are different things. With nearly 3,000 skills and no published security scanning, license checking, or benchmarking, you're doing your own vetting at a scale where individual review isn't realistic. It's a strong discovery and install layer if you pair it with an independent verification source.

pricing 0

• + One of the largest single collections available anywhere.
• + Dedicated CLI package manager rather than manual installs.
• + Free and open-source.

• − Volume without verification: no scanning or benchmarks across thousands of skills.
• − Quality almost certainly varies widely across 2,810 skills.
• − Claude Code-focused, less cross-agent than some collections.

https://tonsofskills.com

Superpowers Marketplace, by obra, is a deliberately curated Claude Code plugin marketplace, installable through the standard /plugin marketplace add flow. At 1.1k stars it's a fraction of the size of the mega-collections, and that's the point: it's a smaller, hand-picked selection of commands, MCPs, and skills rather than an everything-store. For a small business, a tight curated marketplace means less noise and a shorter evaluation cycle per plugin, and the standard install path keeps friction low. The limitation is the flip side of curation: a smaller catalog limits what you'll find, and like the other community marketplaces, there's no published security scanning or benchmarking of the plugins it lists. Curation is a filter, but it's the maintainer's judgment, not an independent test.

pricing 0

• + Small, curated catalog means less noise to wade through.
• + Installs through the same standard marketplace flow as everything else.
• + Free and open-source.

• − Much smaller selection than the big collections (1.1k stars).
• − Curation criteria aren't published.
• − No independent security scanning or benchmarks.

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