The 5 Best Claude Code Marketplace Alternatives in 2026

The Claude Code Marketplace is Anthropic's official directory for Claude Code plugins, packaged extensions that can bundle skills, agents, hooks, MCP servers and LSPs. Anthropic describes plugins as the packaging layer that replaced the old scattered setup of CLAUDE.md files, hook scripts and custom slash commands, making those pieces installable and shareable. The marketplace is available automatically when you start Claude Code: you run /plugin, browse the Discover tab, and install from the official claude-plugins-official repository or add third-party marketplaces like Awesome Claude Plugins with a single command. Popular official and community plugins cover code intelligence (TypeScript, Pyright, Rust Analyzer and Go LSPs), MCP integrations with GitHub, Linear, Slack, Vercel, Sentry and Supabase, code review workflows, and security guardrails like Security Guidance and Semgrep. The catalog is strong and the install flow is genuinely convenient, but the marketplace itself applies no independent security scan, benchmark or quality score to what it lists.

pricing 20/month

• + Zero extra setup: the official marketplace is available the moment you start Claude Code
• + Plugin packaging replaces scattered CLAUDE.md files, hook scripts and MCP configs
• + Strong first-party and community catalog across LSPs, MCP integrations, review and security plugins
• + Installing a plugin takes one slash command

• − Keeps you inside Anthropic's ecosystem and models
• − No independent security scan, license check or benchmark on listed plugins
• − Installing many MCP plugins can choke the LLM context window as all tools load into context
• − Sustained agent use on Claude Code pushes you toward $100-200/month Max tiers

https://code.claude.com

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) have exploded in number, but published research found roughly 26% of them carry at least one vulnerability, and no mainstream marketplace tells you which ones actually help. SkillzBench runs five pillars: it continuously crawls and dedupes skills from GitHub, pins every version to a commit SHA with validation, license checks, security scans and quality judging, benchmarks every skill in a sandbox with the same model with and without the skill and publishes the Lift in percentage points, equips agents through one free MCP server with per-agent loadouts you toggle, and tracks upstream changes with re-scans, re-benchmarks and notifications. 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, never by charging users.

pricing 0

• + Completely free, including the directory, MCP connector, benchmarks and alerts
• + Directly addresses the ~26% vulnerability rate in agent skills with automated security scanning
• + Lift benchmarks show whether a skill actually improves agent performance, not just that it exists
• + Works across Claude Code, Codex, Cursor, Gemini CLI and chat-app agents, not just one tool
• + Ad-funded model means scores and listings can't be bought

• − Focused on skills rather than full plugins, so it doesn't replace a coding agent or IDE
• − Trust scores and Lift results are SkillzBench's own methodology, not an industry standard yet

https://skillzbench.com

Cursor is an AI-native code editor forked from VS Code and the market leader in AI-powered editors, with $2B ARR and over 1 million paying users. Where Claude Code is terminal-first, Cursor gives you a graphical agent workspace: Cursor 3 rebuilt the interface around an Agents Window for launching, monitoring and reviewing multiple agents across repos. It supports Claude, GPT, Gemini, Grok and DeepSeek models plus its built-in Composer model (Composer 2.5, built on Moonshot's Kimi K2.5), which ties Claude Opus 4.7 on SWE-Bench Multilingual at 79.8% vs 80.5% and Terminal-Bench 2.0 at 69.3% vs 69.4% at roughly a tenth of the per-token cost on the standard tier. Background Agents spawn up to 8 parallel agents in isolated cloud VMs that clone your repo, work on a branch and open a PR. Automations trigger agents from GitHub events, Slack messages, Linear changes or cron schedules, and BugBot Autofix runs on every PR, with over 35% of proposed fixes merged directly.

pricing 20/month · free trial

• + Closest drop-in replacement for Claude Code's agentic coding inside a graphical IDE
• + Genuine multi-model flexibility, including a cheap built-in Composer model
• + Free Hobby tier with the full editor and no credit card
• + Mature parallel-agent and automation story

• − Credit-based pricing makes cost planning fiddly; Pro users running frequent agent sessions report real spend of $40-50/month
• − Composer's Fast tier, used by default for interactive work, costs $3/$15 per million tokens, closer to half a frontier model's price
• − Trails Claude Code on developer sentiment: 19% vs 46% 'most loved' in Pragmatic Engineer's early 2026 survey

https://cursor.com

Codex is OpenAI's coding agent, available as a desktop app for macOS and Windows, an open-source CLI (Apache 2.0) and a VS Code extension, used weekly by over two million developers. The desktop app acts as a command center for managing multiple agents: parallel agents work on the same repo conflict-free via Git worktrees, and you review diffs, comment inline and commit without leaving the app. Skills extend Codex beyond code generation, bundling instructions, resources and scripts to connect to Figma, deploy to Vercel or Netlify, manage Linear issues or generate documents, and they work across the app, CLI and IDE extension. Automations run agents on schedules for daily issue triage, CI failure summaries or release briefs, with results landing in a review queue. GitHub works as a task interface: tag @codex on a PR and a cloud agent starts, while the openai/codex-action GitHub Action enables CI/CD workflows including auto-fixing failing CI. The open-source CLI adds OS-level kernel sandboxing that physically prevents file access outside your project or unauthorized network calls.

pricing 20/month

• + No separate billing if you already pay for ChatGPT Plus, Pro or Business
• + Over two million weekly users and an open-source CLI
• + Lower token use per task than Claude Code, per DataCamp's comparison
• + Strong hand-off-and-review workflow for delegating whole tasks

• − OpenAI models only, so no model flexibility
• − API usage costs sit on top of ChatGPT plan limits for heavy use

https://openai.com/codex

OpenCode is the open-source (MIT) terminal coding agent with the most model flexibility of any Claude Code alternative in this comparison: 75+ providers, zero markup on model costs, and the ability to reuse subscriptions you already pay for. It has 120,000+ GitHub stars. Its headline feature is subscription piggybacking: run /connect and authenticate with GitHub Copilot ($10-39/month), ChatGPT Plus ($20/month) or other plans you already hold, and OpenCode runs on top of them instead of billing you separately. That makes it the cheapest serious option for developers who already subscribe to an AI service, and the privacy angle is real too since it can run local LLMs entirely on your own hardware. DataCamp recommends it specifically for privacy and local model use, and Builder.io highlights its model flexibility and zero-markup pricing. The trade-off is that it's a CLI, so non-technical team members get none of the visual affordances of Cursor or Codex's desktop app.

pricing 0

• + Free and open source with no vendor lock-in
• + Can reuse subscriptions you already pay for instead of adding a new bill
• + Model-agnostic across 75+ providers, including local models
• + Strong community traction

• − CLI-only experience, no visual editor
• − You manage your own model costs and API setup

https://opencode.ai

Awesome Claude Plugins is one of the most prominent third-party marketplace collections for Claude Code, maintained as a GitHub repository and installable directly into Claude Code with /plugin marketplace add owner/repo-name. It sits in a broader ecosystem: directory trackers like aitmpl.com list 34+ plugin and skill collections on GitHub, including Anthropic's official claude-plugins-official repo (32k stars), AEcc by affaan-m (229k stars), Claude Mem (87k stars) and Claude Skills by alirezarezvani with 345 skills spanning 30+ agents and 70+ custom commands. These community collections extend the official marketplace with curated slash commands, subagents, MCP servers and hooks, and the Composio-maintained repo includes a connect-apps install that sets up one MCP for accessing Jira, Linear, GitHub and more. They're free and fast to adopt, but curation is manual and community-driven: there's no automated security scanning, license checking or benchmarking of what you install, which is exactly the gap SkillzBench fills.

pricing 0

• + Free and community-maintained
• + Broadens the catalog well beyond Anthropic's official directory
• + One-command install into existing Claude Code setups

• − Manual curation with no automated security scans or benchmarks
• − Quality varies widely across the 34+ community collections
• − Still Claude Code-specific, so no cross-agent reach

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