Sign InOpen Brain
GitHubGitHub RepoNeeds Review

anthropics/claude-plugins-official

Anthropic’s official Claude Code marketplace exposes a standard plugin package for commands, agents, skills, and MCP configuration, while leaving third-party code trust to the installer.

GitHub
Open Source Open MarkdownOpen JSON
Source Summary

The repository is Anthropic’s official Claude Code plugin directory, split into internal and third-party entries. A plugin requires **plugin.json** and may add MCP configuration, slash commands, agents, and skills; installation uses Claude Code’s plugin system.

Practical Implication

Treat its example plugin and schema as packaging references. Keep the published name as an **immutable slug**, use displayName for UI changes, and add a rename mapping when migration is unavoidable.

Agent-Ready Context
The repository is Anthropic’s official Claude Code plugin directory, split into internal and third-party entries. A plugin requires **plugin.json** and may add MCP configuration, slash commands, agents, and skills; installation uses Claude Code’s plugin system.

Treat its example plugin and schema as packaging references. Keep the published name as an **immutable slug**, use displayName for UI changes, and add a rename mapping when migration is unavoidable.

Marketplace inclusion is not a runtime safety guarantee. Anthropic says it does not control or continuously verify the MCP servers, files, or software bundled by third parties, so inspect each plugin and its source before use.
Connected Context · Feed7 Judgment

This provides Claude Code’s authoritative packaging and naming contract, including immutable slugs and explicit rename migration, but narrows what official listing means: it is a distribution reference, not assurance that bundled MCP servers, files, or software are safe. Plugin adoption therefore needs both schema compliance and independent source inspection.

cursor/pluginsCursor’s repository confirms a parallel manifest-based packaging model for skills, MCP servers, and workflows, while Anthropic adds concrete slug-migration rules and an explicit warning that catalog presence is not a safety guarantee.Introducing Agent PluginsThe common Agent Plugins contract can reduce repackaging across clients, but Anthropic’s directory shows that portable structure does not transfer installation policy, naming lifecycle, marketplace governance, or security assurance.anthropics/claude-plugins-communityThe community mirror adds automated scanning and approval before distribution, whereas the official directory still disclaims continuous verification; review status therefore strengthens filtering without becoming a runtime guarantee.Tencent/AI-Infra-GuardAI-Infra-Guard provides a possible CI and runtime inspection layer for the exact skill-and-MCP supply-chain risk that Anthropic says marketplace inclusion does not eliminate.
Context Map
toolscodingsecurity#skills#mcp#coding-agents
Uncertainty
Marketplace inclusion is not a runtime safety guarantee. Anthropic says it does not control or continuously verify the MCP servers, files, or software bundled by third parties, so inspect each plugin and its source before use.