Sign InOpen Brain
GitHubGitHub RepoNeeds Review

anthropics/claude-plugins-community

Anthropic now exposes its reviewed community plugin catalog as a nightly read-only mirror for Claude Code and Cowork. Installation is direct, but submissions and changes must pass its separate review pipeline.

GitHub
Open Source Open MarkdownOpen JSON
Source Summary

This repository mirrors the community plugin marketplace for **Claude Code and Claude Cowork**. Its marketplace file syncs **nightly** from Anthropic's internal pipeline, and every listed plugin has passed automated security scanning plus distribution approval.

Practical Implication

Builders can add the marketplace from the Claude CLI and install a named community plugin, while using the repository as an inspectable catalog. Plugin authors must submit through Anthropic's directory form rather than opening a pull request.

Agent-Ready Context
This repository mirrors the community plugin marketplace for **Claude Code and Claude Cowork**. Its marketplace file syncs **nightly** from Anthropic's internal pipeline, and every listed plugin has passed automated security scanning plus distribution approval.

Builders can add the marketplace from the Claude CLI and install a named community plugin, while using the repository as an inspectable catalog. Plugin authors must submit through Anthropic's directory form rather than opening a pull request.

The repository is **read-only**, so it is not the source of review decisions or direct community edits. Automated scanning and approval reduce one class of risk, but the material does not describe review criteria, ongoing monitoring, or guarantees about plugin behavior.
Connected Context · Feed7 Judgment

This adds a distribution and screening layer to community Claude plugins: a nightly synchronized, inspectable catalog whose entries have passed automated scanning and approval. It is stronger evidence of pre-distribution filtering than an unreviewed discovery list, but weaker than a transparent trust framework because criteria, monitoring, and behavioral guarantees are unspecified. Its read-only mirror also separates catalog access from submission and review authority.

anthropics/claude-plugins-officialTogether they distinguish official and community distribution: the community mirror adds stated scanning and approval, while the official marketplace description leaves third-party code trust with the installer.VoltAgent/awesome-agent-skillsUnlike a broad discovery index that requires repository-level vetting by adopters, this catalog applies an automated scan and distribution approval before listing, though neither establishes ongoing behavioral safety.anthropics/claude-codeClaude Code supplies the plugin-capable runtime and installation surface for the community packages cataloged here; the mirror is distribution infrastructure rather than an alternative agent runtime.alirezarezvani/claude-skillsThe cross-agent skill catalog emphasizes portability and includes its own auditor, whereas this repository narrows scope to approved Claude Code and Cowork plugins synchronized through Anthropic’s pipeline.
Context Map
toolscoding#skills#tool-use#coding-agents
Uncertainty
The repository is **read-only**, so it is not the source of review decisions or direct community edits. Automated scanning and approval reduce one class of risk, but the material does not describe review criteria, ongoing monitoring, or guarantees about plugin behavior.