LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
PluginRisingofficial publisher

Plugins officiels Claude Code

Plugin : A set of capabilities installed into an AI application or a host · requires claude-code

Anthropic's official marketplace of plugins and skills for Claude Code.

The safest starting point to extend Claude Code: official marketplace, supply chain controlled by the vendor.

Overall score
8.0 /10
Security: one caveat, see the card
Utility
8.0
Reliability
10.0
Security
One caveat
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Extending Claude Code with third-party plugins raises a trust issue: how can you tell whether a plugin is reliable, maintained, and free of malicious code? Anthropic's official directory centralises verified plugins to address this need.

The directory distinguishes two categories: internal plugins developed and maintained by Anthropic, and external plugins submitted by partners or the community, which must meet quality and security standards before approval. Installation is done directly from Claude Code using the command /plugin install {name}@claude-plugins-official or through the discovery interface /plugin > Discover.

Each plugin can include slash commands, agent definitions, skills, and an MCP server configuration. Skills are registered as <plugin-name>:<skill-name> in Claude Code, making them easy to identify and invoke precisely.

This directory is aimed at developers who use Claude Code daily and want to extend it with new capabilities without searching for plugins from unknown sources. It is not suited to those looking for highly specialised plugins not yet in the catalogue, or to those who want to publish a plugin without going through the official submission process.

What it offers

  • ·Centralised catalogue of verified plugins, separating Anthropic internal plugins from approved external ones.
  • ·One-command installation from Claude Code: /plugin install {name}@claude-plugins-official.
  • ·Browse and discover available plugins directly via /plugin > Discover inside Claude Code.
  • ·Support for skill-bundle plugins: a plugin can expose multiple skills from a repository without a dedicated manifest.
  • ·Plugin rename management with automatic migration of existing installs via a mapping file.
  • ·Open submission process for partners and the community via an official form, with quality and security validation.
  • ·Standardised structure for each plugin: metadata, optional MCP configuration, commands, agents, and skills.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude-code
Host
claude-code
Licence
MIT

Security and data

Rating
Security: one caveat, see the card
Your data
Data stays local
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 October 2025

How to install Plugins officiels Claude Code

1. Open Claude Code in your development environment. 2. To browse the catalogue, type /plugin > Discover and explore available plugins. 3. To install a plugin directly by name, run /plugin install {plugin-name}@claude-plugins-official. 4. Before installing an external plugin, check its homepage to assess the reliability of the source. 5. Verify that the installed plugin behaves as expected before using it in a sensitive project.
/plugin install {plugin-name}@claude-plugins-official

In the same category

Whole category Frame (methods, guardrails) →