AI Nexus HubAI Nexus Hub
PostsQuestionsDiscussions

Command Palette

Search for a command to run...

AI Nexus Hub

CONTACT:
axc@cyberlogitec.com

Content
PostsQuestionsDiscussionsTopics
Stay in the loop

Weekly digest of the best AI posts. No spam.

© CLT 2026. All rights reserved.
Privacy
Posts  /  Claude-code  /  Stop copying setup snippets: browse 315 Claude Code plugins in the official directory and install the right one in 2 minutes
0
Claude-code

Stop copying setup snippets: browse 315 Claude Code plugins in the official directory and install the right one in 2 minutes

HL
Hung Lay
Oct 28, 2026 · 3 min read
Banner: 315 plugins, one command away. Category counts: 123 development, 69 productivity, 39 database, 22 monitoring, 18 security, 44 other

TL;DR

  • What it is: claude-plugins-official is the catalog behind Claude Code's /plugin browser. It lists 315 plugins: 39 by Anthropic, 276 by partners and other authors.

  • The key benefit: before you install a plugin, you can see what it adds and how many tokens it costs. Then you choose if it is for you, for this repo, or for the whole team.

  • Time to try: 5 minutes. You most likely have this marketplace already: Claude Code adds it the first time you open an interactive session.

8 plugins worth installing first

315 is a lot. Here are the best-known ones. The 5 Anthropic plugins are the core coding workflow plugins. The 3 partner plugins are ranked by GitHub stars of the MCP server they connect to (checked on 2026-10-27). The directory does not publish install counts.

Plugin

By

What it does

Install

code-review

Anthropic

Reviews a pull request with several agents and drops low-confidence findings

/plugin install code-review@claude-plugins-official

commit-commands

Anthropic

Slash commands to commit, push, and open a PR

/plugin install commit-commands@claude-plugins-official

feature-dev

Anthropic

A guided feature workflow: explore the code, design, build, review

/plugin install feature-dev@claude-plugins-official

security-guidance

Anthropic

Warns on risky code as Claude edits, then reviews the diff and each commit

/plugin install security-guidance@claude-plugins-official

frontend-design

Anthropic

Builds UI that does not look like a generic AI template

/plugin install frontend-design@claude-plugins-official

context7

Upstash (63.8k stars)

Fetches up-to-date library docs, so Claude stops using old APIs

/plugin install context7@claude-plugins-official

playwright

Microsoft (38.7k stars)

Drives a real browser: open pages, click, fill forms, take screenshots

/plugin install playwright@claude-plugins-official

github

GitHub (34.0k stars)

Issues, pull requests, and code search through GitHub's official MCP server

/plugin install github@claude-plugins-official

Using TypeScript, Python, Go, Java, or C#? Also search lsp. Plugins such as typescript-lsp and pyright-lsp give Claude a real language server, so it can answer "where is this used?" without grep.

Try it in 5 minutes

Prerequisite: an up-to-date Claude Code (claude update).

  1. In Claude Code, run /plugin. The Discover tab lists every plugin. Type security to filter it.

  2. Open a plugin by name to see its cost: /plugin install security-guidance@claude-plugins-official. The pane shows Will install, Last updated, and Context cost (tokens on every turn, and tokens when it is used).

  3. For your first try, pick local scope (only you, only this repo). Then check it from your shell with claude plugin details security-guidance.

Illustration: the /plugin details pane for security-guidance with Will install, Last updated, Context cost, and three scope options

What you will see: ask Claude for a script that reads YAML with yaml.load. The plugin adds a warning, and Claude usually switches to yaml.safe_load.

Share it with your team

Choose project scope, and the plugin is saved in .claude/settings.json, which you commit. Each teammate still installs it once, so put the commands in a setup script:

claude plugin marketplace add anthropics/claude-plugins-official
claude plugin install code-review@claude-plugins-official
claude plugin install security-guidance@claude-plugins-official --scope project

Caveats

  • "Official" does not mean written by Anthropic. 276 entries come from other authors. Hooks and MCP servers run code on your machine, so read Will install first.

  • Some plugins send data out. context7 uses a hosted server. security-guidance sends diffs to a model endpoint. Check this against company policy before you use them in a client repo.

  • Plugins cost tokens. Every enabled plugin adds context. Disable the ones you have not used recently.

  • Auto-update is on for this marketplace. You get fixes fast, but behavior can change without notice.

Sources

  • https://github.com/anthropics/claude-plugins-official (README, marketplace.json entry counts, read 2026-10-27)

  • https://github.com/anthropics/claude-plugins-official/tree/main/plugins/security-guidance

  • https://code.claude.com/docs/en/discover-plugins

  • https://code.claude.com/docs/en/plugins/anthropic-marketplaces

  • https://claude.com/marketplace/plugins

  • GitHub stars, read 2026-10-27: https://github.com/upstash/context7, https://github.com/microsoft/playwright-mcp, https://github.com/github/github-mcp-server

#claude-code#ai#research
Y
Be kind. Markdown supported. · @ to mention
8 plugins worth installing firstTry it in 5 minutesShare it with your teamCaveatsSources

Related posts

Use the Claude Code extension in Cursor? Check your machine for the 2.1.312 / 2.1.313 backdoor in 2 minutes

TL;DR On 2026-10-29, malicious builds of the Claude Code extension (versions 2.1.312 and 2.1.313) were on the Cursor marketplace for about 11 hours. They tried

HLHung LayNov 2, 20261 min
0 0 0

Lock down any MCP server or agent command with one word: Anthropic's srt sandbox, no container needed

TL;DR srt is Anthropic's open-source sandbox CLI, the same engine that Claude Code's /sandbox mode is built on. Put srt in front of any command or local MCP ser

HLHung LayOct 29, 20261 min
0 0 1

Claude Code on Bedrock or Vertex with a custom model name? Keep the full system prompt after the 2.1.312 update with one setting

TL;DR What it is: Claude Code 2.1.312 (released 2026-10-27) now sends a shorter system prompt when your model name is one it does not recognize on Bedrock, Vert

HLHung LayOct 29, 20261 min
0 0 0

Turn Claude Code into a security auditor that checks its own findings: Cloudflare's security-audit skill, installed in 2 minutes

TL;DR What it is: cloudflare/security-audit-skill is one agent skill that makes Claude Code run a six-phase security audit, where a different agent tries to dis

HLHung LayOct 28, 20261 min
0 0 4

More from Hung Lay

Use the Claude Code extension in Cursor? Check your machine for the 2.1.312 / 2.1.313 backdoor in 2 minutes

TL;DR On 2026-10-29, malicious builds of the Claude Code extension (versions 2.1.312 and 2.1.313) were on the Cursor marketplace for about 11 hours. They tried

HLHung LayNov 2, 20261 min
0 0 0

Lock down any MCP server or agent command with one word: Anthropic's srt sandbox, no container needed

TL;DR srt is Anthropic's open-source sandbox CLI, the same engine that Claude Code's /sandbox mode is built on. Put srt in front of any command or local MCP ser

HLHung LayOct 29, 20261 min
0 0 1

Claude Code on Bedrock or Vertex with a custom model name? Keep the full system prompt after the 2.1.312 update with one setting

TL;DR What it is: Claude Code 2.1.312 (released 2026-10-27) now sends a shorter system prompt when your model name is one it does not recognize on Bedrock, Vert

HLHung LayOct 29, 20261 min
0 0 0

Turn Claude Code into a security auditor that checks its own findings: Cloudflare's security-audit skill, installed in 2 minutes

TL;DR What it is: cloudflare/security-audit-skill is one agent skill that makes Claude Code run a six-phase security audit, where a different agent tries to dis

HLHung LayOct 28, 20261 min
0 0 4