Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 381,711 indexed, measured the same four ways as everything else here.

repo-hygiene

32186

gg-mo/repo-hygiene

Plugin Claude Code

Bundles 9 skills, 1 hook · 466 tokens together

Skills that keep a codebase healthy as agents work in it: repo orientation, docstring discipline, doc freshness, test coverage for new code, and pre-commit verification gates.

not rated 3 5mo ago A tokens not measured original MIT

ultra-research

32187

r-ichard/ultra-research

Plugin Claude Code

Bundles 1 skill · 138 tokens together

Faithful web research → a folder of clean markdown (aggregation, not synthesis). Claude browses, judges each page, and keeps only the good ones. First run silently installs a headless browser (200MB) under /.local/share/ultra-research.

not rated 3 2mo ago A tokens not measured original MIT

consensus-review

32189

akholod/consensus-review

Plugin Claude Code

Bundles 8 commands, 5 agents · 444 tokens together

Two code-review strategies sharing one contract: /consensus-review (parallel multi-source panel with an Opus arbiter, codex consultant and strict sceptic) and /loop-review (sequential coverage-directed passes with evidence-backed cells and a CLEAN verdict enforced in code). Strictly read-only.

not rated 3 changed 2d ago A tokens not measured original MIT

playwright-for-android

32190

fclab-skku/playwright_for_android

Plugin Claude Code

Bundles 1 skill · 97 tokens together

MCP version of the Android debug skill. Exposes adb / emulator / logcat / screenshot / UI-tree as MCP tools; the host LLM (Claude Code) selects each UI action itself. No separate LLM API key required.

not rated 3 3mo ago A tokens not measured original MIT

sip

32191

piyushkhemka/sip

Plugin Claude Code

Bundles 1 command · 21 tokens together

Every prompt takes a sip 💧 — a fun Claude Code status line showing how much water talking to Claude costs, plus cost, 5h/weekly usage (mirrors /usage), context, model & effort, and turn count. All local, all free.

not rated 3 3mo ago A tokens not measured original MIT

metis-plan-task

32192

gsaranti/pantheon

Skill Claude Code

Produce an implementation plan for a free-text task description. Plan stays in chat.

not rated 3 1mo ago A 21 tokens original MIT

beadle-dev

32193

punt-labs/beadle

Plugin Claude Code

Bundles 5 commands, 2 hooks · 38 tokens together

Autonomous agent daemon with cryptographic owner control. Email communication via IMAP/SMTP with PGP trust model.

not rated 3 4d ago A tokens not measured original MIT

ralphex

32194

salmundani/ralphex

Plugin Claude Code

Bundles 3 skills · 58 tokens together

ralphex. Ralphex is a Claude Code plugin that uses Claude Code as planner + implementer, and Codex as code reviewer.

not rated 3 4mo ago A tokens not measured copy · 86% MIT

yaml-lsp

32195

zircote/yaml-lsp

Plugin Claude Code

Bundles 1 command · 8 tokens together

YAML language server plugin for Claude Code with yaml-language-server integration and automated hooks for validation and formatting.

not rated 3 2mo ago A tokens not measured original MIT

scout

32197

shidoyu/scout

Plugin Claude Code

Bundles 3 skills, 1 MCP server · 126 tokens together

Web research plugin that thinks before it searches. Query design, multi-engine search, privacy-aware fetching.

not rated 3 4mo ago A tokens not measured original MIT

automation-helper

32200

MacroMan5/AutomationHelper_plugins

Plugin Claude Code

Bundles 6 skills, 5 agents · 2,190 tokens together

AI assistant for Power Automate and n8n workflows. 6 skills in active development: design, build, debug, quick-fix, refactor, and validate. Documentation-driven approach (no hallucinations). Contributions welcome!

not rated 3 11mo ago A tokens not measured original MIT

greybeard

32202

ManojLingala/greybeard

Skill Claude CodeCodex

Makes your AI agent defensive about the backend failure modes that page you at 3am. Before writing server-side code, the agent stops at a ladder of hard-won rules — money as integer minor-units, idempotent mutations, timeouts and backoff on every external call, explicit transaction boundaries, no N+1 queries…

not rated 3 14d ago A 109 tokens original MIT

clear

32205

QBall-Inc/clear

Plugin Claude Code

Bundles 15 skills, 3 agents, 7 hooks · 686 tokens together

Context Layered Engineering for Agentic Resources - Persistent memory and intelligent context management for Claude Code sessions.

not rated 3 3mo ago A tokens not measured original Apache-2.0

agentic-ml

32206

lawwu/agentic-ml-plugin

Plugin Claude Code

Bundles 15 skills · 1,409 tokens together

Skills for machine learning workflows: monitoring training runs, debugging models, and managing experiments.

not rated 3 7mo ago A tokens not measured

hotwire-codex-skills

32208

davidteren/hotwire-codex-skills

Plugin Claude Code

Bundles 8 skills · 907 tokens together

Unofficial skillset inspired by The Rails and Hotwire Codex (by Ayush Newatia), published with the author's permission. Skills and runnable checkers for Rails + Hotwire apps that ship to web/PWA, iOS, and Android. Unique vs other Rails plugins (which are LLM coders/reviewers): every skill ships a deterministic…

not rated 3 3mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: