Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,374 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex needs its repo
Use when (re)indexing a Sweet Search project. Runs the full-profile indexer with GPU model prewarming (CoreML cascade on M3+, candle Metal on M1/M2, ORT CPU elsewhere), kills ORT CPU models during indexing to avoid memory contention, and rewarms them for query readiness on completion. Incremental runs under 20 files…
Shellishack/agent-arena-online
Skill Claude CodeCodex
Start an Agent Arena Online local client agent runner. Use when the user provides an AAO join prompt such as "Join this AAO session " or wants Codex/Claude Code to join and play through the local client, which owns the AAO backend WebSocket and invokes the local CLI on arena events.
Skill Claude CodeCodex
Use when starting ANY conversation. Mandatory: activate 10x. Governs project memory, ambiguity, records, tickets, subagents, evidence, review, closure, and retrospective learning.
Skill Claude CodeCodex needs its repo
Bug bounty findings secretary, tracker, and workspace initializer for the bb-huge portal. Use this skill for web security research, vulnerability hunting, and hunt workspace setup. Triggers on: "log finding", "save finding", "add to bb-huge", "record vulnerability", "update finding", "show findings", "bb-huge stats"…
lucasrosati/claude-security-agents
Agent Claude Code
Defensive security specialist. Use to apply vulnerability fixes, security hardening, security headers implementation, rate limiting, and automated security tests. Works on top of red-team-scanner reports.
Neverlow512/agent-droid-bridge
MCP server Claude CodeCodexCursor +2
MCP server giving AI agents eyes and hands inside Android devices via ADB. Runs locally from the agent-droid-bridge Python package. Needs 16 environment variables to run.
Skill Claude Code
Author, edit, and render deterministic .zen design documents (posters, decks/slides, social graphics, flyers, books, magazines, diagrams, ads) with the zenith CLI. Use when the task is to create or change a visual design as structured, editable, version-controllable source — not a flat AI image. Covers: design tokens…
Plugin Claude Code
Bundles 42 skills, 4 agents, 6 hooks · 2,051 tokens together
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.10.8,<0.11.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Plugin Claude Code
Bundles 1 skill · 50 tokens together
AI-Driven Development Lifecycle - a structured, adaptive software development methodology guided by AI.
scholarly360/owasp-top10-web-skills
Skill Claude CodeCodex
Expert Python security testing skill for OWASP A05:2025 — Injection vulnerabilities in FastAPI and Flask applications. Use this skill whenever the user asks about: SQL injection, XSS, SSTI (Server-Side Template Injection), OS command injection, ORM injection, LLM prompt injection, input validation, parameterized…
Skill Claude CodeCodex
A guide for using Seedream, an image-generation service, through MCP, a standard way for AI assistants to use external tools. It covers text-to-image, image editing, combining references, sequential image sets, saved-image browsing, and some layer-splitting workflows.
xaviviro/Opendata.cat-MCP-Server
Skill Claude CodeCodex
Useu quan calgui respondre una pregunta amb dades obertes catalanes (15 portals — Generalitat, Barcelona, Diba, AOC, Reus, Girona, FGC, Idescat, Renfe, INE, REE, CNMC, CORA, Catalònica) amb les eines del servidor MCP opendata.cat (searchdatasets, getdatasetinfo, listdatasetfields, querydataset, relateddatasets).…
MCP server Claude CodeCodexCursor +2
MCP server for Cucumber Studio - test scenarios, action words, and execution data. Runs locally from the cucumberstudio-mcp npm package.
Skill Claude CodeCodex
Una guia sobre la configuració i l'arquitectura de TanStack Router, la biblioteca que gestiona les rutes d'una aplicació web.
Skill Claude CodeCodex
Compose multi-agent systems with SequentialAgent, ParallelAgent, and LoopAgent. Use when building agent pipelines, parallel workflows, or iterative loops.
Skill Claude CodeCodex
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
Plugin Claude Code
Bundles 1 skill · 51 tokens together
Skill marketplace for AI agents. Search, download, and install from 70+ skills. One subscription, unlimited tools.
Plugin Claude Code
Bundles 13 skills, 9 commands, 11 agents, 2 hooks · 1,682 tokens together
Comprehensive Frappe/ERPNext full-stack development with DocType scaffolding, bench integration, and specialized agents for server-side Python, client-side JavaScript, and ERPNext customization.
mathruffian-dot/claude-html-slide-builder
Skill Claude CodeCodex
A tool that turns teaching material—such as text, course outlines, PDFs, lectures, or spoken topics—into interactive Reveal.js HTML presentations. Reveal.js is a web presentation framework.
Skill Claude CodeCodex
A set of ideas attributed to Dan Koe about running a one-person business, writing, focus, personal growth, digital work, and how people think. It is based on 3,378 original posts, according to the description.
manthanpatelll/claude-code-starter
Plugin Claude Code
Bundles 1 command · 18 tokens together
Example plugin: a deploy + release workflow bundled as one installable package. Commands are namespaced (e.g. /deploy:release).
MCP server Claude CodeCodexCursor +2
MCP server "spotdb" as configured in aliengiraffe/spotdb. Runs in Docker (docker.io/aliengiraffe/spotdb:0.1.0). Needs 1 environment variable to run.
Skill Claude CodeCodex
Elite programming cognitive architecture. Enforces deep multi-pass reasoning, rigorous architectural planning (Stage Maps), scope-controlled execution, test-driven development, verifiable quality checks, self-critique, error recovery strategies, parallel delegation with graceful degradation, context efficiency, and…
Skill Claude CodeCodex
Implement Clean Architecture with domain, application, and infrastructure layers. Use when creating modules, organizing code in layers, separating business rules from infrastructure, or structuring a new project.
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: