38,381 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
DayronDLR/sap-enterprise-stack-plugin
Plugin Claude Code
Bundles 38 skills, 19 commands, 6 agents, 7 hooks, 5 MCP servers, 10 plugins · 2,946 tokens together
SAP Enterprise Agent Stack — 11 agentes especializados (ABAP, CAP/BTP, Fiori, HANA, Integration, Basis, Migration, QA, DevOps, Requirements, Docs), gates de Definition of Done, y MCP servers SAP. Orquestador SAP como skill.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Installs agentic engineering practices into a project's CLAUDE.md as permanent coding standards.
Plugin Claude Code
Bundles 2 skills · 173 tokens together
Bridge plugin that automatically delegates OpenSpec planning artifacts to Oh My ClaudeCode execution modes. Provides quick (simple tasks → autopilot) and deploy (complex tasks → team/ralph).
Plugin Claude Code
Bundles 6 commands, 4 agents, 1 MCP server · 265 tokens together
AI orchestration tool for Claude Code — GSD management shell + Superpowers quality core.
Plugin Claude Code
Bundles 2 skills, 6 agents · 246 tokens together
Don't free-solo your code. Let Sherpai guide the climb.
Plugin Claude Code
Bundles 1 skill, 11 agents, 3 hooks · 954 tokens together
Model multiplexer: keep an expensive orchestrator (Fable) but route subagent work to the cheapest model that can do the job (Opus, Sonnet, Haiku, or external models via Codex/Gemini CLIs).
Plugin Claude Code
Bundles 4 commands, 4 agents · 159 tokens together
Semantic knowledge extraction and context enrichment for Claude Code - automatically analyzes codebases to provide intelligent coding context, architectural boundaries, and guardrails.
Plugin Claude Code
Bundles 21 skills, 16 agents, 1 hook, 1 MCP server, 1 plugin · 1,505 tokens together
Project-aware Karpathy-style knowledge base for agentic coding tools: 21 prompt-only skills (wiki-, proj-, using-skillwiki, skillwiki-mcp) backed by the deterministic skillwiki CLI.
Plugin Claude Code
AI-DLC workflows packaged as a Claude Code plugin.
Plugin Claude Code
Bundles 10 skills · 414 tokens together
Knowledge-Graph-Driven Development (KGDD) workflow for AI Agents. Models product requirements (PRD) and implementation plans (Plan) as structured Node/Edge/Fact graphs, with full spec traceability, automated review, multi-Agent execution, testing, visualization, and a built-in design system.
Plugin Claude Code
Bundles 3 skills, 1 hook · 174 tokens together
AI agent skill builder and validator — create and validate SKILL.md files following the Anthropic agent skill specification.
Plugin Claude Code
Bundles 17 skills, 2 MCP servers · 1,864 tokens together
A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect, agentic-systems architect (ADK / Agent Runtime / MCP / A2A / AP2), plus security, SRE, and QA — wired into a design-first, security-first delivery gate. Eleven service skills (Cloud Run, GKE, IAM, BigQuery…
Plugin Claude Code
Bundles 6 skills, 13 commands, 2 hooks · 267 tokens together
Prompt planner and validator for ralph-loop — transforms vague tasks into battle-tested autonomous development prompts.
Plugin Claude Code
Bundles 10 skills, 12 commands, 5 hooks · 1,199 tokens together
Proactive technology mentor, security advisor, and prompt coach for Claude Code. Catches bad practices, advises on architecture decisions, and coaches better prompting.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 agent · 380 tokens together
Delegate coding tasks to OpenAI Codex CLI as a fast build agent. Supports non-interactive execution with configurable reasoning levels and parallel task dispatch.
JaimeCernuda/ralph-wiggum-crossplatform
Plugin Claude Code
Bundles 3 commands, 1 hook · 25 tokens together
Cross-platform Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion. Uses Python for cross-platform compatibility.
strigov/superpowers-strigov-ver
Plugin Claude Code
Bundles 16 skills, 1 command · 995 tokens together
Personal fork of superpowers for strigov: multi-model dev orchestrator on the GPT-5.6 family — Sonnet main thread orchestrates (triage, dispatching, polling, git); an Opus subagent at max thinking effort writes the plan and its authorized revisions; Codex Sol max reviews the plan (loop cap=4, fresh task each round…
Cursor rule Cursor
Meta-rule that instructs every LLM-powered agent how to write, store, and compile new “source-of-truth” rules. All new rules must live in ./agent-rules/ as Markdown files with the same front-matter structure shown here. After a rule is added or changed, the agent must run ./translaterules.ts to regenerate…
Skill Claude CodeCodex
TLAE (Tech Lead Agentic Engineering) . use this skill when working on software projects. It turns Claude into a disciplined Tech Lead that adapts to YOUR stack, YOUR risk profile, and YOUR domain. Auto-detects language, framework, package manager, and tests on first use; asks 3 short questions about team size, domain…
Skill Cursor
Coordinate RIPER phase flow for non-trivial changes and enforce evidence-first handoffs across research, planning, execution, and review.
Muhammad-Qasim-Munir/skillguard
Skill Claude CodeCodex
Review Claude/Cursor Skills for security issues (prompt injection, agentic/tool injection, data exfiltration, unsafe automation). Use when evaluating a Skill package/folder or SKILL.md + bundled scripts for risks like hidden instructions, tool misuse, credential theft, network exfil, destructive commands, and policy…
Skill Claude CodeCodex
Connect WhatsApp phone control (user-run login + watch + Cursor CLI agent) or Slack MCP. Always ask owner number. Never run QR/login/watch yourself — give commands. After Pinky install channel ask, or /agent-channels / connect WhatsApp.
Plugin Claude Code
Bundles 1 skill, 4 commands, 12 agents · 1,051 tokens together
Self-improving, spec-driven multi-agent delivery framework as a plugin. v2 adds the self-improvement layer: acceptance-method escrow, three-valued gates (NOT-EARNED), process-health ledger, correction intake, lessons library, factory-integrity lock, and the visual-parity playbook (multi-layer L1-L5 acceptance…
MCP server Claude CodeCodexCursor +2
MCP server "cursor-mcp-installer" as configured in Gnayiak/cursor-mcp-installer. Runs locally from the @anaisbetts/cursor-mcp-installer npm package.
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: