38,215 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.
Plugin Claude Code
Bundles 1 skill · 44 tokens together
Generate self-updating CLI repos from API documentation URLs. Produces Node.js CLIs with agent framework wrappers, smoke tests, and a self-learning knowledge system.
Plugin Claude Code
Bundles 23 skills, 19 commands, 6 agents · 1,906 tokens together
Plugin for effective agentic development.
ContextJet-ai/awesome-llm-observability
Plugin Claude Code
Bundles 26 skills · 2,363 tokens together
26 Agent Skills (several with runnable, unit-tested scripts) for building, evaluating, securing, and monitoring reliable LLM & AI-agent apps.
FlyFission/nuclear-grade-context-engineering
Plugin Claude Code
Bundles 29 skills, 28 commands, 5 agents · 2,677 tokens together
Risk-graded context engineering for AI-assisted software work — a catalog of agent skills, paste-ready command prompts, and change-record templates that keep agent work questioned, controlled, and reviewable.
Plugin Claude Code
Bundles 5 skills · 138 tokens together
Skills for creating, testing, packaging, publishing, auditing, and visualizing skill libraries.
MCP server Claude CodeCodexCursor +2
The infrastructure for the AI economy: primitives for inference, agents, and decisions. Remote server at mcp.carbonarc.ai.
Cursor rule Cursor
Discover and use MCP tools via the mcpx CLI.
machinesoul11/anti-sycophant-ai-agent-skills
Plugin Claude Code
Bundles 3 skills, 2 commands · 690 tokens together
Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.
MCP server Claude CodeCodexCursor +2
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. Runs locally from the @agentkitai/agentgate-mcp npm package.
Skill Claude CodeCodex
Use proactively when a user is defining, constraining, debugging, or evaluating an agent system and needs the right PromethOS skill.
Plugin Claude Code
Bundles 6 commands, 3 hooks · 116 tokens together
A living, annotated architecture map for AI-built projects.
sibilleb/AAP-Enterprise-MCP-Server
Cursor rule Cursor
Enhanced Ansible best practices with comprehensive MCP server integration for AI-assisted automation. This guide extends standard Ansible practices with Model Context Protocol (MCP) server capabilities for Ansible Automation Platform (AAP), Event-Driven Ansible (EDA), and ansible-lint code quality assurance through AI…
Skill Claude CodeCodex
An operating guide for using the AIRP MCP server, a tool service that helps AI agents manage role-playing sessions. The server stores session data, while the agent handles reasoning, storytelling, and character acting.
Skill Claude CodeCodex
Delegate a task to an autonomous H Company agent (Holo-powered web surfer and computer-use agents) through the hai-agents MCP server. Use to offload open-ended browser or research work that the agent should carry out end to end on its own infrastructure, then report a final answer. Runs remotely, so it is the right…
Command Claude Code needs its repo
Deep quality audit of all skills, agents, and commands for inconsistencies, gaps, duplication, and token waste.
Plugin Claude Code
Bundles 21 skills · 1,220 tokens together
teneo-skills. Teneo Protocol AI agent skills for Claude Code and AI coding assistants.
soupandpsy/amazing-psycoder-skills
Skill Codex
A coordinator for Amazing PsyCoder, a system that turns psychology experiments or experimental data into reviewed code and analysis materials. It sends each request through design, coding, and review stages when the available input requires them.
frank-luongt/faos-skills-marketplace
Plugin Claude Code
Bundles 14 skills, 8 commands · 0 tokens together
🤖 AI Engineer — AI Engineer + LLM Systems Specialist.
Manikantareddy941-hash/-caveman
Plugin Claude Code
Bundles 6 skills · 457 tokens together
Ultra-compressed communication mode. Cuts 75% of tokens while keeping full technical accuracy by speaking like a caveman.
Plugin Claude Code
Bundles 122 skills, 76 agents · 13,415 tokens together
361 agentic skills across 65 domains, 72 agent personas, and 17 team compositions following the agentskills.io open standard.
Plugin Claude Code
Bundles 32 skills, 2 commands, 89 agents, 6 hooks · 10,054 tokens together
Framework for behavior and workflow guardrails with knowledge accrual.
Plugin Claude Code
Multi-stack AI-assisted SDLC pipelines for Claude Code. Stack Provider Pattern: core owns the pipeline, framework plugins register themselves via stack.md profiles.
DeployFaith/hermes-bible-skill
Skill Claude CodeCodex
Use when the user asks for community Hermes Agent knowledge: hidden features, real-world workflows, SOUL.md patterns, delegation/Kanban/cron patterns, or examples of how people use Hermes. Complements hermes-agent; official docs remain source of truth for commands and setup.
Plugin Claude Code
Bundles 13 skills · 946 tokens together
Focused skills for capable coding agents: design exploration, research, planning, implementation, multi-agent coordination, independent review, prose editing, memory, Git, terminal UI, and delegated image generation.
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: