22,731 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 43 skills, 9 agents, 12 hooks · 2,645 tokens together
GAIA — Generative AI Interface for Agents. Security-first multi-agent orchestration for Claude Code and OpenCode: reads run free, state changes need approval, irreversible ops blocked.
janegilring/awesome-azure-landing-zones
Skill Claude CodeCodex
Technical skill for deploying an Azure landing zone with the official ALZ Accelerator. Covers the deployment phases (bootstrap → deploy), choosing the IaC variant (Terraform, Bicep on AVM, or Bicep classic), and migrating ALZ-Bicep classic to the AVM Bicep accelerator. Implementation specifics (Bicep/Terraform) live…
EngDawood/emdash-claude-plugin
Plugin Claude Code
Bundles 8 skills, 6 agents, 3 MCP servers · 911 tokens together
Claude Code skills for building, debugging, and deploying EmDash CMS sites on Astro + Cloudflare.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 131 tokens together
Blaxel agent skills and MCP server for building and deploying AI workloads. Includes the Blaxel SDK skill for creating cloud sandboxes and deploying agents, the Blaxel CLI skill for managing Blaxel resources from the command line, and the hosted Blaxel MCP server for managing workspace resources.
MCP server Claude CodeCodexCursor +2
A simple MCP server for Amazon S3 operations. Runs locally from the aws-s3-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Secure SSH gateway for AI assistants — MCP server with connection pooling, session isolation, and command safety. Runs locally from the shuttle-mcp Python package.
Cursor rule Cursor
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
MCP server Claude CodeCodexCursor +2
Assurance for autonomous work: submit a run, get the case a person decides from - what needs a human, what would resolve it, and what was never assessed. Runs locally from the release-gate Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Run arbitrary JavaScript inside disposable Docker containers and install npm dependencies on the fly. Runs locally from the node-code-sandbox-mcp npm package.
Skill Claude CodeCodex
Turn a natural-language cloud architecture description into an editable diagram whose nodes are official vendor service icons (Azure, AWS, GCP, Kubernetes), exported as PDF, draw.io, or VSDX (Lucid-importable). Use when the user asks to draw, diagram, or visualize a cloud/system architecture, or to produce a…
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 324 tokens together
Governed Proxmox VE VM/container ops — 43 MCP tools with audit, budget, undo & risk-tier guards.
MCP server Claude CodeCodexCursor +2
Unified MCP server for Kubernetes, ArgoCD, Prometheus, PagerDuty, and Loki. Runs locally from the @notharshhaa/devops-mcp npm package. Needs 9 environment variables to run.
helbertparanhos/easypanel-mcp-server
Skill Claude Code
Workflow de deploy e gestão do Easypanel via MCP. Use sempre que o usuário pedir para fazer deploy, gerenciar projetos/serviços, configurar GitHub auto-deploy, checar logs, alterar env vars ou verificar status no Easypanel. Triggers: /ep, 'fazer deploy', 'deployar', 'redeployar', 'subir no easypanel', 'checar logs do…
MCP server Claude CodeCodexCursor +2
An MCP server for TacticalRMM, with an out-of-band human approval gate for privileged actions. Runs locally from the trmm-mcp Python package. Needs 4 environment variables to run.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 214 tokens together
Multi-step workflow orchestration for VMware MCP skills with approval gates and rollback.
Skill Claude Code
The llama-swap operations console — durable history, drain-aware control, and measurement commands with three specific guarantees: keep-set unloads are refused statically by id AND alias (never from server ttl), --drain fails closed when slot state is unreadable, and fit/ctx refuse to answer inside their uncertainty…
Skill Claude Code needs its repo
Creates cloud sandboxes and deploys apps with the lizard CLI. Sandboxes run untrusted or AI-generated code and give an agent its own computer: shell, files, HTTPS URLs for ports, a desktop and browser for computer use, and Claude Code or Codex in the cloud. Deploys cover apps, agents, workers and managed databases…
ahmedawan-oracle/claude-code-plugins
Plugin Claude Code
Bundles 10 skills, 4 commands, 2 agents · 1,249 tokens together
Drive the Oracle AI Data Platform (AIDP) Databricks Migration Toolkit in natural language. Self-contained — the full Python engine (scripts/, aidpcompat/) ships bundled under engine/ and is invoked from skills via ${CLAUDEPLUGINROOT}/engine/scripts/. Teaches Claude how to plan and execute an automated end-to-end mig.
Plugin Claude Code
Bundles 1 skill, 2 commands · 293 tokens together
Set up, run, and troubleshoot a self-hosted Dograh voice-AI deployment (Docker, local or remote).
Skill Claude Code
Deploy the engineering service to production.
Skill Claude CodeCodex
Manage DNS records, domains, mailmaps, and nameservers via the easyDNS REST API.
Skill Claude CodeCodex
Set up, upgrade, operate, and diagnose Hot Updater projects. Use for provider infrastructure setup or upgrades, server template extraction, deployment, delivery policy, rollback, promotion, Bundle inspection, patching, Storage cleanup, channels, signing keys, API keys, Remote Config templates, Insights reads such as…
Skill Claude CodeCodex
Use when reviewing production readiness, resilience, failure modes, or reliability of code, services, or system designs. Trigger for requests about error handling, retries, timeouts, circuit breakers, graceful degradation, observability, DR/RPO/RTO, abuse resilience, quota exhaustion, production architecture…
Plugin Claude Code
Bundles 1 skill, 8 commands, 3 agents · 379 tokens together
Full lifecycle nginx hardening: audit configs, analyze logs, generate rules, respond to IoCs, deploy and monitor.
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: