Command
Implement Graphql Api
Implement GraphQL API with comprehensive schema, resolvers, and real-time subscriptions
setup1 file · MIT
AI Plugins
Claude Code agents, commands, MCP configs and hooks. Formats vary—not every entry is a native plugin.
Community source · Runtime untested. Licenses are included. Review scripts and hooks before installing; integrations may need your own keys or paid services. Browsing does not install or run tools.
Claude Code Templates ↗1,034 components · page 16 of 35
Agent
Implementation Plan
Generate an implementation plan for new features or refactoring existing code.
expert advisors1 file · MIT
Sandbox configuration
IMPLEMENTATION SUMMARY
A sandbox configuration for cloudflare workflows.
cloudflare1 file · MIT
Agent
Incident Responder
Use this agent when an active security breach, service outage, or operational incident requires immediate response, evidence preservation, and coordinated recovery. Specifically:\n\n \nContext: Your production database has gone offline and customers are experiencing service failures.\nuser: "Our database is down and affecting all users. We need to respond immediately."\nassistant: "I'll activate the incident-responder agent to manage this service outage - we'll assess severity, mobilize the resp
devops infrastructure1 file · MIT
Agent
Incident Responder
Handles production incidents with urgency and precision. Use IMMEDIATELY when production issues occur. Coordinates debugging, implements fixes, and documents post-mortems.
security1 file · MIT
Command
Init Project
Initialize new project with essential structure, configuration, and development environment setup
project management1 file · MIT
Command
Initref
A command for utilities workflows.
utilities1 file · MIT
Command
Interactive Documentation
Use PROACTIVELY to create interactive documentation platforms with live examples, code playgrounds, and user engagement features
documentation1 file · MIT
Mod
Invaders
Space Invaders above the Claude Code prompt: shoot each wave before it lands. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs an interactive terminal with a mouse.
games9 files · MIT
Agent
Ios Developer
Native iOS development specialist with Swift and SwiftUI. Use PROACTIVELY for iOS applications, UIKit/SwiftUI components, Core Data integration, app lifecycle management, and App Store optimization.
development team1 file · MIT
MCP configuration
Ios Simulator Mcp
Control iOS Simulator directly from Claude Code. Launch apps, take screenshots, manage device states, and streamline mobile development workflows.
devtools1 file · MIT
Agent
Iot Engineer
Use when designing and deploying IoT solutions requiring expertise in device management, edge computing, cloud integration, and handling challenges like massive device scale, complex connectivity scenarios, or real-time data pipelines. Specifically:\n\n \nContext: A smart city project needs to deploy 50,000 sensors across a metropolitan area with cellular and LoRaWAN connectivity, requiring edge processing to reduce cloud costs and real-time anomaly detection.\nuser: "We're building a smart city
programming languages1 file · MIT
Command
Issue To Linear Task
Convert individual GitHub issues to Linear tasks with comprehensive data preservation
sync1 file · MIT
Command
Issue Triage
Intelligent issue triage with automatic categorization, prioritization, and team assignment
team1 file · MIT
Agent
It Ops Orchestrator
Use for orchestrating complex IT operations tasks that span multiple domains (PowerShell automation, .NET development, infrastructure management, Azure, M365) by intelligently routing work to specialized agents. Specifically:\n\n \nContext: An organization needs to audit stale Active Directory users and then disable them in a safe manner.\nuser: "We need to find all inactive AD users from the last 90 days and disable them. I want enumeration of users, a safety check before disabling, and a clear
expert advisors1 file · MIT
Agent
Janitor
Perform janitorial tasks on any codebase including cleanup, simplification, and tech debt remediation.
expert advisors1 file · MIT
Agent
Java Architect
Use this agent when designing enterprise Java architectures, migrating Spring Boot applications, or establishing microservices patterns for scalable cloud-native systems. Specifically:\n\n \nContext: A team needs to refactor a monolithic Spring application into microservices with proper service boundaries and inter-service communication.\nuser: "We need to design a microservices architecture for our legacy Spring Boot monolith with 15 services. Current bottlenecks are the shared database and tig
programming languages1 file · MIT
Agent
Java Mcp Expert
Expert assistance for building Model Context Protocol servers in Java using reactive streams, the official MCP Java SDK, and Spring Boot integration.
web tools1 file · MIT
Agent
Javascript Pro
Use this agent when you need to build, optimize, or refactor modern JavaScript code for browser, Node.js, or full-stack applications requiring ES2025 features, async patterns, or performance-critical implementations. Specifically:\n\n \nContext: User has a legacy callback-based Node.js service and wants to modernize it with async/await, implement proper error handling, and optimize memory usage.\nuser: "I have an old Node.js service with callback hell. Can you refactor it to use modern async/awa
programming languages1 file · MIT
Project template
Javascript Typescript
Javascript-Typescript project template
languages26 files · MIT
Mod
Jev Auto Mode
A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers can go to TypeSafe's Jev, which judges the action against your latest request with thresholds you set. Claude can never edit the policy.
security9 files · MIT
Mod
Jev Guardrails
Screens every prompt going into the conversation and every reply coming out of it with TypeSafe's Jev, a System One decision model, the way TypeSafe's guardrails cookbook does: one request per message asks a battery of hazard questions (jailbreak, harm or a crime, a diagnosis or a dosage, self-harm) and scores how much harm complying would do. The thresholds live here, in a named policy (strict or permissive), and turn the probabilities into pass, review (the user is asked), block (the prompt is
security6 files · MIT
Mod
Jev Model Router
Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.
productivity6 files · MIT
Mod
Jev Skill Suggestion
Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at all, a second re-reads the top three with their SKILL.md and can reject them all. The winner's SKILL.md is attached to the prompt, so the skills can be hidden from the model altogether (/jev-skill-suggesti
productivity7 files · MIT
Mod
Jev Skill Typeahead
Shows, while you type, the skills and subagents Claude will probably call for your prompt: reads the draft on every edit and lists them in the band above the prompt, ranked by keyword match (English or Spanish). When you pause, Jev (TypeSafe's decision model) decides which one will be called and the band marks it. Slash commands are left out, since you run those yourself. Without a Jev key it stays on the instant local match.
productivity9 files · MIT
Mod
Jev Vercel Sandbox
A Vercel Sandbox Claude sends work to on purpose: long test runs in the background, someone else's repository, an installer of unknown origin, a bulk change to preview as a patch, a clean build. TypeSafe's Jev reads each Bash command and spots those jobs; by default you are asked whether it runs in the sandbox or locally (confirmSandbox), or it always goes to the sandbox with the question off. Claude also gets sandbox_run, sandbox_jobs, sandbox_result and sandbox_apply. Each job starts from the
security10 files · MIT
MCP configuration
Jfrog
JFrog MCP Server: providing your agents with direct access to JFrog Platform services.
devtools1 file · MIT
Agent
Jfrog Sec
The dedicated Application Security agent for automated security remediation. Verifies package and version compliance, and suggests vulnerability fixes using JFrog security intelligence.
security1 file · MIT
MCP configuration
Jina Ai
Official Jina AI MCP Server for web reading, search, grounding, and fact-checking capabilities powered by Jina AI APIs.
devtools1 file · MIT
MCP configuration
Jupyter
Model Context Protocol server for Jupyter notebooks. Execute code, manage notebooks, and interact with Jupyter kernels directly from Claude.
devtools1 file · MIT
Choose the files that fit your workflow
Skills package reusable instructions with supporting resources. Agents describe a specialist role, commands define a repeatable request, and MCP configurations connect a compatible client to an external service. Hooks and settings change project behavior. Inspect the actual format before adding it to your project; this catalog does not imply compatibility with every AI assistant.
Downloads preserve the original source and license notices. Keep those notices when adapting a bundle. Use source control to review changes, keep credentials outside the downloaded files, and test in a disposable project before enabling hooks or external services.