Enables AI agents and IDE assistants to run zero-config security audits, detect secrets and vulnerable dependencies, and apply adversarial verification to reduce false positives.

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.

Enables agents to reach pump.fun's full API surface — official developer routes, bonding-curve reads, Solana RPC, and unsigned trade building — by writing JavaScript against one merged OpenAPI document, using just two tools (search and execute). Model-authored code runs in a network-less sandbox, so multi-step questions resolve in a single round trip while credentials stay on the host Worker.

Connects MCP-compatible AI clients to a university Moodle campus locally so users can query courses, assignments, materials, grades, forums, and calendar events, including reading attachments and PDFs. It is a read-only beta that does not modify the campus or store passwords.

Frontier model solution tracing, then made the prompting skills so Sonnet, GPT, DeepSeek, GLM, Kimi, ETC models work like that

Enables AI clients to create passwordless document intake requests with itemized checklists, dispatch secure upload links, and track completion status. Also supports reviewing and approving or rejecting uploaded files, fetching short-lived download links, and managing client records and reusable checklist templates.

Enables MCP clients to run provider-backed reverse-engineering and software-analysis workflows for source code, binaries, and architecture, with evidence, limits, and optional external tool integrations.

AI agent skills for production grade applications

Claude Code skill: replicate a reference Word (.docx) typography onto new content via HTML bridge — browser render → clipboard → Word paste. Append-mode preserves page setup / styles / theme / headers 100%. macOS only.

Enables Antigravity to delegate concrete local coding tasks to Codex CLI with durable sessions, background execution, native chat links, and event-driven receipts.

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.

🎨 Open-source design MCP server + shadcn/ui registry — AI design systems for Claude Code, Cursor, Codex, GitHub Copilot & any MCP client. 31 brand-grade themes (Linear, Stripe, Vercel, Notion, Apple, Supabase, Figma…) + design tokens, UI principles & WCAG rules. Install any component with one command.

Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough, and known-good markers — as a CLI and as an MCP server.

Claude Cup — worldwide building contest. Track your Value/Token Ratio, climb the real-time leaderboard, and fill a live trophy in your terminal.

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

Awesome Claude Mods — evidence-graded index of Claude Code mods, plugins and hooks. 20 languages, rebuilt every 2 hours.

Exposes a single tool, generar_cierre(usuario), that reads the last three days of a public GitHub user's activity and returns a roughly forty-word end-of-day script covering what was closed, what is still open, and where to start tomorrow, including why the oldest open PR is stuck. Callable from Cursor, OpenCode, Claude Code or any MCP client, unlocked with a one-time x402 license token passed as an x-license header.

Enables AI clients and CLI users to query and modify multiple MySQL data sources routed by project and environment, with explicit environment binding, server-side read-only enforcement, hot-reloaded web configuration, and SQL execution auditing.

Enables MCP clients to retrieve mid-band account summaries, quarterly reviews, upgrade-path eligibility, and priority artifact access for a named-relationship retainer.

Read-only MCP tools for querying USDA FAS Global Agricultural Trade System census export and import records by partner country, year, month and HS10 code prefix, plus the release-date lists for each flow. Results are capped with notes on omitted rows, and responses carry release vintages and retrieval metadata.

Lets Claude or any MCP client inspect a TP-Link Deco mesh locally — nodes, backhaul, clients, WAN, firmware — and carefully change settings with graded, read-back-verified writes, secrets redacted by default and an optional read-only mode. No cloud or app involved.

CLI and MCP server for driving the Unreal Engine 5 editor with AI — create and edit materials, blueprints, Niagara, PCG, StateTrees, data tables, widgets, and Enhanced Input. Single Go binary, no Python, no dependencies.

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.