codex Tools

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

This is a library of 50 open-source marketing skills for AI agents like Claude Code, Codex, and Cursor. It solves the problem of democratizing advanced marketing expertise—like CRO, SEO, and analytics—by encoding it into skills AI agents can use. It's built for technical marketers, growth engineers, and founders who want to leverage AI for scalable marketing execution.

Build a custom Codex Desktop theme from any image with a free browser-local builder. Preview five workspace views, check readability, and export data-only files with no sign-up or image upload.

Humanizer is an agent skill that transforms AI-generated writing by removing robotic patterns and unnatural phrasing. It solves the problem of content that feels artificial, helping writers, marketers, and developers produce text that resonates with human readers. This tool is ideal for anyone using AI assistants who needs polished, natural-sounding output for blogs, emails, or communications.

Atlas is a native macOS editor built to manage the work around coding—research, planning, and knowledge—alongside the AI agent threads that turn them into commits. It solves the problem of fragmented workflows by providing a unified planning surface where teams of humans and multiple AI agents can collaborate efficiently. It's for developers and engineering teams who use AI coding assistants like Claude, Codex, and Gemini and want to coordinate their work in a single, local-first application.

Router is a model router for agentic systems that intelligently directs each prompt to the most cost-effective model capable of handling the task, typically in under 50ms. It solves the problem of overspending on expensive frontier models for simple coding prompts, allowing engineering teams to maintain quality while dramatically reducing token spend. It's designed for developers and organizations using AI coding assistants like Claude Code, Codex, and Cursor who want to optimize their AI infrastructure costs without changing their workflow.

Archify is an agent skill that transforms plain English descriptions of systems into beautiful, interactive HTML diagrams. It solves the problem of creating and maintaining accurate, up-to-date architecture, workflow, and sequence diagrams by generating them directly from conversation. It's for developers, architects, and teams who need to quickly visualize, share, and verify system designs with motion, exploration, and crisp export built-in.

Hermes Agent is a persistent, multi-platform AI assistant that grows with you. It solves the problem of fragmented AI tools by providing a single agent with unified memory that works across Telegram, Discord, Slack, CLI, and more. It's for developers, teams, and power users who need an automated assistant that remembers context, schedules tasks, delegates work, and securely browses the web—all from one intelligent core.

Sub2API is an open-source relay service that consolidates access to multiple AI subscriptions like Claude, OpenAI, Gemini, and Grok into a single interface. It solves the problem of managing and paying for multiple expensive AI services individually by enabling cost-sharing through pooled subscriptions. This tool is designed for developers, teams, and cost-conscious users who want efficient, unified access to various AI models while leveraging native tool functionality and reducing per-user expenses.

Ruflo is an agent meta-harness for building and orchestrating intelligent multi-agent systems. It solves the complexity of coordinating autonomous AI workflows by providing adaptive memory, RAG integration, and self-learning intelligence. It's designed for developers and teams building advanced conversational AI, autonomous swarms, and complex, coordinated AI applications.

Obsidian Skills is a set of tools that enables AI agents to read from and write to Obsidian vaults using its command-line interface and open formats like Markdown and JSON Canvas. It solves the problem of AI assistants being unable to directly access or manipulate personal knowledge bases, bridging the gap between conversational AI and structured note-taking. It's designed for developers, researchers, and power users who want their AI agents to seamlessly integrate with and act upon their Obsidian-based knowledge systems.

holaOS is an open-source, all-in-one workspace for AI agents. It solves the problem of fragmented AI tools by letting you run any agent (like Claude Code or Codex) across your entire digital environment—100+ integrations, apps, browser, and files—with shared memory for seamless context. It's built for developers and teams who want to centralize their AI workflows, offering built-in models or the flexibility to bring your own keys.

Orca is an Agent Development Environment (ADE) that lets you run and manage multiple AI coding agents like Claude Code, Codex, and OpenCode in parallel, within isolated worktrees. It solves the problem of coordinating and reviewing output from a fleet of agents by providing integrated terminals, a file editor, and git tracking to keep all branches moving. It's designed for developers and teams who want to automate and scale their coding workflows using multiple AI assistants simultaneously.

Agent-Skills is a collection of 24 production-grade engineering skills that encode senior-level workflows and judgment for AI coding agents. It solves the problem of inconsistent, low-quality AI-generated code by providing structured, phase-specific commands that guide agents through the entire software lifecycle—from specification to deployment. It's designed for developers and teams using AI coding assistants like Claude Code, Cursor, or GitHub Copilot to ensure their agents produce reliable, maintainable, and production-ready code.

LoopX is a lightweight, agent-agnostic state kernel designed to manage long-running AI agent teams. It solves the problem of coordination, state persistence, and verifiable handoffs between different AI coding agents like Codex and Claude Code. With features like durable goals, quota-aware auto-wake, and executable todos, it provides the backbone for reliable, persistent AI team workflows. It's built for developers and engineers orchestrating complex, multi-agent AI systems that need to run continuously and maintain state across sessions.

ADR is a production-proven system for securing enterprise AI agents built on the Model Context Protocol (MCP). It solves the critical challenges of limited observability, insufficient robustness, and high detection costs by providing comprehensive telemetry, systematic red teaming, and scalable, two-tier detection. It is designed for large enterprises deploying AI agents at scale, as demonstrated by its deployment at Uber.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows