# Tools that support Agent Skills

Agent Skills are folders of instructions and scripts that an agent loads when a task calls for them. These tools in the directory say they support it.

20 tools, in alphabetical order. Nothing is ranked by popularity.

- [Agent Skills](https://modelmoot.com/tools/agent-skills.md): A file format for packaging instructions, scripts and resources that an agent loads when a task calls for them. (Agent Skills project; open source)
- [Circle Agent Stack](https://modelmoot.com/tools/circle-agent-stack.md): Circle tools for agents: a command-line tool, agent wallets, USDC nanopayments, skills and an MCP server. (Circle; not open source, hosted service)
- [Claude Agent SDK](https://modelmoot.com/tools/claude-agent-sdk.md): Anthropic's libraries for running the Claude Code agent loop, with its tools, from Python or TypeScript. (Anthropic; open source)
- [Claude Code](https://modelmoot.com/tools/claude-code.md): A coding agent from Anthropic that works in the terminal, in editors and on the web, reading and changing a codebase on request. (Anthropic; not open source)
- [Claude Managed Agents](https://modelmoot.com/tools/claude-managed-agents.md): Anthropic hosted agent harness in which Claude runs long tasks in a managed sandbox that a program starts and steers through an API. (Anthropic; not open source, hosted service)
- [ClawHub](https://modelmoot.com/tools/clawhub.md): A registry for finding, publishing and syncing skills and plugins for OpenClaw agents. (OpenClaw Foundation; open source, hosted service)
- [Codex](https://modelmoot.com/tools/openai-codex.md): OpenAI coding agent that runs as a terminal program, an editor extension, an app and a cloud service working on repositories. (OpenAI; open source, hosted service)
- [Deep Agents](https://modelmoot.com/tools/deepagents.md): A LangChain agent harness with planning, a virtual file system and subagents, built on LangGraph. (LangChain; open source)
- [GitHub Copilot](https://modelmoot.com/tools/github-copilot.md): GitHub service with code completion, chat, agent mode in editors and a coding agent that works on issues and opens pull requests. (GitHub; not open source, hosted service)
- [Google Antigravity](https://modelmoot.com/tools/antigravity.md): Google agent-first development product with a desktop application and a command-line tool named agy, built around Gemini models. (Google; not open source, hosted service)
- [Hermes Agent](https://modelmoot.com/tools/hermes-agent.md): An open-source agent from Nous Research that runs on a server or local machine and builds up skills and memory over time. (Nous Research; open source)
- [Kapso](https://modelmoot.com/tools/kapso.md): A platform for adding WhatsApp messaging to software, with a CLI, an MCP server and agent skills. (Kapso; not open source, hosted service)
- [Lightning Agent Tools](https://modelmoot.com/tools/lightning-agent-tools.md): A toolkit of agent skills and an MCP server for Lightning Network payments, including paying for L402 APIs. (Lightning Labs; not open source)
- [microsandbox](https://modelmoot.com/tools/microsandbox.md): A local-first runtime that starts microVMs as sandboxes for running untrusted code, used as a library or CLI. (Super Rad Company; open source)
- [Moltbook](https://modelmoot.com/tools/moltbook.md): A social network where AI agents post, comment and vote, and people can only watch. (Matt Schlicht; not open source, hosted service)
- [OpenClaw](https://modelmoot.com/tools/openclaw.md): An open-source personal agent that runs on the user own machine and is reached through chat apps, acting on files, the web and other tools. (OpenClaw; open source)
- [opencode](https://modelmoot.com/tools/opencode.md): An open-source terminal coding agent that works with models from many providers and also runs as a desktop app and editor extension. (Anomaly; open source, hosted service)
- [Ramparts](https://modelmoot.com/tools/ramparts.md): A Rust command-line scanner that audits MCP servers and agent skill files for injection, tool poisoning and other risks. (Highflame; open source)
- [Snyk Agent Scan](https://modelmoot.com/tools/snyk-agent-scan.md): A command-line scanner that checks agents, MCP servers and agent skills for security problems such as tool poisoning. (Snyk (originally Invariant Labs); open source)
- [Stripe agent toolkit and MCP server](https://modelmoot.com/tools/stripe-agent-toolkit.md): Stripe libraries, skills and a hosted MCP server that let agents work with the Stripe API. (Stripe; open source, hosted service)

HTML: https://modelmoot.com/tools/speaks/agent-skills. All categories: https://modelmoot.com/tools.md
