Loop Library is a library and installable skill for designing repeatable AI-agent workflows. It is built around the idea of loops, which are bounded playbooks that tell an agent what to do, how to check progress, what to try next, and when to stop. The repository contains both a public loop library website and the Loopy skill that agents can use to discover, audit, adapt, run, and prepare loops. It helps turn open-ended prompts into measurable workflows with evidence, stopping criteria, and human approval points. The skill can work with agent environments such as Codex, Cursor, and Claude Code through the Skills CLI. Overall, it is useful for teams that want safer, reusable, and more reliable agent workflows instead of one-off prompting.
Features
- Library of repeatable AI-agent loops
- Installable Loopy skill for supported coding agents
- Loop discovery, audit, repair, and adaptation workflows
- Bounded run process with evidence and stopping reasons
- Catalog search for published loops
- Support for Codex, Cursor, Claude Code, and detected agent setups