A catalog of repeatable AI agent workflows with built-in feedback loops, plus an installable skill for finding, adapting, and designing your own loops.
What it does
Loop Library is a curated catalog of 69+ practical AI agent prompts built as feedback loops, each with clear checks, stopping conditions, and next-step logic. It ships as a browsable public website and an optional installable skill for Codex, Cursor, and Claude Code. No installation needed to browse
One-shot prompts leave agents guessing. A loop gives an agent a feedback cycle: try something, measure it, keep only what works, and stop when the goal is met or progress stalls. Loop Library is a curated catalog of 69+ such loops, each answering four questions: what to accomplish, how to verify success, what to do with the result, and when to stop.
Loop Library ships as two independent but complementary things. The website is the library itself, browsable by anyone without an account or install. The skill is an optional companion that installs into your coding agent and adds five guided modes: Discover (find repeated work in your codebase), Find (search the live catalog), Loop Doctor (audit and repair a loop you paste in), Adapt (tailor a loop to your tools and constraints), and Design (create a new loop through plain-language conversation).
Install the skill with a single npx skills add command, targeting Codex, Cursor, Claude Code, or all three at once. Once installed, invoke it with /loop-library followed by a plain-language request. The skill checks the live catalog in real time when recommending published loops. Per the README, it requires at least two distinct thread occurrences before calling work "repeated," and labels unverified code patterns as potential loops rather than proven recurrence.
Every published loop includes five concrete parts: a "Use when" statement, a copy-ready prompt, a "Verify" section defining evidence of success, a "Steps" view of the feedback cycle, and "Notes" flagging practical limits or risks. The library also exposes machine-readable endpoints, including a JSON catalog and an llms.txt, so agents that skip the skill can still read the catalog directly.
Loops are deliberately bounded, not autonomous. Per the README, the skill does not start schedules, deploy code, delete data, send messages, or grant new permissions. Those actions still require explicit approval. Discovery also depends on what your agent can actually access: if coding-thread history is unavailable, the skill uses codebase evidence alone and says so.
Loop Library solves the "keep improving this" problem by making agent work measurable and repeatable. The catalog is free to browse and copy today; the skill adds guided discovery and design for teams who want to build their own loops or adapt published ones to their stack.
Features
Field notes
Reviewed Jun 26, 2026
Best for
Builder outcomes
Watch out
Tested with
Cost
The catalog is free to browse and copy with no account or install required. The installable skill appears to be free via npx; no paid tiers are mentioned in the entry.
Loop Library is a curated catalog of 69+ practical AI agent prompts structured as feedback loops, each with a clear goal, a verification step, next-step logic, and a stopping condition. It exists as a public browsable website (no account needed) and an optional installable skill for Codex, Cursor, and Claude Code. The project is built by Forward Future and released under the MIT License.
You need Node.js and npx. Run `npx skills add Forward-Future/loop-library --skill loop-library --agent claude-code -g -y` to install for Claude Code, swapping `claude-code` for `codex` or `cursor` as needed. Once installed, invoke it with `/loop-library` followed by a plain-language request in Claude Code or Cursor, or choose it from `/skills` in Codex. If your agent was already open, restart it after install for the skill to appear.
Loop Library is free and released under the MIT License, per the README. The public catalog website requires no account or installation to browse and copy loop prompts. The installable skill is also free and pulls from the same live catalog.
Loop Library fits best when agent work is recurring and the first attempt is unlikely to be the final answer: fixing production errors, improving test coverage, keeping documentation current, or sweeping SEO gaps. The library's loops are deliberately bounded, so they suit teams who want measurable, repeatable agent workflows rather than open-ended runs. The skill's Discover mode is especially useful for finding repeated engineering work in your own codebase and turning it into a reusable loop.
A hand-written prompt typically asks an agent to do something once, leaving verification and stopping behavior implicit. Loop Library prompts encode the feedback cycle directly: what to measure, what counts as success, what to do when an attempt fails, and when to hand control back to a person. The library also provides Loop Doctor, which audits an existing prompt or loop for weak checks, unsafe actions, or unclear stopping behavior and repairs only the material problems, something a blank-slate prompt approach does not provide.
The skill does not take production actions on its own: it will not start schedules, deploy code, delete data, send messages, or grant permissions without an explicit request. Discovery requires at least two distinct thread occurrences before marking work as truly repeated, and a code pattern without run history is labeled a potential loop rather than confirmed recurrence. If your agent cannot access thread history, the skill falls back to codebase evidence alone and notes the limitation explicitly.
Agent skill collection for engineers who use Claude Code or Codex, small, composable prompts that enforce TDD, domain modeling, and architecture review.
Best for Engineers already using Claude Code or Codex daily who want to stop architectural and quality driftOpen-source collection of reusable agent skills, shared AGENTS.MD rules, and portable helper scripts for Codex and Claude agents, by steipete.
Best for Developers running multiple Codex or Claude agent projects who need one canonical source for shared rules and skillsAnthropic's official skill library for Claude: modular SKILL.md bundles that add repeatable, domain-specific workflows across docs, dev, design, and enterprise tasks.
Best for Teams who need Claude to follow repeatable, specialized workflows across many sessions without re-promptingAgent skill that audits your codebase with a capable model and writes executable plans for cheaper models to implement, by shadcn.
Best for Teams running AI-assisted development at scale who want high-quality code review without paying for a capable model on every execution stepOpen-source agentic skills framework that brings spec-first, TDD-enforced, subagent-driven software development to Claude Code, Cursor, Codex, and 8 other AI coding harnesses.
Best for Teams wanting a full SDLC enforced automatically on coding agents, from spec through code reviewOpen-source PM skills marketplace: 68 AI skills and 42 workflows across 9 Claude plugins for product managers doing discovery, strategy, execution, and launch.
Best for PMs using Claude Code or Claude Cowork who want framework-driven decisions baked into daily AI workflows