🔁
AI EngineeringPython

New Loop

by AI-Builder-Club

New Loop is an AI Engineering skill for Claude Code, published by AI-Builder-Club in skills.

1.2K stars153 forkson AI-Builder-Club/skillsAdded 2026/08/20Repository updated 2026/07/27
agent-harnessagent-skillsai-agentsclaudeclaude-codedeveloper-toolsloop-engineering
Install in seconds
Install New Loop
Copy New Loop into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/AI-Builder-Club/skills/tree/main/skills/new-loop ~/.claude/skills/new-loop

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/AI-Builder-Club/skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/new-loop/SKILL.md in AI-Builder-Club/skills
Installs to
~/.claude/skills/new-loop
Collection
One of 10 skills cataloged from this repository
Category
AI Engineering2451 skills

What New Loop does

New Loop spins up a new loop (domain) in a file-based knowledge base, bootstraps the substrate if missing, scaffolds the loop README, and does one real test run recorded in the Timeline and LOG.md. Use when setting up a recurring job or workstream the agent should own.

New Loop is cataloged under AI Engineering on DirSkills. New Loop comes from a repository tagged agent-harness, agent-skills, ai-agents, claude and claude-code.

Documentation

README

new-loop — spin up a new loop

A loop (a domain) is a recurring thread of work the agent owns: a charter, a cadence, and the artifacts it produces. This skill creates one, proves it works with a single real run, and leaves behind a domains/<loop>/README.md that is the loop's live state.

When to use

The user wants to stand up a new workstream/beat/job (e.g. "a weekly SEO loop", "a support triage loop", "a competitor-watch loop"). Don't use this for a one-off task — that's a backlog line in an existing domain, or a doc/signal.

This is the opening of the README. Read the full README on GitHub.

Commands New Loop provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /verify

Frequently asked about New Loop

  • What else does AI-Builder-Club publish alongside New Loop?

    New Loop is one of 10 skills that DirSkills catalogs from AI-Builder-Club/skills, the repository it ships in. Its siblings there include Agent Context Audit, Codebase Harness Setup and Crabbox Setup. Each one is a separate skill with its own page in this directory, installs the same way New Loop does, and is maintained by AI-Builder-Club in that same repository. The rest of the collection is listed on the AI-Builder-Club/skills page.

  • How does New Loop compare to other AI Engineering skills?

    New Loop ranks #1172 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of New Loop against them. Open each page to compare what they document and how they install.

More from AI-Builder-Club/skills

New Loop is one of 10 skills cataloged on DirSkills from AI-Builder-Club/skills.

See all 10 skills
🔍
2w ago

Agent Context Audit

Agent Context Audit audits a repository's agent context—CLAUDE.md files, codebase docs, skills, and tool/MCP designs—against Anthropic's Claude 5 context-engineering guidance to find overconstraint, conflicts, redundancy, stale facts, and missing unknown knowns. It produces a scored findings report with concrete rewrites and applies approved fixes, used when someone says 'audit my CLAUDE.md' or
AI Engineering
1.2K153
🛠️
2w ago

Codebase Harness Setup

Codebase Harness Setup prepares a codebase for agent-driven development by making it legible, executable, and verifiable through structured docs, a reproducible dev stack, and a verify-before-ship loop. Use when onboarding a new or unfamiliar codebase to agent-driven development.
AI Engineering
1.2K153
☁️
2w ago

Crabbox Setup

Crabbox Setup scaffolds an isolated cloud dev box per agent (via crabbox + Daytona) for any codebase, giving each agent its own full stack and in-box browser so concurrent loops never collide on ports or state. Use when you need parallel-safe testing or per-agent isolation in cloud environments.
DevOps
1.2K153
🛠️
2w ago

Dev Local Setup

Dev Local Setup investigates a codebase to discover services, ports, and infrastructure dependencies, then generates a single scripts/dev-local.sh launcher that runs every dev server in one tmux session. Use when someone asks for a one-command local development environment.
DevOps
1.2K153
🧪
2w ago

E2E Setup

E2E Setup sets up an end-to-end test suite in any repository, following practices that make e2e a reliable per-PR gate, including real flows, layered assertions, reusable auth helpers, and video/trace evidence. Use it when a repository lacks e2e tests or has weak e2e and needs system-level tests.
Quality
1.2K153
🤖
2w ago

Open Agent Teams

Open Agent Teams delegates tasks to any CLI agent (Claude, Codex, Aider, etc.) running in a detached tmux session, using file sentinels for race-safe completion signaling and multi-turn iteration. Use it when delegating work to a non-Claude CLI agent or running executor work in an observable background terminal.
AI Engineering
1.2K153