#5454th of 73 in Skills, plugins and rules

loop-engineering

Pattern library and CLI for running scheduled agent loops around a codebase

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 11.5k
License: MIT
Last commit: Oct 2026
Last release: Jul 2026
Language: TypeScript

Stars, last 18 weeks+11,470

65 on 10 Jun 202611,535 on 14 Oct 2026

From GitHub's daily star counts.

Checked 15 Oct 2026 on GitHub.

Overview

Loop Engineering is a library of documented patterns (daily triage, PR babysitter, CI sweeper, dependency sweeper, changelog drafter and others) for running coding agents on a schedule against a repo. An npm CLI (@cobusgreyling/loop) scaffolds a pattern for Claude, Grok, Codex or Opencode, then offers doctor, status, audit and cost commands. Rollout is staged from L1 report-only to L3 unattended.

Who it is for: Teams running coding agents on a schedule against their own repos

Strengths

CLI scaffolds a pattern with init, then checks it with doctor, audit and cost
Eight documented patterns, each with cadence, week-one level and relative cost
Staged L1 to L3 rollout; week one is report-only
Examples for Claude Code, Grok, Codex, Opencode, OpenClaw and GitHub Actions

Weaknesses

Mostly docs and templates; the agent itself comes from a separate tool
PR Babysitter and CI Sweeper are rated high or very high cost
README warns unattended loops can ship mistakes and token costs can explode
Related features live in separate companion repos

What it needs

no GPU
Needs Node.js (npx), GitHub, A coding agent CLI (Claude Code, Grok, Codex or Opencode)
Models: Claude Code, Grok, Codex, Opencode, OpenClaw

Also in Skills, plugins and rules

See all 73

Also in Skills, plugins and rules
Rank	Project	Score
1	skillsAgent skills for planning, TDD, debugging and code review291.3k starsMIT	94 out of 100
2	eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses279.5k starsMIT	94 out of 100
3	cavemanCuts token use in coding agents with terse replies and compressed inputs Live demo ↗ (opens in a new tab)111.9k starsApache-2.0	93 out of 100
#4	ponytailSkill prompt that makes coding agents write less code and add tests163.6k starsMIT	92 out of 100
#5	ui-ux-pro-max-skillDesign-system skill that gives coding agents searchable UI styles, palettes and fonts135.9k starsMIT	91 out of 100

How to choose

Check which agent it targets and whether it works with the version you run.
Read what it adds to every prompt; big rule sets cost tokens on each call.
Prefer add-ons you can turn off per project.

Health

Releases: 2 in the last 12 monthsLast one 87 days ago
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#54 of 73 in Skills, plugins and rules on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/cobusgreyling/loop-engineering.svg)](https://archestack.com/best-of-vibe-coding/projects/loop-engineering/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/loop-engineering/" title="loop-engineering on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with loop-engineering filled in.