A skill for coding agents that runs a structured, multi-phase security audit of a codebase. It uses separate agents to find, challenge and verify vulnerabilities, then writes the results as machine-readable records and readable reports.
loop-engineering
by cobusgreyling
A library of patterns and a command-line tool for setting up repeating routines in which AI coding agents check a codebase, do small jobs and report back. It is meant for people who want agents to handle tasks such as issue triage, CI fixes and dependency updates without typing each prompt.
Proof level: ReadWorth a lookMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Needs an AI coding agent account, so token costs can be high, especially for CI and PR loops.
Things to check
- Needs an AI coding agent account, so token costs can be high, especially for CI and PR loops
- Unattended loops can make unattended mistakes, so output needs reviewing
- Mostly a pattern library and documentation rather than a single finished application
Can you use loop-engineering commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with loop-engineering?
- Set up a daily triage routine that reports on issues, CI and dependencies in a repository
- Run a thin GitHub Actions loop that has an agent watch pull requests or draft changelogs
- Estimate the running cost of a loop and check whether a project is ready for it before turning it on
How do you get loop-engineering running?
Run it with npx (for example "npx @cobusgreyling/loop init . --pattern daily-triage --tool claude"), which needs Node.js and an AI coding agent such as Claude Code, Codex or Grok.
Follow the official instructions in the project README.
Make money with it
A freelance developer could set up and monitor these agent routines for client repositories as a paid maintenance service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Automate routine repository upkeep, such as issue sorting, dependency updates and changelog drafts, to save developer hours
- Offer a small team or client a monitored agent routine that keeps pull requests and CI moving, with costs estimated beforehand
Checked 08 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in Agent skills and plugins
A skill for Claude Code and Codex that reviews a screen built with AI tools, finds the generic "AI look" such as purple gradients, glows and uneven spacing, and fixes it step by step. It is for making dashboards, apps and landing pages look designed rather than auto-generated.
A small collection of agent skills, each a folder with a SKILL.md file of instructions for an AI agent. At present it holds one skill, a Socratic tutor that teaches a topic through questions, a skill map and spaced review.