caty-ai

Self Growth Loop — AI skill for Claude Code

AI community

Self-governed skill-growth loop for AI agents: propose -> owner-approve -> trial -> council-review -> adopt, with an append-only ledger and mechanical growth-lint.

How to install Self Growth Loop

This entry records only its repository, not the path inside it, so there is no exact command to give. Open caty-ai/self-growth-loop and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Self Growth Loop does

Self-governed skill-growth loop for AI agents: propose -> owner-approve -> trial -> council-review -> adopt, with an append-only ledger and mechanical growth-lint.

Alternatives in AI

Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
Adopt AI Properly — Workflow recipe — the org-side AI adoption arc, policy to proof, by chaining 4 skills 1.3k ★
MioIsland — macOS Dynamic Island for AI coding agents 388 ★

README

self-growth-loop

**🇺🇸 English** ｜ [🇯🇵 日本語](README.ja.md) ｜ [🇨🇳 简体中文](README.zh.md) ｜ [🇹🇭 ไทย](README.th.md)

![Family OS ecosystem map with the Self Growth Loop node highlighted: improvement proposals cycle through sense, propose, trial, council, and adopt — usable standalone, and every adoption passes explicit human approval.](assets/readme/hero.png)

[![Test + Lint](https://github.com/caty-ai/self-growth-loop/actions/workflows/test-lint.yml/badge.svg)](https://github.com/caty-ai/self-growth-loop/actions/workflows/test-lint.yml) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) ![runtime](https://img.shields.io/badge/runtime-bash%203.2%2B%20%2B%20ruby-lightgrey) ![platform](https://img.shields.io/badge/platform-macOS%20%E2%9C%85%20%7C%20Linux%20%E2%9C%85%20CI%20tested-lightgrey)

Your AI keeps suggesting improvements to its own setup — new tools, better prompts, workflow tweaks.
Adopting them by hand doesn't scale; letting the AI change things by itself is how setups get quietly broken.
self-growth-loop turns every suggestion into a tracked proposal that must earn its way through testing, risk-scaled review, and **your explicit approval** before anything changes.

**Growth you can audit. Every change passes a human gate.**

🔧 [Engineering guide](INTEGRATION.md) ｜ 📘 [Specifications](docs/ledger-spec.md)

generation: 1d006b1 (2026-09-07T06:16:41Z) · verify: API HEAD · status.json

Sound familiar?

Your AI assistant says "we should adopt tool X" — and the idea dies in a chat log because there's no process for it
You tried letting an agent tweak its own configuration once, and spent an evening figuring out what changed
Improvement ideas pile up with no