swingerman/disciplined-agentic-engineering

README preview

# Disciplined Agentic Engineering — a Claude Code methodology marketplace

*Spec-driven, test-driven, charter-bound AI coding for Claude Code. ATDD + mutation testing + deterministic guardrails. Three plugins: `engineer`, `atdd`, `crap-analyzer`.*

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
[![Claude Code Marketplace](https://img.shields.io/badge/Claude%20Code-Marketplace-blueviolet)](https://github.com/swingerman/disciplined-agentic-engineering)

> ℹ️ **Repo renamed:** this marketplace was previously `swingerman/atdd`. Existing `swingerman/atdd` URLs continue to work via GitHub's automatic redirect — no action needed unless you want to update local remotes (`git remote set-url origin https://github.com/swingerman/disciplined-agentic-engineering.git`).

A Claude Code marketplace hosting the **Disciplined Agentic Engineering (DAE)** methodology kit — skills, agents, hooks, slash commands, and deterministic guardrail tools that keep software engineers in charge of architecture, behavior decisions, and verification while AI agents do the typing. Built around **Acceptance Test Driven Development (ATDD)**, **mutation testing**, and the **iterative, layered specification** pattern of [GitHub's Speckit](https://github.com/github/spec-kit).

## What is Disciplined Agentic Engineering?

DAE is a methodology for **engineering-led AI development**. AI agents do the coding; software engineers stay in charge of architecture, performance, and feature validation. Discipline lives in the contracts at every layer (charter → ACs → specs → plans → verification) and in **deterministic guardrail tools** that gate every checkpoint — not in prompt rules that erode over long agent runs.

It's positioned in direct opposition to **vibe coding** — the loose-prompt, weak-check style of agentic development where AI produces code with no charter, no behavior contract, and no verification gates. DAE makes the boundaries explicit and the checks continuous.

**The headline outcome: semantic stability.** ATDD + mutation testing together form a *semantic firewall* — code can be refactored, extended, or modified by agents without the system's intended behavior drifting. This is the moat between DAE-built systems and "AI plops code around."

### Who is this for?

View full repository on GitHub →