tdd-agent

Automates the RED-GREEN-REFACTOR cycle for autonomous code development with strict TDD guardrails.

2|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/michaelalber/ai-toolkit --skill tdd-agent-michaelalber
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tdd-agent
Source: https://github.com/michaelalber/ai-toolkit/tree/main/skills/tdd-agent
Command: npx skills add https://github.com/michaelalber/ai-toolkit --skill tdd-agent-michaelalber

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the entire Test-Driven Development (TDD) cycle, allowing an AI to independently write tests, implement code, and refactor, while strictly adhering to TDD principles and safety guardrails.

Core Features & Use Cases

  • Full TDD Cycle Automation: Manages RED, GREEN, and REFACTOR phases autonomously.
  • Strict Guardrails: Enforces non-negotiable TDD constraints and self-check loops.
  • Use Case: Use this Skill when you want an AI to develop a new feature using TDD from scratch, ensuring code quality and adherence to best practices without direct human intervention in each micro-step.

Quick Start

Initiate the TDD agent to develop a new feature for the calculator class.

Frequently Asked Questions about tdd-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate the test-driven development cycle for a new feature?

You can automate test-driven development by deploying an autonomous agent to independently drive the RED, GREEN, and REFACTOR phases while enforcing strict TDD guardrails and minimality constraints.

What are the TDD guardrails enforced during autonomous code generation?

TDD guardrails enforced during autonomous code generation include requiring implementation without failure proof, making evidence-based claims, adhering to minimality principles, and executing rollback protocols for safety.

How does an autonomous agent handle the refactoring phase in TDD?

An autonomous agent handles the TDD refactoring phase by applying Kent Beck's principles and the 12 Test Desiderata, ensuring code improvements maintain test correctness without direct human intervention.

Can I use autonomous TDD for developing a new class from scratch?

Yes, you can use autonomous TDD to develop a new class from scratch by initiating the agent to write tests, implement code, and refactor while maintaining adherence to best practices.

What is the difference between autonomous TDD and manual test-driven development?

Autonomous TDD eliminates direct human intervention in each micro-step by using an AI agent to independently manage the RED, GREEN, and REFACTOR phases, whereas manual TDD requires a developer to drive every step.

When should I avoid using an autonomous agent for test-driven development?

You should avoid using an autonomous agent for TDD if your workflow requires bypassing strict guardrails, failure proofs, or minimality constraints, as the agent enforces these non-negotiable TDD safety protocols.