Test-Driven Development

Write the failing test first, watch it fail, then write the minimum code that makes it pass.

Why use it

• Tests written after the code test what the code does, not what it should do.
• A bug with no reproducing test comes back.
• Agents rationalize skipping the test ("it's too simple to break"); this counters that.

What it does

• The red → green → refactor loop, stated as a hard sequence.
• Test-quality principles: one behavior per test, no logic in tests, names that describe the behavior.
• Rationalization counters for the usual excuses to skip a test.
• Test-layer selection, which level (unit / integration / end-to-end) actually proves this behavior.

Benefits

• Bugs stop coming back: every fix ships with the test that catches it next time.
• Better design, for free. Testable code is decoupled code, and you get it early.
• No more skipped tests: the usual excuses are answered in advance.
• Any language, any framework. The loop is the same everywhere.

Install

Download this skill and copy the test-driven-development folder to .claude/skills/test-driven-development/ in your project, or to ~/.claude/skills/test-driven-development/ to use it in every project. Claude Code finds it on its own; you can also call it with /test-driven-development.

Part of the Agent Engineering bundle. To get the whole set as a Claude Code plugin: /plugin marketplace add endorphin-ai/hasbrains-agent-kit, then /plugin install agent-engineering@hasbrains-agent-kit.

Source: endorphin-ai/hasbrains-agent-kit. License: MIT.