Agent0 is an AI agent framework built on Obsidian and Claude Code. It gives you 7 specialized AI agents powered by 83 reusable skills, with built-in governance, persistent memory, and a vault that catches every idea and ships the ones that matter.

Do I need to know how to code to use Agent0?

No. The Starter tier uses copy-paste prompts with step-by-step instructions. The Pro tier runs one command. The Custom tier is fully set up for you.

How is Agent0 different from other AI agent frameworks?

Agent0 runs on Obsidian and Claude Code with your data staying local. No hosted servers, no monthly infrastructure costs. The reflect/evolve layer (seeing your thinking patterns over time) is something no other framework offers.

Home/Skills/dev/Test-Driven Development (TDD)

devDevelopment

/test-driven-development

Test-Driven Development (TDD)

No production code without a failing test first. Watch it fail. Minimal code to green. Refactor under green.

Used by 1 agent

Axon

What it does

The iron law applied end to end: red, verify red, green, verify green, refactor. Tests name one behavior. Real code over mocks. Failing test watched every time, because a test you didn't see fail hasn't proven it tests the right thing. Covers bug fixes and features alike.

Use it on every feature, every bug, every behavior change. Exceptions (throwaway prototype, generated code, config) require explicit human partner sign-off. "Skip TDD just this once" is the rationalization the skill exists to refuse.

Outputs commits where every production function has a test that failed first, a pristine test run (no warnings, no stray output), and a verification checklist signed at the end. Pairs with `subagent-driven-development` (the subagents follow TDD per task) and `systematic-debugging` (the bug-first discipline that hands off to TDD).

Build your second brain

Run /test-driven-development with your agents.

This skill ships with Agent0 Starter, plus 82 others. Axon runs it from day one.

Found an error? Fix it on GitHub