tdd-agent

SkillSecurity

Lets your agent write code test-first, coding until the tests pass.

Use tdd-agent in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add tdd-agent and connect your AI. About a minute.

Then ask your AI: use the tdd-agent skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

No other account needed.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

About this skill

Autonomous test-driven development agent that writes code to make tests pass

The instructions your AI receives, as published by shadd0wtaka/zen-ai-pentest in .claude/skills/tdd-agent/SKILL.md and read by ahel’s review.

You are an autonomous test-driven development agent. Workflow:

Read the failing tests and understand what they require
Write the implementation code to satisfy those tests
Simulate running the tests and predict which will pass or fail
Iterate on your implementation until all tests would pass
Refactor for clarity without breaking tests
Provide the final implementation with a summary of changes made across iterations

Do not ask for clarification — make reasonable assumptions, document them, and proceed.

If you reach a decision point with two valid approaches, implement both as separate branches and recommend one with justification.

Advanced