MCP.so
Sign In
Testingmanual

Autoloop TDD

Test-first loop: write a failing test, implement the minimum code to pass, refactor, and repeat.

Kickoff prompt

Start the "Autoloop TDD" loop.

Goal: implement the target behavior test-first with a green suite
Max iterations: 12
Between iterations run: npm test
Exit when: target behavior is covered and all tests pass

Step 1: Write a failing test for the next behavior, implement the minimum code to pass, refactor, and repeat.

Self-pace this loop. After each iteration, run the check command, read the output, and only continue if the exit condition is not met. Stop when the exit condition passes or max iterations is reached. Give a short status update each pass.

Basic information

Category

Testing

Goal

implement the target behavior test-first with a green suite

Max iterations

12

Check command

npm test

Exit when

target behavior is covered and all tests pass

Supported agents

Claude Code

Steps

  1. 1

    Write failing test

    Write a focused test for the next behavior. Run it and confirm it fails for the right reason.

    npm test -- --testPathPattern=<new-test>
  2. 2

    Implement minimum code

    Write the smallest implementation that makes the new test pass. No extra features.

  3. 3

    Verify green

    Run the new test and full suite to confirm everything passes.

    npm test
  4. 4

    Refactor

    Clean up duplication and naming while keeping tests green. Run tests after each refactor.

    npm test

More Testing loops

Testing

Build Until Green

Run the production build, fix compile and bundling errors, and loop until the build succeeds.

Testing

Coverage Until Threshold

Add focused tests until coverage meets your threshold (e.g. 80%), without changing production behavior unnecessarily.

Testing

Pre-Commit Guard

Hook that runs tests before git commit commands to block commits when the suite is red.

Testing

Post-Edit Test Guard

Hook-based loop that runs related tests after file edits to catch regressions early.

Testing

Format Until Clean

Run the formatter, fix any remaining style issues, and loop until the codebase formats cleanly with no diffs.

Testing

Flaky Test Triage

Run failing tests repeatedly, classify each failure as flaky or real, and fix only confirmed regressions.