Test Maze for developers

Write the story once. Everything else reads it.

Test Maze plugs into Claude Code, Cursor, Cline, Gemini CLI, Codex CLI or any MCP client. The user story and its acceptance tests live in one place; your agent implements against them, a separate verifier runs them, and the verdict is computed by fixed rules against the exact commit.

Start free Watch the workflow

SOUND FAMILIAR?

What goes wrong today

Re-explaining the spec every session

The agent loses context, you paste the requirements again, and the version it builds against drifts from the one you agreed.

Self-grading drift

The agent edits the assertion until the test passes. The diff looks clean. The bug ships.

“Tests pass” on which commit?

A green summary from the agent says nothing about which working tree it ran against, or whether the tree was dirty.

WITH TEST MAZE

What changes

One story, read by everyone

userstory.create · case.create_batch

As a / I want / so that, points, a breakdown and acceptance cases tagged by facet. The agent reads it back at every session start; the verifier grades against it.

Deterministic verdicts

pdlc.verify

No LLM in the pass/fail path. The same results always give the same verdict, with failure buckets and a reliability KPI your agent can act on.

Commit-pinned runs

testrun.create · testrun.record_results

Every verifier run carries gitSha, branch and workingTreeClean, so a green run means a specific commit was green.

A repair loop that points somewhere

nextStep: repair_code · repair_test · add_coverage

On failure the verdict says whether the code or the test is wrong and which case to look at first. No more guessing.

Code health on request

quality.smell_check · architecture.advise

A code-smell check with fixed rules, mapped to the refactorings that fix each smell, plus design-pattern advice ranked for your problem. Only the snippet you choose is sent.

SEE IT MOVE