mirror of
https://github.com/bmad-code-org/BMAD-METHOD.git
synced 2026-08-29 03:44:18 +08:00
cff69a6d54
* refactor(review): slim adversarial hunter prompt across build and review skills Drop cynical-persona framing. Inline a short review prompt (≥10 findings, look for missing, empty/zero guards) into blind-hunter layer instructions for bmad-build, bmad-build-auto, and bmad-code-review. Delete the old review-prompts/adversarial.md files. Align offline no-subagent dump with the same child prompt. Update bmad-review's adversarial lens to the same method while keeping its canonical finding fields. * test(renderer): stop requiring deleted adversarial.md prompt file Blind hunter is inlined; assert the inlined prompt text and remaining file-backed review prompts instead. * docs: align adversarial review explanation with slim hunter prompt Document the finding floor and missing-not-only-wrong method instead of the old cynical persona. Update core-tools lens table and localized pages.
Test Suite
Tests for the BMAD-METHOD tooling infrastructure.
Quick Start
# Run all quality checks
npm run quality
# Run individual test suites
npm run test:install # Installation component tests
npm run test:refs # File reference CSV tests
npm run validate:refs # File reference validation (strict)
Test Scripts
Installation Component Tests
File: test/test-installation-components.js
Validates that the installer compiles and assembles agents correctly.
File Reference Tests
File: test/test-file-refs-csv.js
Tests the CSV-based file reference validation logic.
Test Fixtures
Located in test/fixtures/:
test/fixtures/
└── file-refs-csv/ # Fixtures for file reference CSV tests