ame Prompt, Three Workflows: What Happens When BMAD Joins SpecKit

 In my previous article, I looked at SpecKit without extensions and SpecKit with extensions, trying to understand how much structure really helps when we use AI to generate code. This post is a follow-up of that work. I kept the same prompt, tools, and evaluation method, but added a third approach: BMAD (BMad Agentic Development).

From the beginning, BMAD felt different. SpecKit guides the AI through clear workflows. BMAD, on the other hand, feels like a small virtual team that thinks first, plans more, and then writes code. This difference shows clearly in the output.

What impressed me most was simplicity. Even if BMAD did not win on all linting scores, the code was much easier to read and reason about. The Halstead cognitive metrics showed a big gap that classic linters do not really capture. In simple words, the BMAD code is easier for a human brain.

Testing was another strong signal. BMAD produced the highest number of tests and almost 99% coverage, while also having the smallest codebase. Less code, more tests — that is usually a good sign.

Still, SpecKit with extensions remains very strong for documentation and project maturity. If you think about long‑term maintenance or enterprise readiness, extensions add real value.

Below is a small snapshot of the numbers that influenced my conclusion:

Metric	SpecKit	SpecKit + Extensions	BMAD
Source Lines of Code	604	629	517
Pylint Score	9.68	9.32	8.50
Halstead Effort	2,665	1,526	1,090
Test Count	65	102	107
Test Coverage	94.27%	92.24%	99.01%

 

My takeaway so far is simple:
BMAD optimises for thinking and simplicity, while SpecKit + Extensions optimises for structure and completeness.
Ultimately, establishing a balance between BMAD and SpecKit + Extensions is key. Measuring the trade-offs helps determine the optimal approach for your needs.