While these (MCP Servers) were heavily promoted a couple of months ago, these bloat the context window of the agents, resulting in lower quality output. There are many skills and/or CLI tools that can replace tasks for an MCP server.
I found it (spec-driven development) to be a great way to communicate the requirements and expectations to the coding agent, and it helped me to get a better understanding of the feature, the implementation, and possible caveats and drawbacks. It also helped me to keep track of the progress, and to steer that the feature is implemented according to the requirements and expectations.
To make smaller changes and bugfixes to existing features, [..] I just prompted the agent to make the changes directly, or to create a plan suggestion. This worked well without the need for a more formal spec.
The models evolve at a fast pace, and I think it doesn’t matter (which model to use) as much as it used to be. [..] The tools we use to interact with the models are an abstraction layer around the models, which is called the harness. If I’m well informed, this layer is becoming thinner because the power of AI lies within the models themselves. Because of this, there isn’t much difference between the tools, and they are becoming more and more identical.