I haven’t looked at the code but the collision detection was buggy even back in the day. You have to switch lanes while there is nothing or a donkey in front of you. If the donkey is in the other lane it registers a hit even if it looks like you passed it
Edit: line 1750 is where it does a simple collision check and yep looks like it registers a collision without checking you’re past the donkey or not
Author here. I built Maverik because I want to be able to 1) assess + quantify improvements in agents 2) predict what an agent that would be exposed in a business setting (ie. a single agent for a specific task in a UI) is estimated to cost. So this is JMeter for agents :) be able to define test suites, pass criteria, run them and compare cold hard numbers.
An interesting find (intuitive but still interesting in terms of numbers), for one of my test agents, adding harmless MCP Servers that have tools this agent does not need, make it 28% more costly in terms of input+output tokens.
Anyway, next up for me are small improvements and maybe a crack at integrating the 2026-07-28 MCP Spec (stateless core, tasks, ...).
I guess I'm trying to define the agent itself to be wider than just the chat loop. The reason is that, when we test agents (not in production yet), the results are extremely varied depending on the model you use, the system context, what the current context holds, etc. So I guess I could replace my agent-definition with agent-harness? I also like the 'production tools' list from the bottom of the emperor has no clothes article. My main goal though remains to be able to express how the agentic system is constructed (be that the harnass, the production tooling or the agent definition) and the actual current state (that is what i defined the agent to be). And then afterwards, be able to reason about what characteristics are good for which types of agentic systems.
Yes, it does. And the thing is this space is very new and evolving and things are very opinionated which is fine, because there isn't much book written about this like we have in our CS degree, this is new and changing. I think the distinction between the what is an agent and agent harness need to be made clear. Harness is the machinery around the agent(ic loop) which does the state management, the system prompt, etc) that what is claude code and codex are basically they are native agent harness. Now the user with their own custom tooling, skills and added machinery makes it a user harness and when that get to a point that the user harness stuff can be looped, that it goes to another level like an orchestrator. What you are refering to I guess is the native inner harness machinery, how does that work and how it comes together.
The improvements look great. At the same time I wonder if it is possible to keep using MCP 1.x as well for now. Development is expensive, right? It also looks possible to transition to MCP 2.x by tackling the different improvements one at a time as long as we take stateless core first?
I just realized that MCP releases do not use semver. It says this is a 2026-07-28 version which is quite unusual and can be quite hard to keep track of, especially when backwards compatibility is of concerns.
You are right, in my mind the 2026-07-28 version was MCP 2.0 but the article never mentions that. I do remember having read about MCP 2.0 elsewhere. Regardless, we cannot expect this to be the last impactful change and to me it makes sense to indeed semantically version.
