HarnessTax: How Much Does the Harness Matter for Coding Agents?

ed_mercer

Does this extend to open models like GLM 5.3? This would mean that simply changing the harness to Pi reduces cost in half?

jswelker

Much of the extra weight of Claude Code and Codex harness are (ostensibly?) for security and alignment purposes. Whether they are effective is an open question, but leaving those dimensions out and calling it a tax is disingenuous, just turning insecurity into a negative externality. "Why pay the waste disposal tax? Dumping into the ocean is free!" Pi actively omits any sort of guardrails and sandboxing in the name of speed and simplicity, so it is not shocking that it is faster and simpler. Doubling the cost of something in the name of vague security is standard operating procedure for big enterprises, maybe even quite cheap.

Supermancho

The term "harness" here is being overloaded for the term "agent", which is worrying. Putting that aside, there are many factors that matter. The "harness" context, the execution pattern (parallel vs sequential), the ability to delegate to other models, etc. Optimal harnesses use concurrent execution + subagents and are not stuck on one model. Cost and performance are impacted GREATLY by these tactics, regardless of the native agent context (instruction). This kind of single-harness analysis is shallow and misleading, although the finding that "Provider-specific optimization does not guarantee the best pairing" is probably correct, depending on how you measure. It is a starting point.

robinpie

claude code feels mildly shitty to use in the way that every other vibe-coded-project-got-out-of-hand project does, which is like, not that bad, but it's fucking ridiculous for a 2 trillion dollar company's main companion product

mikert89

As the model gets smarter, you need to tell it less

corv

My own findings are in line with this research: Having a coding harness is critical but the differences between them are overstated. Personally, I’ve replaced OpenCode with a thin wrapper around Pydantic-AI as the pythonic analogue to Pi-Agent for headless use via Hermes They’d all do the job - I just prefer to compartmentalize for access control. Keeping the harness’ surface area tiny had the added benefit of preserving my understanding and being able to adapt it to my preferred workflow effortlessly

x312

Claude Code/Codex charge the user for their extremely bloated one-size-fits-all system prompts (including safety instructions and other stuff users dont want). In my experience if you're using OpenAI/Claude models and paying API costs, almost every other harness beats Claude Code/Codex in cost.

spike021

Say I'm using Claude Code or GPT Codex's harnesses but also sending some queries to the respective Anthropic and OpenAI models via OpenRouter. Do harnesses and therefore sending the queries directly to the LLM providers have caching and other benefits that OpenRouter does not provide? Would I get any of those benefits if I simply proxied any requests to the major providers' harnesses through OpenRouter? Or only if the requests go straight from the harness to the provider's API?

lexicalmathical

If this is mostly because of the size of the system prompt, then perhaps in long horizon tasks the "tax" will be less obvious.

nojs

We really need better harness benchmarks. It seems there's no reliable source that benchmarks the main harnesses against all open source models. I also wish the discussion around Pi did not always use cost/token count as the metric. It's amazingly token efficient, but how does it stack up again opencode and others if you don't care about token count? My experience is that the harness is mainly polish preventing failed tool calls, bad edits, stuff like that, but doesn't make much difference to the overall "intelligence". But that opencode seems slightly more robust against stupid errors than out of the box Pi due to the additional context it forces through every thread.

Yashjain413

I think it’s really important, especially when you look at everything the tool does, from the execution loop and context management to feedback. The harness is basically the underlying source of truth. With coding agents, what I’ve noticed is that a simple task can often be handled with a fairly simple harness. But the hidden cost is really around context. One of the more interesting things I’ve seen is that two different harnesses can make a similar number of model calls while consuming a very different amount of context. I think I recently came across a paper comparing Claude Code and Pi that touched on this. More context, more tooling, focused context, simpler loops, all of these can lead to very different costs and performance, even when the number of model calls looks similar.

snehesht

I have been using jcode for past two weeks, honestly I feel its much better compared to Opencode.

lukax

What matters more is that you use the tools that the target model was fine-tuned on. E.g. for editing files with Claude models you should use Edit(file_path, old_string, new_string, replace_all) but with GPT models you should use apply_patch_call(patch) (where patch is a custom patch string with custom grammar). It appears newer models are better at narive harness tool calls and worse at custom tools that look similar to default tools. https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/

sn0n

It matters about as much as where you leave the electrician, he’s gonna use what tools he has to get the job done with what he has.