Why Pi Is My GOAT Agent HarnessSkip to content<br>I was a Claude Code customer for a long time. Eventually, though, Anthropic’s pricing became harder for me to justify, and the model quality felt less consistent. I switched to OpenAI’s Codex, which was good, but the experience still had limits. New releases sometimes shipped with bugs or changes that disrupted my workflow. Codex CLI is open source, but its release cadence and product direction were not mine to control, and I did not want to maintain a fork just to keep my workflow stable. The development experience never felt fully consistent.

Then DeepSeek V4 arrived. OpenCode Go’s $10 subscription looked like a great deal, so I gave OpenCode a try. It was fast, inexpensive, and well optimized for running open models. Its plugin system also let me customize parts of the experience and workflow. Even with that flexibility, however, I still felt as though I was adapting my workflow to the harness instead of shaping the harness around how I wanted to work.

While scrolling through X, I found a Composio benchmark comparing agent harnesses with the same DeepSeek V4 Flash model. Pi came out ahead on the metrics that mattered most to me.

In Composio’s set of 30 agentic tasks, Pi passed 20, giving it a 66.7% pass rate. That was the best result among the four newly tested harnesses.

DeepSeek V4 Flash results across four newly tested agent harnesses. Source: Composio.

Cost per successful task was where Pi stood out most. Across all eight harnesses in Composio’s comparison, Pi was the cheapest at $0.028 per successful task. Claude Code was the most expensive at $0.195, almost seven times as much. Pi’s median completion time was 132.2 seconds; only Claude Code and OpenCode were faster in the broader comparison.

Estimated cost per successful task at the API rates used by Composio.

This is still one benchmark with one model and 30 tasks, not proof that Pi will win every workload. The full Composio report also notes that Pi used a different reasoning setting and two model providers, which limits a direct comparison. I treat the result as a useful signal, not a universal verdict.

The more important lesson is that the harness matters. The same model can perform very differently depending on the tools, prompts, context management, and agent loop wrapped around it. The benchmark was enough to make me curious, but Pi’s design is what convinced me to stay.

Why harness choice matters

This effect is not limited to Composio’s test. Harness-Bench evaluated 106 sandboxed tasks across 5,194 execution trajectories and found substantial differences in completion, efficiency, process quality, and failure behavior across model–harness pairings. Its authors argue that “agent capability should be reported at the model-harness configuration level” rather than attributed to the base model alone.

A second, preliminary study, The Scaffold Effect in Coding Agents, tested two models across three open-source harnesses and observed up to a 40× difference in tokens per solved task. Pass-rate differences were much smaller, between 0 and 8 percentage points in its paired comparisons. This shows that harness choice can change cost and latency even when success rates look similar.

Neither study proves that Pi is always the best harness. They support a more careful claim: the model name alone does not tell you how an agent will behave in practice.

What is Pi?

Pi describes itself as a minimal terminal coding harness . A model is only the engine; the harness is the system around it that gives the model tools, feeds it context, runs its agent loop, and connects it to your codebase.

Pi’s philosophy is simple:

Adapt Pi to your workflows, not the other way around.

Out of the box, Pi keeps the core small. Its default workflow revolves around four essential tools: read, write, edit, and bash. You can add the rest through TypeScript extensions, skills, prompt templates, themes, and packages.

In What I learned building an opinionated and minimal coding agent, Pi creator Mario Zechner summarizes the argument plainly:

“As it turns out, these four tools are all you need for an effective coding agent.”

He also notes that Pi’s default system prompt and tool definitions together fit within 1,000 tokens. The goal is not minimalism for its own sake; it is to avoid paying a permanent context and complexity cost for features that a particular workflow may never use.

That minimalism is not a limitation. It is the point. Instead of guessing which planning system, permission flow, subagent design, or UI every developer wants, Pi gives you a foundation and lets you build the workflow that suits you.

Why I chose Pi

I have now used Claude Code, Codex, OpenCode, and Pi. Each has strengths, but Pi is the first one that makes the harness itself feel like something I own.

Dimension<br>Pi<br>Claude Code<br>Codex CLI<br>OpenCode

License / source<br>MIT, open source<br>Proprietary<br>Apache-2.0, open source<br>MIT, open source

Default...