Arena

Fan out N parallel attempts at the same task. Read every candidate end to end. Pick the strongest as the base. Graft the best ideas from the others into it. Verify the synthesized result.

Start

Open a todolist with one entry per phase before launching anything.

1. Frame
2. Fan out
3. Cross-judge
4. Pick
5. Graft
6. Verify

Phase A: Frame

The N candidates will receive the same prompt, so the prompt is the contract.

1. State the artifact each candidate is producing.
2. Derive the rubric. State what success looks like for this task, then turn it into 3-6 concrete gradeable criteria. The rubric is the picker's tool in Phase D. Candidates only see the task.
3. Pick the runners. Use the arena runners line in p3-models.md, resolved against orchestrator_capabilities. If the file or that line is missing, run setup-p3 or pick one model per available provider from orchestrator_capabilities. An auto or inherit-parent entry in this line or the cross-judge line means the parent model, so omit model for it. If delegate_task rejects a configured entry, run that seat on the closest valid model of the same provider from its error message and say so. Spawn more when the arena covers multiple design directions. Same model N times when the work is generation-bound rather than judgment-sensitive.
4. Assign output paths. Each candidate writes to its own location (a git worktree where possible, otherwise /tmp/arena-<slug>/candidate-<n>/), per the separate-before-serializing-shared-state principle skill. A candidate that needs its own worktree gets one through t3_thread_launch with a workspaceStrategy. One writer per worktree.

Phase B: Fan out

Spawn all N candidates in one turn with delegate_task, one per runner entry, each with mode: "async". T3 child agents get only the brief, never the parent's context, so every brief stands alone: the task, the path to the shared grounding, its own output path, and instructions to produce both the artifact and a short rationale.

Each rationale names the alternatives the candidate considered and what it rejected.

Drain the candidates with task_status. If a candidate fails to produce output, proceed with N-1 and note the dropout in the synthesis record.

Phase C: Cross-judge

After all Phase B candidates complete, choose one model from the arena cross-judge pool line in p3-models.md. Prefer a different provider from the parent's. Spawn one judge with delegate_task on that model. The brief says read-only: inspect only, no writes. It sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with the parent's reading in Phase D, not with the candidates themselves. Don't spawn the judge while candidates are still writing.

Phase D: Pick a base

Read every candidate end to end before picking.

Score each candidate against the rubric criterion by criterion, not on holistic feel. Compare against the cross-judge. Agreement on the base confirms the pick. Disagreement means one of you is biased or the rubric was ambiguous. Read both rationales before deciding.

Pick the base on which candidate a future maintainer can extend most easily without breaking invariants. Prefer the cleaner boundary or smaller API when two feel tied, per the Laziness Protocol.

Record the pick and the reason in a short synthesis note alongside the base artifact, including the cross-judge's verdict.

Phase E: Graft

Walk each losing candidate once more and identify what is worth porting into the base. The signal is usually one or two things per candidate, not most of it.

Fold each graft in by hand, per the redesign-from-first-principles principle skill. Don't paste mechanically. The result has to remain coherent under one mental model.

Record what was grafted, from which candidate, and what was rejected and why.

When N candidates converge on the same shape, that is a strong agreement signal. Note the convergence in the record and ship the consensus shape. No graft is needed. When N candidates wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.

Phase F: Verify

The synthesized artifact has to hold up under the same scrutiny as any other output, per the prove-it-works principle skill.

If verification surfaces a problem the arena did not catch, either Phase A was wrong (re-frame and re-run) or one candidate caught it and you missed the graft (go back to Phase E). Don't paper over.

Outputs

One synthesized artifact. One short synthesis note alongside, naming the base, the grafts (with source candidate), the rejections, the dropouts if any, and the verification result.