arena

Files (2)

• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

# 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 from `roles.arena-runners` in `~/.codex/pstack/models.yaml`. Default to `gpt-6-astra`, `gpt-6-sol`, and `gpt-6-luna`. An `inherit-parent` entry means omit the model override. Pass the configured reasoning effort separately. If a configured model is unavailable, use the nearest available Codex model and report the fallback.
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.

## Phase B: Fan out

Launch all N children concurrently with `collaboration.spawn_agent`. Give each a unique task name, the task, the shared grounding path, 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.

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 `roles.arena-cross-judge-pool` in `~/.codex/pstack/models.yaml`, defaulting to `gpt-6-astra`. Prefer a model different from the candidate that produced the likely base. Spawn one read-only judge. It sees the rubric and candidates by path label, scores each criterion, and recommends a base with rationale. Collect each finished child and call `collaboration.interrupt_agent` before continuing.

## 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.

From vuongquocphong/pstack-codex, MIT.

More from vuongquocphong/pstack-codex