arena · git:20261109.c998def · 2026-11-09 · sha256 22463b4f97195177
arena git:20261109.c998defA
Immutable. This exact content never changes and is served at /api/v1/blob/22463b4f97195177.
No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_dkn3ppbdd5xbv5av/22463b4f971951776ad313d9ea709d48f3747705648b415c2f123e1d41fd1cdc.json
Then /plugin install arena@markdownregistry-dkn3ppbdd5xbv5av in Claude Code. It installs this exact version, the one graded A here, pinned to the commit it was graded at, and leaves it there.
--- name: arena description: "Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape." disable-model-invocation: true --- # 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. <!-- CORE-OVERLAY-START --> ## This repository (Asymmetric-al/core) Vendored from [p3-stack](https://github.com/uzairansaruzi/p3-stack) (MIT) at commit `09909eb`. Provenance is in `references/upstream.md`. On conflict, the current user request, root `AGENTS.md`, the nearest nested `AGENTS.md`, and the matching `docs/ai/rules/*` rulebook win over this skill. - Explicit invocation only: use it when the user invokes `/arena` (Claude Code, Cursor, T3 Code) or `$arena` (Codex), or when an invoked p3-stack skill routes here. Do not route other work to it. - The T3 Code tools named above map to Claude Code, Codex, and Cursor in `docs/ai/skills/p3-mode/references/core-adapter.md`. Read it before you delegate, watch a PR, schedule work, or drive a preview outside T3 Code. - Confirm before outward-facing or hard-to-reverse actions such as pushing, merging, deploying, deleting, or posting messages, unless the user authorized that action for this task. - Use the operating system's temporary directory for candidate scratch space when `/tmp` does not exist. Edit this canonical copy in `docs/ai/skills/arena/`, then run `bun run skills:sync` and `bun run skills:verify`. <!-- CORE-OVERLAY-END -->