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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Arena
In Claude Code, read [the Claude Code adapter](../../docs/harness/claude-code.md) once per session before you follow this skill. It maps the Cursor names in pstack skills to Claude Code.
Open a todolist with one entry per phase (Frame, Fan out, Cross-judge, Pick, Graft, Verify) before launching anything.
## Phase A: Frame
Every candidate gets the same prompt, so the prompt is the contract.
1. State the artifact each candidate is producing.
2. Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on *this* task. It is the picker's tool in Phase D. Candidates only see the task.
3. Pick the runners. Use the `arena runners` line in `~/.cursor/rules/pstack-models.mdc`. If the rule or that line is missing, default to one each on `claude-opus-5-5-xhigh` and `grok-4.7-xhigh-fast`. An `auto` or `inherit-parent` entry in this line or the cross-judge line means the parent model, so omit `model` for it. If the Task tool rejects a configured entry, run that seat on its family's default and say so. Families go by prefix: `claude-*`, and `grok-*` with `cursor-grok-*` and `composer-*`. A refused `composer-*` entry runs on `grok-4.7-xhigh-fast`. With no family
…
The line at the top of this page pins the label git:20261016.182f2ce, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_4xo4cckhu4a2og2u
GET https://markdownregistry.com/api/v1/resolve?ref=cursor/plugins/arena
GET https://markdownregistry.com/api/v1/blob/1129389c9b1361841c40eb668b8e7c34f64184782b3036621db1edffb665ecf9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
cursor/plugins · advisor/skills/advisor/SKILL.md · Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an…
cursor/plugins · agent-compatibility/skills/check-agent-compatibility/SKILL.md · Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.
cursor/plugins · cli-for-agent/skills/cli-for-agents/SKILL.md · Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples…
cursor/plugins · create-plugin/skills/create-plugin-scaffold/SKILL.md · Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring. Use when…
cursor/plugins · create-plugin/skills/review-plugin-submission/SKILL.md · Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths…
cursor/plugins · cursor-sdk/skills/cursor-sdk/SKILL.md · Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`)…
cursor/plugins · cursor-team-kit/skills/control-cli/SKILL.md · Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use…
cursor/plugins · cursor-team-kit/skills/control-ui/SKILL.md · Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI…
cursor/plugins · pstack/skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
michael-denyer/pstack-claude · plugins/pstack/skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
backnotprop/pstack · skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
j-star-films-studios/vibecode-protocol-suite · assets/.agent/skills/agent-engineering/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
creedants/pstack-t3 · t3/overrides/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
creedants/pstack-t3 · skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
arjitj2/open-pstack · plugins/pstack/skills/arena/SKILL.md · Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for…
