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
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 the configured pstack model panel (`pstack-models.json` in the hermes config dir next to `config.yaml`). If the rule or that line is missing, default to one each on `claude-opus-5-5-max`, `gpt-5.6-sol-max`, `grok-4.7-xhigh-fast`. An `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 its family's default and say so. Families go by prefix…
…
The line at the top of this page pins the label git:20261006.f7c5841, 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.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5133 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
iap/pstack-hermes · 30 stars · license a license file GitHub does not identify · pushed 2026-10-31 · branch dist
API
GET https://markdownregistry.com/api/v1/artifacts/art_tbfn5637ynff2o5y
GET https://markdownregistry.com/api/v1/resolve?ref=iap/pstack-hermes/arena
GET https://markdownregistry.com/api/v1/blob/f164f3affec261fa9f0d24bd7bb467eae45cbffbdfd3b815dc226e72991e76b5
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.
iap/pstack-hermes · skills/architect/SKILL.md · Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use…
iap/pstack-hermes · skills/automate-me/SKILL.md · Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a…
iap/pstack-hermes · skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
iap/pstack-hermes · skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives your app the way a user does — any language, framework, or…
iap/pstack-hermes · skills/figure-it-out/SKILL.md · Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a…
iap/pstack-hermes · skills/hermesbot/SKILL.md · Use when building a control surface (page, dashboard, buttons) that wakes a hermes bot over a webhook subscription…
iap/pstack-hermes · skills/how/SKILL.md · Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions…
iap/pstack-hermes · skills/interrogate/SKILL.md · Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find…
cursor/plugins · harness/pstack/claude-code/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…
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…
nightly-labs/openbot · marketplace/production-catalog/bundles/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…
barbieri/local-openfinance · .agents/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…