agentmods.dev

arena

arena is a skill for Claude Code from serdardb/multi-agent. It costs 49 tokens per session (868 once invoked), scanned A, original, MIT.

A fixed workflow in which several AI models review code, critique one another, converge on conclusions, and have a judge verify the results against the actual code.

In plain words
What is it for?
Use it to run a multi-model code audit, choose which agent and AI command-line tools participate, and view the process and scoreboard in /workflows.
Why use it?
It provides multiple independent assessments and a structured way to compare disagreements before producing a final review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the multi-agent plugin — 2 skills, 3 agents shipped together

not rated 1repo 2mo ago A scan 49 tokens original MIT

Good fit Use it to run a multi-model code audit, choose which agent and AI command-line tools participate, and view the process and scoreboard in /workflows.

Compare 6 skills from other repositories ↓
View source ↗ serdardb/multi-agent dogrubakar.com
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add serdardb/multi-agent
Claude Code
/plugin install multi-agent

Made for: Claude Code.

Or install multi-agent, the plugin that ships this one along with the rest of its 2 skills, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for arena

README.md
[![agentmods](https://agentmods.dev/badge/skills/serdardb/multi-agent/arena/github.svg)](https://agentmods.dev/skills/serdardb/multi-agent/arena)
Your own site
<a href="https://agentmods.dev/skills/serdardb/multi-agent/arena"><img src="https://agentmods.dev/badge/skills/serdardb/multi-agent/arena/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for arena

Your own site · 80×15
<a href="https://agentmods.dev/skills/serdardb/multi-agent/arena"><img src="https://agentmods.dev/badge/skills/serdardb/multi-agent/arena.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 868 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00868
Opus 5.5 $0.00020 $0.00347
Sonnet 5.5 $0.00010 $0.00174
Haiku 4.5 $0.00005 $0.00087

Measured 1mo ago against content hash 29998885c4a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arena scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/arena/SKILL.md · 48 lines

What it actually says

Run a DETERMINISTIC multi-model review arena. The whole pipeline (rounds, cross-critique, convergence, judge, scoreboard) is fixed in the engine — you ONLY collect the user's choices and launch it. Do NOT greet or narrate; go straight to step 1. Never audit anything yourself.

  1. Resolve the engine path: run echo "${CLAUDE_PLUGIN_ROOT}" → call the result ENGINE. The arena CLI is ENGINE/arena.py; the workflow script is ENGINE/arena.workflow.js.

  2. List what's available: python3 ENGINE/arena.py list --path . → parse JSON {models, agents}. If models is empty, say no AI CLIs are usable and stop. If $ARGUMENTS already carries <agent> <models> <topic>, use them and skip the matching questions.

  3. Pick the agent: AskUserQuestion, one option per entry in agents (label = name, description = its description).

  4. Pick the AIs: AskUserQuestion (multiSelect), one option per entry in models. Default: all.

  5. Topic + scope: if given in $ARGUMENTS, use it. Otherwise ask what to review. If they refer to changes / a method / a path, resolve scope with git diff / git status / Grep and fold it into the topic. (You interpret intent in any language.)

  6. Suggest the mode: python3 ENGINE/arena.py suggest-mode --topic "<topic>" → {mode, reason}. Show it, then AskUserQuestion: keep it or switch (adversarial = debate & critique; independent = audit separately). The user's pick wins.

  7. Rounds & options: AskUserQuestion for min/max rounds (preset min 2 / max 4; independent ignores this) and judge on/off (recommended on). Tip: grok+codex as debaters with claude as the neutral judge is a good default.

  8. Launch the WORKFLOW (shows in /workflows): Workflow({ scriptPath: "ENGINE/arena.workflow.js", args: { arenaPath: "ENGINE/arena.py", agent: "<agent path>", agentName: "<agent name>", models: ["grok","codex",...], topic: "<full topic+scope>", mode: "<mode>", minRounds: <n>, maxRounds: <m>, judge: <true|false>, path: "." } }) (substitute the real ENGINE). Tell the user it's running and they can watch it live in /workflows.

  9. Present when it finishes (it returns rounds, judge, scoreboard):

    • 🏆 scoreboard first: winner: <model> (or tie: a = b), then per model: <model>: <points> pts · <confirmed> confirmed · <false> false · <unique> unique.
    • the FINAL ranked findings — the judge's list if judging was on, else the last round; most-severe first.
    • how each model's positions evolved (NEW → KEEP / WITHDRAW / ADOPT). Cross-model findings are unverified claims unless the judge marked them CONFIRMED against real code; flag the rest and offer to trace any finding's call chain.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 48 lines · 49 tokens per session scan A 29998885c4a5

Subscribe to this mod's changes

arena is a skill published in the GitHub repository serdardb/multi-agent (1 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 868 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeCode reviewadversarialai-agentsclaude-code-plugincode audit
Related

Other skills, from other repositories

code-gauntlet

Prefer this skill for code review requests — it runs a multi-agent pipeline with blind challenge verification for high-confidence results. Trigger for ANY of these situations: (1) user says "review" in the context of code, PRs, MRs, branches, diffs, or changes, (2) user references a PR/MR number and wants feedback or…

liatrio-labs/claude-code-gauntlet · 218 tokens

build-review-md

Use this skill when the user wants to create or set up a REVIEW.md configuration file for their repository. Trigger for ANY of these: (1) user says "create REVIEW.md", "set up REVIEW.md", or "configure review rules", (2) code-gauntlet Phase 2d detects no REVIEW.md and suggests creating one, (3) user wants to customize…

liatrio-labs/claude-code-gauntlet · 171 tokens

Refactor-Claim Audit リファクタ完了主張の検証

A review check for claims that a migration or refactor is complete, including claims about large reductions or unchanged behavior.

s977043/river-review · 120 tokens

Cross-File Leakage リファクタ後の caller 側残骸検出

A code review check for structural changes such as renamed functions, changed arguments, moved files, or split modules. It searches the rest of the project for callers that still use the old structure.

s977043/river-review · 79 tokens

Logic Torturing 論理検証

A review method for testing the reasoning behind design choices and implementation decisions in a code change.

s977043/river-review · 57 tokens

Self-Contradiction Detector 自己矛盾検出

A consistency check that compares written rules with the code or implementation next to them.

s977043/river-review · 59 tokens