recursive-arena

A command that runs repeated rounds of answer refinement, with each round using a multi-model comparison. It reports the best result and a summary of how it evolved.

In plain words
What is it for?
Use it when a task benefits from model battles, judge scores, accumulated insights, and iterative improvement.
Why use it?
It removes the manual work of asking several models for answers, comparing them, and feeding feedback into later rounds.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/lollipopkit/cc-plugins/recursive-arena
Clone the repo
git clone --depth 1 https://github.com/lollipopkit/cc-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 176 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00007 $0.00176
Opus 5 $0.00003 $0.00088
Sonnet 5 $0.00001 $0.00035
Haiku 4.5 $0.00001 $0.00018

Measured 2d ago against content hash b21a275dacb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recursive-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 2d 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.

plugins/recursive-reasoning/commands/recursive-arena.md · 30 lines

What it actually says

Recursive-Arena Command

Use the recursive-arena skill to orchestrate recursive iterations where each iteration uses the multi-model battle as the generator.

Task

$ARGUMENTS

Instructions

Run the recursive-arena orchestrator:

python3 "${CLAUDE_PLUGIN_ROOT}/skills/recursive-arena/scripts/recursive_arena.py" --prompt "$ARGUMENTS" --iters 4 --arena-iters 3

Present the results with:

  1. Final best answer
  2. Evolution summary table (iteration, writer model ID, avg judge score, key refinement)
  3. Accumulated insights from the reflection memory

Never disclose provider/model names; only use numeric IDs.

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. 2d ago First seen · 30 lines · 7 tokens per session scan A b21a275dacb9

Subscribe to this mod's changes

recursive-arena is a command published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 176 once invoked, about $0.0000 per session on Opus 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.