multi-model

A command that sends a task through several large language models, has them compare or judge answers, and repeats the process for refinement.

In plain words
What is it for?
Use it to ask several language models to solve a task, review the competing answers, see the winning answer and scores, and inspect how results change across rounds.
Why use it?
It helps expose weaknesses in one generated answer by comparing multiple attempts and selecting a judged result.

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/multi-model
Clone the repo
git clone --depth 1 https://github.com/lollipopkit/cc-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 157 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 $0.00011 $0.00157
Opus 5 $0.00005 $0.00078
Sonnet 5 $0.00002 $0.00031
Haiku 4.5 $0.00001 $0.00016

Measured yesterday against content hash 1f3d8717c6cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-model 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 yesterday.

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/multi-model.md · 28 lines

What it actually says

Multi-Model Command

Use the multi-model skill to run a multi-model battle where different LLMs compete and judge each other's answers.

Task

$ARGUMENTS

Instructions

Run the multi-model script with the given task:

python3 "${CLAUDE_PLUGIN_ROOT}/skills/multi-model/scripts/multi_model.py" --prompt "$ARGUMENTS" --iters 5

Parse the output and present:

  1. The winning answer
  2. Judge scores summary
  3. Model rotation insights (using numeric IDs only, never disclose model names)
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. yesterday First seen · 28 lines · 11 tokens per session scan A 1f3d8717c6cf

Subscribe to this mod's changes

multi-model is a command published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 157 once invoked, about $0.0001 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.