llm-compare

llm-compare is a command for coding agents from gopherguides/gopher-ai. It costs 7 tokens per session (2,143 once invoked), scanned A, original, MIT.

A command that sends the same question to several language models and compares their answers. Language models are AI systems that generate and analyze text.

In plain words
What is it for?
Use it for architecture decisions, code reviews, error handling, security questions, and language-specific best-practice checks.
Why use it?
Comparing answers can reveal differing suggestions, assumptions, or risks before you choose an approach.

Command

Part of the llm-tools plugin — 2 skills, 7 commands shipped together

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/gopherguides/gopher-ai/llm-compare
Clone the repo
git clone --depth 1 https://github.com/gopherguides/gopher-ai

Or install llm-tools, the plugin that ships this one along with the rest of its 2 skills, 7 commands.

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 llm-compare

README.md
[![agentmods](https://agentmods.dev/badge/commands/gopherguides/gopher-ai/llm-compare.svg)](https://agentmods.dev/commands/gopherguides/gopher-ai/llm-compare)
Your own site
<a href="https://agentmods.dev/commands/gopherguides/gopher-ai/llm-compare"><img src="https://agentmods.dev/badge/commands/gopherguides/gopher-ai/llm-compare.svg" alt="Measured on agentmods" height="20"></a>
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 2,143 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 $0.02143
Opus 5 $0.00003 $0.01071
Sonnet 5 $0.00001 $0.00429
Haiku 4.5 $0.00001 $0.00214

Measured 4d ago against content hash 2e32d8d5ccb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-compare 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 4d 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/llm-tools/commands/llm-compare.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compare Multiple LLMs

If $ARGUMENTS is empty or not provided:

Run the same prompt through multiple LLMs and compare responses.

Usage: /llm-compare <prompt>

Command Description
/llm-compare should I use microservices or monolith Architectural decision
/llm-compare review this error handling approach Code review comparison
/llm-compare what are the security risks here Security analysis
/llm-compare is this the idiomatic Go approach Best practices

Available LLMs: OpenAI (codex, cloud, strong reasoning) · Gemini (gemini, cloud, good at analysis) · Ollama (ollama, local, private, various models).

Ask: "What question would you like multiple LLMs to answer?"


If $ARGUMENTS is provided:

Compare responses from multiple LLMs for: $ARGUMENTS.

1. Select LLMs to Compare

AskUserQuestion (select 2-3): OpenAI / Gemini / Ollama. Default: all available.

For each selected, verify availability:

# Codex must already be installed for this automated comparison
CODEX_AVAILABLE=false
if command -v codex &>/dev/null; then
  CODEX_CMD="codex"; CODEX_AVAILABLE=true
fi
command -v gemini >/dev/null 2>&1 && GEMINI_AVAILABLE=true || GEMINI_AVAILABLE=false
command -v ollama >/dev/null 2>&1 && OLLAMA_AVAILABLE=true || OLLAMA_AVAILABLE=false

If a user-selected LLM is unavailable, do NOT silently skip. Use AskUserQuestion:

"$LLM_NAME CLI not found. How would you like to proceed?"

Option Description
Retry Check again after installing
Install instructions Show how to install the missing CLI
Skip this LLM Continue without it
Abort Stop the comparison

Only skip if the user explicitly chooses "Skip this LLM".

For Codex installation guidance, show npm install -g @openai/codex. Explain that codex login supports ChatGPT sign-in and API-key authentication. Do not download or execute a package as part of the availability check.

Read the full file on GitHub · 243 lines

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. 4d ago First seen · 243 lines · 7 tokens per session scan A 2e32d8d5ccb4

Subscribe to this mod's changes

llm-compare is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 2,143 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 2026-08-30.