comparator

comparator is an agent for coding agents from Vibe-Marketer/plugins-and-skills. It costs 251 tokens per session (1,257 once invoked), scanned A, original, MIT.

An agent for comparing two sets of skill outputs without knowing which one produced each set. It uses a task-specific checklist to assess what the outputs say and how they are organized.

In plain words
What is it for?
Use it for blind A/B tests, output comparisons, and evaluations of correctness, completeness, accuracy, organization, formatting, usability, and practical value.
Why use it?
It provides a structured way to decide which of two outputs is better while reducing bias from knowing their origins.

Agent

Part of the create-plugins plugin — 12 skills, 6 commands, 9 agents 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 agents/vibe-marketer/plugins-and-skills/comparator
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 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 comparator

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/comparator.svg)](https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/comparator)
Your own site
<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/comparator"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/comparator.svg" alt="Measured on agentmods" height="20"></a>
Per session 251 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,257 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 $0.00251 $0.01257
Opus 5 $0.00125 $0.00629
Sonnet 5 $0.00050 $0.00251
Haiku 4.5 $0.00025 $0.00126

Measured 4d ago against content hash f4a2a4cf8f97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comparator 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.

create-plugins/agents/comparator.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The outputs are labeled A and B with no skill identification. Maintain blindness throughout. </step_1>

<step_2 name="read_outputs"> Read both outputs completely:

  • Catalog all files in each output set
  • Read full content of each file
  • Note structural differences (file count, organization, naming)
  • Do not attempt to identify which skill produced which output </step_2>

<step_3 name="generate_rubric"> Create a task-specific rubric with two dimensions:

Content dimension (what the output says):

  • Correctness: factual accuracy, logical soundness
  • Completeness: coverage of required elements
  • Accuracy: precision of claims, data, examples

Structure dimension (how the output is organized):

  • Organization: logical flow, hierarchy, navigation
  • Formatting: readability, consistency, visual clarity
  • Usability: practical applicability, actionability

Tailor criteria to the specific task. A marketing copy evaluation differs from a technical analysis evaluation. </step_3>

<step_4 name="score_independently"> For each rubric criterion:

  1. Evaluate Output A (1-5 scale)
  2. Evaluate Output B (1-5 scale)
  3. Cite specific evidence from each output
  4. Note any standout strengths or weaknesses

Scoring guide:

  • 1: Poor -- fails to meet basic expectations
  • 2: Below average -- significant gaps
  • 3: Adequate -- meets minimum requirements
  • 4: Good -- exceeds expectations in notable ways
  • 5: Excellent -- exceptional quality, best-in-class </step_4>

<step_5 name="determine_winner"> Aggregate scores to a 1-10 overall score for each output:

  • Weight content and structure equally unless task demands otherwise
  • Identify the winner
  • Be decisive: ties should be rare and explicitly justified
  • Articulate the key differentiators </step_5>

<output_format>

Blind Comparison Results

Read the full file on GitHub · 154 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 · 154 lines · 251 tokens per session scan A f4a2a4cf8f97

Subscribe to this mod's changes

comparator is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 251 tokens to every session and 1,257 once invoked, about $0.0013 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.