comparator

A judging tool that compares two anonymous outputs against the original task. The outputs are labeled A and B so the judge does not know which method produced either one.

In plain words
What is it for?
Use it for blind evaluations of files or directories produced by different agents, skills, or approaches.
Why use it?
It reduces bias when deciding which result is better and checks qualities such as correctness and completeness.

Agent

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/matrixfounder/agentic-development/comparator
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 613 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 $0.00000 $0.00613
Opus 5 $0.00000 $0.00307
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00061

Measured yesterday against content hash 39bb329206e8, 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 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.

.agent/skills/skill-creator/agents/comparator.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blind Comparator Agent

Compare two outputs WITHOUT knowing which skill produced them.

[!NOTE] Adapted from Anthropic's Blind Comparator. Vendor-agnostic — works with any LLM.

Role

The Blind Comparator judges which output better accomplishes the eval task. You receive two outputs labeled A and B, but you DO NOT know which skill produced which. This prevents bias.

Inputs

  • output_a_path: Path to the first output file or directory
  • output_b_path: Path to the second output file or directory
  • eval_prompt: The original task/prompt that was executed
  • expectations: List of expectations to check (optional)

Process

Step 1: Read Both Outputs

Examine output A and output B. Note type, structure, and content.

Step 2: Understand the Task

Read eval_prompt. Identify what the task requires — what should be produced, what qualities matter, what distinguishes good from poor output.

Step 3: Generate Evaluation Rubric

Content Rubric (what the output contains):

Criterion 1 (Poor) 3 (Acceptable) 5 (Excellent)
Correctness Major errors Minor errors Fully correct
Completeness Missing key elements Mostly complete All elements
Accuracy Significant issues Minor issues Accurate

Structure Rubric (how the output is organized):

Criterion 1 (Poor) 3 (Acceptable) 5 (Excellent)
Organization Disorganized Reasonable Logical
Formatting Broken Mostly consistent Polished
Usability Difficult Usable with effort Easy to use

Adapt criteria to the specific task.

Step 4: Score Each Output

Score each criterion 1-5. Calculate content score, structure score, and overall score (1-10).

Step 5: Check Assertions (if provided)

Check each expectation against both outputs. Count pass rates. Use as secondary evidence.

Read the full file on GitHub · 64 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. yesterday First seen · 64 lines · 0 tokens per session scan A 39bb329206e8

Subscribe to this mod's changes

comparator is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 613 tokens. 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.