comparator

An agent that compares two skill outputs without knowing which skill produced each one. It judges them against the original task and any stated expectations.

In plain words
What is it for?
Use it to compare two files or directories of results, assess them against an evaluation prompt, and report which output better meets the requirements.
Why use it?
Blind comparison reduces bias and makes it easier to identify which output is clearer, more accurate, and more complete.

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/feiskyer/claude-code-settings/comparator
Clone the repo
git clone --depth 1 https://github.com/feiskyer/claude-code-settings
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod 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 $0.00031 $0.01798
Opus 5 $0.00015 $0.00899
Sonnet 5 $0.00006 $0.00360
Haiku 4.5 $0.00003 $0.00180

Measured 2d ago against content hash 0163e7c285cf, 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 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.

Origin

This is a copy

92% identical to comparator — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/skill-creator/agents/comparator.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 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.

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 toward a particular skill or approach.

Your judgment is based purely on output quality and task completion.

Inputs

You receive these parameters in your prompt:

  • 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 - may be empty)

Process

Step 1: Read Both Outputs

  1. Examine output A (file or directory)
  2. Examine output B (file or directory)
  3. Note the type, structure, and content of each
  4. If outputs are directories, examine all relevant files inside

Step 2: Understand the Task

  1. Read the eval_prompt carefully
  2. Identify what the task requires:
    • What should be produced?
    • What qualities matter (accuracy, completeness, format)?
    • What would distinguish a good output from a poor one?

Step 3: Generate Evaluation Rubric

Based on the task, generate a rubric with two dimensions:

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 present
Accuracy Significant inaccuracies Minor inaccuracies Accurate throughout

Structure Rubric (how the output is organized):

Criterion 1 (Poor) 3 (Acceptable) 5 (Excellent)
Organization Disorganized Reasonably organized Clear, logical structure
Formatting Inconsistent/broken Mostly consistent Professional, polished
Usability Difficult to use Usable with effort Easy to use

Read the full file on GitHub · 208 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. 2d ago First seen · 208 lines · 31 tokens per session scan A 0163e7c285cf

Subscribe to this mod's changes

comparator is an agent published in the GitHub repository feiskyer/claude-code-settings (1,639 stars, last pushed 19d ago), licensed MIT. It adds 31 tokens to every session and 1,798 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to comparator, differing in 5 lines, and is treated as a copy.

Related

Other agents, from other repositories

agents

Use Local Operator agent profiles, roles, and subagents: discover, create, select, interact, delegate, and choose the correct collaboration mode.

damianvtran/local-operator · 31 tokens

10-Challenger

Standalone adversarial review wrapper. Runs challenger-review-subagent, then runs the shared Per-Finding Decision Protocol so the user can Apply selected fixes and hand off to the next step. For orchestrated workflows, the subagent is auto-invoked by parent agents.

jonathan-vella/apex-accelerator · 60 tokens

README

Optional subagent role definitions (same format as .claw/agents/). Use this folder if you want Claude Code–style paths or to share agent files with tools that only look under .claude/.

deepelementlab/jupyter-studio · 0 tokens

cto

Use this agent as the supreme technical authority and team leader — a hyper-active, self-evolving CTO that proactively manages, delegates, monitors, debates, and adapts the entire 32-agent team. Has ALL Claude Code tools and capabilities. Can dispatch any agent, create new agents, install MCPs/plugins, evolve any…

asiflow/claude-nexus-hyper-agent-team · 573 tokens

skill-builder

Builds individual newsletter pipeline skills from agent logic, prompt files, and benchmark examples. Use with /fleet for parallel skill construction.

briancl2/CustomerNewsletter · 29 tokens

cto

Use this agent as the supreme technical authority and team leader — a hyper-active, self-evolving CTO that proactively manages, delegates, monitors, debates, and adapts the entire 26-agent team. Has ALL Claude Code tools and capabilities. Can dispatch any agent, create new agents, install MCPs/plugins, evolve any…

asiflow/claude-nexus-hyper-agent-team-light · 573 tokens