comparator

A blind reviewer that compares two outputs without knowing which tool or skill produced either one.

In plain words
What is it for?
It reads two output files or folders, checks them against the original task and optional expectations, and determines which output better meets the requirements.
Why use it?
It reduces bias toward a particular implementation by judging both outputs against the same yes-or-no questions.

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/smixs/skill-conductor/comparator
Clone the repo
git clone --depth 1 https://github.com/smixs/skill-conductor
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 2,235 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 $0.02235
Opus 5 $0.00000 $0.01118
Sonnet 5 $0.00000 $0.00447
Haiku 4.5 $0.00000 $0.00224

Measured 2d ago against content hash f6828a5bd5a4, 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.

skills/skill-conductor/agents/comparator.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 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, using binary yes/no questions.

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. There is NO 1-5 rubric and NO numeric overall_score. Instead, A and B answer the SAME set of binary questions, each with evidence.

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 Binary Questions (per dimension)

Derive a SINGLE set of binary yes/no questions from the task, organized by the 5 dimensions. Use the two-step meta-prompt:

  1. Summarize: turn the task into explicit requirements — each a distinct criterion the output must satisfy.
  2. Decompose: for each requirement, emit one or more binary yes/no questions where "yes" = satisfied and "no" = violated. Pair each with a concise violation example.

Tag each question with its dimension (Discovery, Clarity, Structure, Robustness, Completeness) and mark whether it is critical. Fold any provided expectations in as binary questions too.

Read the full file on GitHub · 178 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 · 178 lines · 0 tokens per session scan A f6828a5bd5a4

Subscribe to this mod's changes

comparator is an agent published in the GitHub repository smixs/skill-conductor (163 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,235 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 2026-08-30.