compare

compare is a command for coding agents from AURORA-NEURO/aurora-agent. It costs 26 tokens per session (299 once invoked), scanned A, original, Apache-2.0.

A command for comparing FIBER, a compiler, with simpler reference methods on a specified test world and query. It reports which methods expose the needed facts and preserve the reference answer.

In plain words
What is it for?
Running graph-walk and lexical-retrieval comparisons, measuring exposed facts and protected recall, listing missing evidence, and identifying the cheapest method that preserves the expected verdict.
Why use it?
It prevents treating a method as correct merely because it returns a valid-looking status. The comparison highlights whether each method reaches the same verdict and which acceptable method is cheapest.

Command

Part of the aurora-agent plugin — 4 skills, 7 commands, 1 agent 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/aurora-neuro/aurora-agent/compare
Clone the repo
git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Or install aurora-agent, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 1 agent.

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 compare

README.md
[![agentmods](https://agentmods.dev/badge/commands/aurora-neuro/aurora-agent/compare.svg)](https://agentmods.dev/commands/aurora-neuro/aurora-agent/compare)
Your own site
<a href="https://agentmods.dev/commands/aurora-neuro/aurora-agent/compare"><img src="https://agentmods.dev/badge/commands/aurora-neuro/aurora-agent/compare.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 299 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 $0.00026 $0.00299
Opus 5 $0.00013 $0.00150
Sonnet 5 $0.00005 $0.00060
Haiku 4.5 $0.00003 $0.00030

Measured 5d ago against content hash fb9b122e8ccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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/aurora-agent/commands/compare.md · 22 lines

What it actually says

Run the baseline comparison and report it with its honesty semantics intact.

  1. Resolve the aurora-agent checkout ($AURORA_AGENT_ROOT~/aurora-agent~/bioprism); CLI at <root>/target/release/bioprism(.exe).
  2. Defaults if $ARGUMENTS is empty: the reference fixture pair (fixtures/fiber-v0.1/radiogenomic_world.json, fixtures/fiber-v0.1/leakage_query.json).
  3. Run from the checkout root: bioprism --json context compare --world <world> --query <query>
  4. Report per strategy: facts exposed, fraction of world, status, verdict_preserving, admissible, protected recall, missing witnesses. CRITICAL: a "valid" status from a strategy whose verdict_preserving is false is a FALSE verdict — judge strategies by verdict preservation, never by the status column alone. Name the cheapest_admissible_strategy verbatim, including when it is a baseline rather than FIBER — that honest headline is the point of the tool.
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. 5d ago First seen · 22 lines · 26 tokens per session scan A fb9b122e8ccd

Subscribe to this mod's changes

compare is a command published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 299 once invoked, about $0.0001 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.