compare.de

compare.de is a command for coding agents from druide67/asiai. It costs 34 tokens per session (344 once invoked), scanned A, original, Apache-2.0.

A command-line comparison for measuring how quickly different AI models run through different local engines on Apple Silicon Macs. It compares your benchmark history with community median results.

In plain words
What is it for?
Use it to filter by model or chip, compare engine results, and inspect speed in tokens per second. It reads results from a local benchmark database.
Why use it?
It removes the need to compare benchmark files manually or guess whether your setup is fast. It shows the difference between your local median and the community median.

Command

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/druide67/asiai/compare.de
Clone the repo
git clone --depth 1 https://github.com/druide67/asiai

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.de

README.md
[![agentmods](https://agentmods.dev/badge/commands/druide67/asiai/compare.de.svg)](https://agentmods.dev/commands/druide67/asiai/compare.de)
Your own site
<a href="https://agentmods.dev/commands/druide67/asiai/compare.de"><img src="https://agentmods.dev/badge/commands/druide67/asiai/compare.de.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00034 $0.00344
Opus 5 $0.00017 $0.00172
Sonnet 5 $0.00007 $0.00069
Haiku 4.5 $0.00003 $0.00034

Measured 4d ago against content hash f489f975fa7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare.de 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.

docs/commands/compare.de.md · 46 lines

What it actually says

asiai compare

Vergleichen Sie Ihre lokalen Benchmarks mit Community-Daten.

Verwendung

asiai compare [options]

Optionen

Option Beschreibung
--chip CHIP Apple-Silicon-Chip zum Vergleich (Standard: Auto-Erkennung)
--model MODEL Nach Modellname filtern
--db PATH Pfad zur lokalen Benchmark-Datenbank

Beispiel

asiai compare --model qwen3.5
  Compare: qwen3.5 — M4 Pro

  Engine       Your tok/s   Community median   Delta
  ────────── ──────────── ────────────────── ────────
  lmstudio        72.6           70.1          +3.6%
  ollama          30.4           31.0          -1.9%

  Chip: Apple M4 Pro (auto-detected)

Hinweise

  • Wenn --chip nicht angegeben wird, erkennt asiai Ihren Apple-Silicon-Chip automatisch.
  • Das Delta zeigt den prozentualen Unterschied zwischen Ihrem lokalen Median und dem Community-Median.
  • Positive Deltas bedeuten, dass Ihr Setup schneller als der Community-Durchschnitt ist.
  • Lokale Ergebnisse stammen aus Ihrer Benchmark-Verlaufsdatenbank (~/.local/share/asiai/benchmarks.db standardmäßig).
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 · 46 lines · 34 tokens per session scan A f489f975fa7c

Subscribe to this mod's changes

compare.de is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 344 once invoked, about $0.0002 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 2026-08-30.