compare.it

compare.it is a command for coding agents from druide67/asiai. It costs 31 tokens per session (350 once invoked), scanned A, original, Apache-2.0.

A benchmark comparison command for local AI models and the programs that run them. It compares your recorded results with community median results for an Apple Silicon chip.

In plain words
What is it for?
Use it to compare up to eight model-and-engine combinations, filter by model or chip, and view token-per-second results and percentage differences from the community median.
Why use it?
It shows whether your setup is faster or slower than similar community setups, without requiring you to compare benchmark records manually.

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.it
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.it

README.md
[![agentmods](https://agentmods.dev/badge/commands/druide67/asiai/compare.it.svg)](https://agentmods.dev/commands/druide67/asiai/compare.it)
Your own site
<a href="https://agentmods.dev/commands/druide67/asiai/compare.it"><img src="https://agentmods.dev/badge/commands/druide67/asiai/compare.it.svg" alt="Measured on agentmods" height="20"></a>
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 350 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 $0.00031 $0.00350
Opus 5 $0.00015 $0.00175
Sonnet 5 $0.00006 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 4d ago against content hash 1d6aba559460, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare.it 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.it.md · 46 lines

What it actually says

asiai compare

Confronta i tuoi benchmark locali con i dati della community.

Uso

asiai compare [options]

Opzioni

Opzione Descrizione
--chip CHIP Chip Apple Silicon contro cui confrontare (default: rilevamento automatico)
--model MODEL Filtra per nome modello
--db PATH Percorso al database benchmark locale

Esempio

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)

Note

  • Se --chip non è specificato, asiai rileva automaticamente il tuo chip Apple Silicon.
  • Il delta mostra la differenza percentuale tra la tua mediana locale e la mediana della community.
  • Delta positivi significano che la tua configurazione è più veloce della media comunitaria.
  • I risultati locali provengono dal tuo database storico di benchmark (~/.local/share/asiai/benchmarks.db di default).
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 · 31 tokens per session scan A 1d6aba559460

Subscribe to this mod's changes

compare.it is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 31 tokens to every session and 350 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.