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.
npx agentmods add commands/druide67/asiai/compare.jagit clone --depth 1 https://github.com/druide67/asiaiWrote 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.
[](https://agentmods.dev/commands/druide67/asiai/compare.ja)<a href="https://agentmods.dev/commands/druide67/asiai/compare.ja"><img src="https://agentmods.dev/badge/commands/druide67/asiai/compare.ja.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.00412 |
| Opus 5 | $0.00021 | $0.00206 |
| Sonnet 5 | $0.00008 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
compare.ja 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- compare.ko — 100% identical, 30 lines differ
- compare.zh — 95% identical, 30 lines differ
What it actually says
asiai compare
ローカルベンチマークをコミュニティデータと比較します。
使用方法
asiai compare [options]
オプション
| オプション | 説明 |
|---|---|
--chip CHIP |
比較対象のApple Siliconチップ（デフォルト：自動検出） |
--model MODEL |
モデル名でフィルター |
--db PATH |
ローカルベンチマークデータベースのパス |
例
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)
注意事項
--chipが指定されていない場合、asiai はApple Siliconチップを自動検出します。- デルタはローカルの中央値とコミュニティの中央値の差をパーセンテージで表示します。
- 正のデルタは、あなたのセットアップがコミュニティ平均より速いことを意味します。
- ローカル結果はベンチマーク履歴データベース（デフォルト：
~/.local/share/asiai/benchmarks.db）から取得されます。
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.
- 5d ago First seen · 46 lines · 42 tokens per session scan A a67fa5552cdc
compare.ja is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 42 tokens to every session and 412 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.
Other commands, from other repositories
perfup
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR.
netllm-connect
Wire Cursor, Claude Code, Codex, or Honcho to the local netllm router.
netllm-setup
First-time netllm install from this repo (uv sync, init, discover, verify).
simplicio-status
Toggle the simplicio-prompt opt-in status output ([Tuple Space Snapshot] / [Active] / [Total] / [Next Yool] / [Partial Result]).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.