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.kogit 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.ko)<a href="https://agentmods.dev/commands/druide67/asiai/compare.ko"><img src="https://agentmods.dev/badge/commands/druide67/asiai/compare.ko.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 5.1 | $0.00033 | $0.00370 |
| Opus 5 | $0.00016 | $0.00185 |
| Sonnet 5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
compare.ko 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 6d 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.
This is a copy
100% identical to compare.ja — 30 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
asiai compare
로컬 벤치마크를 커뮤니티 데이터와 비교합니다.
사용법
asiai compare [options]
옵션
| 옵션 | 설명 |
|---|---|
--chip CHIP |
비교할 Apple Silicon 칩 (기본: 자동 감지) |
--model MODEL |
모델 이름으로 필터 |
--db PATH |
로컬 벤치마크 데이터베이스 경로 |
예시
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)
참고 사항
--chip이 지정되지 않으면 asiai가 Apple Silicon 칩을 자동 감지합니다.- 델타는 로컬 중앙값과 커뮤니티 중앙값의 차이를 백분율로 표시합니다.
- 양수 델타는 당신의 설정이 커뮤니티 평균보다 빠르다는 의미입니다.
- 로컬 결과는 벤치마크 이력 데이터베이스(기본:
~/.local/share/asiai/benchmarks.db)에서 가져옵니다.
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.
- 6d ago First seen · 46 lines · 33 tokens per session scan A b48f53879fe2
compare.ko is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 33 tokens to every session and 370 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to compare.ja, differing in 30 lines, and is treated as a copy.
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.