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/bench.zhgit 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/bench.zh)<a href="https://agentmods.dev/commands/druide67/asiai/bench.zh"><img src="https://agentmods.dev/badge/commands/druide67/asiai/bench.zh.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 | $0.00033 | $0.01745 |
| Opus 5 | $0.00016 | $0.00873 |
| Sonnet 5 | $0.00007 | $0.00349 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade B, and why
bench.zh scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `--power` | 使用 sudo powermetrics 交叉验证功耗（IOReport 始终开启） | How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
asiai bench
使用标准化提示词进行跨引擎基准测试。
用法
asiai bench [options]
选项
| 选项 | 描述 |
|---|---|
-m, --model MODEL |
基准测试的模型（默认：自动检测） |
-e, --engines LIST |
筛选引擎（如 ollama,lmstudio,mlxlm） |
-p, --prompts LIST |
提示词类型：code、tool_call、reasoning、long_gen |
-r, --runs N |
每提示词运行次数（默认：3，用于中位数 + 标准差） |
--power |
使用 sudo powermetrics 交叉验证功耗（IOReport 始终开启） |
--context-size SIZE |
上下文填充提示词：4k、16k、32k、64k |
--export FILE |
导出结果到 JSON 文件 |
-H, --history PERIOD |
显示历史基准测试（如 7d、24h） |
-Q, --quick |
快速基准测试：1 个提示词（code），1 次运行（约 15 秒） |
--compare MODEL [MODEL...] |
跨模型比较（2-8 个模型，与 -m 互斥） |
--card |
生成可分享的基准测试卡片（本地 SVG，配合 --share 生成 PNG） |
--share |
将结果分享到社区基准测试数据库 |
示例
asiai bench -m qwen3.5 --runs 3 --power
Mac Mini M4 Pro — Apple M4 Pro RAM: 64.0 GB (42% used) Pressure: normal
Benchmark: qwen3.5
Engine tok/s (±stddev) Tokens Duration TTFT VRAM Thermal
────────── ───────────────── ───────── ────────── ──────── ────────── ──────────
lmstudio 72.6 ± 0.0 (stable) 435 6.20s 0.28s — nominal
ollama 30.4 ± 0.1 (stable) 448 15.28s 0.25s 26.0 GB nominal
Winner: lmstudio (2.4x faster)
Power: lmstudio 13.2W (5.52 tok/s/W) — ollama 16.0W (1.89 tok/s/W)
提示词
四种标准化提示词测试不同的生成模式：
| 名称 | Token 数 | 测试内容 |
|---|---|---|
code |
512 | 结构化代码生成（Python BST） |
tool_call |
256 | JSON 函数调用 / 指令跟随 |
reasoning |
384 | 多步数学问题 |
long_gen |
1024 | 持续吞吐量（bash 脚本） |
使用 --context-size 测试大上下文填充提示词。
跨引擎模型匹配
运行器自动跨引擎解析模型名——gemma2:9b（Ollama）和 gemma-2-9b（LM Studio）被识别为同一模型。
JSON 导出
导出结果用于分享或分析：
asiai bench -m qwen3.5 --export bench.json
JSON 包含机器元数据、按引擎统计（中位数、95% 置信区间、P50/P90/P99）、原始每次运行数据和 schema 版本。
回归检测
每次基准测试后，asiai 将结果与过去 7 天的历史比较，对性能回归发出警告（如引擎更新或 macOS 升级后）。
快速基准测试
运行单提示词单次运行的快速基准测试（约 15 秒）：
asiai bench --quick
asiai bench -Q -m qwen3.5
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 · 164 lines · 33 tokens per session scan B a86c2e1000d9
bench.zh 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 1,745 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.
integrate-pipeline
Integrate a new document parsing pipeline into ParseBench: $ARGUMENTS.
netllm-setup
First-time netllm install from this repo (uv sync, init, discover, verify).
netllm-swarm
Configure multi-machine LAN mesh for netllm (mDNS, peers, gateway).
/opsx-explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
/opsx-propose
Propose a new change - create it and generate all artifacts in one step.