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/detect.itgit 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/detect.it)<a href="https://agentmods.dev/commands/druide67/asiai/detect.it"><img src="https://agentmods.dev/badge/commands/druide67/asiai/detect.it.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 | $0.00038 | $0.00667 |
| Opus 5 | $0.00019 | $0.00333 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
detect.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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
asiai detect
Rilevamento automatico dei motori di inferenza con cascata a 3 livelli.
Uso
asiai detect # Rilevamento automatico (cascata a 3 livelli)
asiai detect --url http://host:port # Scansiona solo URL specifici
Output
Detected engines:
● ollama 0.17.4
URL: http://localhost:11434
● lmstudio 0.4.5
URL: http://localhost:1234
Running: 1 model(s)
- qwen3.5-35b-a3b MLX
● omlx 0.9.2
URL: http://localhost:8800
Come funziona: rilevamento a 3 livelli
asiai utilizza una cascata di tre livelli di rilevamento, dal più veloce al più approfondito:
Livello 1: Configurazione (più veloce, ~100ms)
Legge ~/.config/asiai/engines.json — motori scoperti nelle esecuzioni precedenti. Questo rileva motori su porte non standard (es. oMLX su 8800) senza dover riscansionare.
Livello 2: Scansione porte (~200ms)
Scansiona le porte predefinite più un range esteso:
| Porta | Motore |
|---|---|
| 11434 | Ollama |
| 1234 | LM Studio |
| 8080 | mlx-lm o llama.cpp |
| 8000-8009 | oMLX o vllm-mlx |
| 52415 | Exo |
Livello 3: Rilevamento processi (fallback)
Usa ps e lsof per trovare processi motore in ascolto su qualsiasi porta. Rileva motori in esecuzione su porte completamente inaspettate.
Persistenza automatica
Qualsiasi motore scoperto al Livello 2 o 3 viene automaticamente salvato nel file di configurazione (Livello 1) per un rilevamento più rapido la volta successiva. Le entry autodiscoverte vengono eliminate dopo 7 giorni di inattività.
Quando più motori condividono una porta (es. mlx-lm e llama.cpp su 8080), asiai usa il probing degli endpoint API per identificare il motore corretto.
URL espliciti
Usando --url, vengono scansionati solo gli URL specificati. Nessuna configurazione viene letta o scritta — utile per controlli una tantum.
asiai detect --url http://192.0.2.10:11434,http://localhost:8800
Vedi anche
- config — Gestire la configurazione persistente dei motori
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.
- 4d ago First seen · 74 lines · 38 tokens per session scan A 9c44f647825d
detect.it is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 38 tokens to every session and 667 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.
integrate-pipeline
Integrate a new document parsing pipeline into ParseBench: $ARGUMENTS.
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).
netllm-swarm
Configure multi-machine LAN mesh for netllm (mDNS, peers, gateway).
/opsx-explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.