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.ptgit 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.pt)<a href="https://agentmods.dev/commands/druide67/asiai/detect.pt"><img src="https://agentmods.dev/badge/commands/druide67/asiai/detect.pt.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 | $0.00037 | $0.00623 |
| Opus 5 | $0.00018 | $0.00311 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
detect.pt 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.
What it actually says
asiai detect
Auto-detecta motores de inferência usando uma cascata em 3 camadas.
Uso
asiai detect # Auto-detectar (cascata 3 camadas)
asiai detect --url http://host:port # Verificar apenas URL(s) específica(s)
Saída
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
Como funciona: detecção em 3 camadas
O asiai usa uma cascata de três camadas de detecção, da mais rápida à mais abrangente:
Camada 1: Config (mais rápida, ~100ms)
Lê ~/.config/asiai/engines.json — motores descobertos em execuções anteriores. Isso encontra motores em portas não padrão (ex: oMLX na 8800) sem precisar re-escanear.
Camada 2: Varredura de portas (~200ms)
Verifica portas padrão mais um range estendido:
| Porta | Motor |
|---|---|
| 11434 | Ollama |
| 1234 | LM Studio |
| 8080 | mlx-lm ou llama.cpp |
| 8000-8009 | oMLX ou vllm-mlx |
| 52415 | Exo |
Camada 3: Detecção de processos (fallback)
Usa ps e lsof para encontrar processos de motores ouvindo em qualquer porta. Encontra motores rodando em portas completamente inesperadas.
Auto-persistência
Qualquer motor descoberto nas Camadas 2 ou 3 é automaticamente salvo no arquivo de configuração (Camada 1) para detecção mais rápida na próxima vez. Entradas auto-descobertas são removidas após 7 dias de inatividade.
Quando múltiplos motores compartilham uma porta (ex: mlx-lm e llama.cpp na 8080), o asiai usa probing de endpoints de API para identificar o motor correto.
URLs explícitas
Ao usar --url, apenas as URLs especificadas são verificadas. Nenhuma configuração é lida ou escrita — útil para verificações pontuais.
asiai detect --url http://192.0.2.10:11434,http://localhost:8800
Veja também
- config — Gerencie configuração persistente de motores
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 · 37 tokens per session scan A 64f544078e4e
detect.pt is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 37 tokens to every session and 623 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.