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.esgit 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.es)<a href="https://agentmods.dev/commands/druide67/asiai/detect.es"><img src="https://agentmods.dev/badge/commands/druide67/asiai/detect.es.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 | $0.00035 | $0.00625 |
| Opus 5 | $0.00017 | $0.00313 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
detect.es 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
Detección automática de motores de inferencia usando una cascada de 3 capas.
Uso
asiai detect # Detección automática (cascada de 3 capas)
asiai detect --url http://host:port # Escanear solo URL(s) específicas
Salida
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
Cómo funciona: detección de 3 capas
asiai utiliza una cascada de tres capas de detección, de la más rápida a la más exhaustiva:
Capa 1: Configuración (más rápida, ~100ms)
Lee ~/.config/asiai/engines.json — motores descubiertos en ejecuciones anteriores. Esto detecta motores en puertos no estándar (ej. oMLX en 8800) sin necesidad de reescanear.
Capa 2: Escaneo de puertos (~200ms)
Escanea puertos por defecto más un rango extendido:
| Puerto | Motor |
|---|---|
| 11434 | Ollama |
| 1234 | LM Studio |
| 8080 | mlx-lm o llama.cpp |
| 8000-8009 | oMLX o vllm-mlx |
| 52415 | Exo |
Capa 3: Detección de procesos (respaldo)
Usa ps y lsof para encontrar procesos de motores escuchando en cualquier puerto. Detecta motores ejecutándose en puertos completamente inesperados.
Persistencia automática
Cualquier motor descubierto en la Capa 2 o 3 se guarda automáticamente en el archivo de configuración (Capa 1) para una detección más rápida la próxima vez. Las entradas autodescubiertas se eliminan después de 7 días de inactividad.
Cuando múltiples motores comparten un puerto (ej. mlx-lm y llama.cpp en 8080), asiai usa sondeo de endpoints API para identificar el motor correcto.
URLs explícitas
Al usar --url, solo se escanean las URLs especificadas. No se lee ni escribe configuración — útil para verificaciones puntuales.
asiai detect --url http://192.0.2.10:11434,http://localhost:8800
Ver también
- config — Gestionar configuración 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 · 35 tokens per session scan A 2ddd8438508c
detect.es is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 35 tokens to every session and 625 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.