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.frgit 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.fr)<a href="https://agentmods.dev/commands/druide67/asiai/detect.fr"><img src="https://agentmods.dev/badge/commands/druide67/asiai/detect.fr.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 | $0.00031 | $0.00617 |
| Opus 5 | $0.00015 | $0.00309 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
detect.fr 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
Auto-détection des moteurs d'inférence via une cascade à 3 niveaux.
Utilisation
asiai detect # Auto-détection (cascade 3 niveaux)
asiai detect --url http://host:port # Scanner des URL spécifiques uniquement
Sortie
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
Fonctionnement : détection à 3 niveaux
asiai utilise une cascade de trois niveaux de détection, du plus rapide au plus approfondi :
Niveau 1 : Config (le plus rapide, ~100ms)
Lit ~/.config/asiai/engines.json — les moteurs découverts lors des exécutions précédentes. Cela attrape les moteurs sur des ports non standard (ex. oMLX sur 8800) sans rescanner.
Niveau 2 : Scan de ports (~200ms)
Scanne les ports par défaut plus une plage étendue :
| Port | Moteur |
|---|---|
| 11434 | Ollama |
| 1234 | LM Studio |
| 8080 | mlx-lm ou llama.cpp |
| 8000-8009 | oMLX ou vllm-mlx |
| 52415 | Exo |
Niveau 3 : Détection de processus (secours)
Utilise ps et lsof pour trouver les processus moteurs écoutant sur n'importe quel port. Attrape les moteurs sur des ports totalement inattendus.
Persistance automatique
Tout moteur découvert au Niveau 2 ou 3 est automatiquement sauvegardé dans le fichier de config (Niveau 1) pour une détection plus rapide la prochaine fois. Les entrées auto-découvertes sont supprimées après 7 jours d'inactivité.
Quand plusieurs moteurs partagent un port (ex. mlx-lm et llama.cpp sur 8080), asiai utilise le sondage des endpoints API pour identifier le bon moteur.
URL explicites
Avec --url, seules les URL spécifiées sont scannées. Aucune config n'est lue ni écrite — utile pour des vérifications ponctuelles.
asiai detect --url http://192.0.2.10:11434,http://localhost:8800
Voir aussi
- config — Gérer la configuration persistante des moteurs
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 · 31 tokens per session scan A 0405fb95a95d
detect.fr is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 31 tokens to every session and 617 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.