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/daemon.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/daemon.fr)<a href="https://agentmods.dev/commands/druide67/asiai/daemon.fr"><img src="https://agentmods.dev/badge/commands/druide67/asiai/daemon.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
daemon.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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
asiai daemon
Gérer les services d'arrière-plan via les LaunchAgents macOS launchd.
Services
| Service | Description | Modèle |
|---|---|---|
monitor |
Collecte les métriques système + inférence à intervalles réguliers | Périodique (StartInterval) |
web |
Lance le dashboard web comme service persistant | Longue durée (KeepAlive) |
Utilisation
# Daemon de monitoring (par défaut)
asiai daemon start # Démarrer le monitoring (toutes les 60s)
asiai daemon start --interval 30 # Intervalle personnalisé
asiai daemon start --alert-webhook URL # Activer les alertes webhook
# Service dashboard web
asiai daemon start web # Démarrer le web sur 127.0.0.1:8899
asiai daemon start web --port 9000 # Port personnalisé
asiai daemon start web --host 0.0.0.0 # Exposer sur le réseau (pas d'auth !)
# Statut (affiche tous les services)
asiai daemon status
# Arrêt
asiai daemon stop # Arrêter le monitor
asiai daemon stop web # Arrêter le web
asiai daemon stop --all # Arrêter tous les services
# Logs
asiai daemon logs # Logs du monitor
asiai daemon logs web # Logs du web
asiai daemon logs web -n 100 # 100 dernières lignes
Fonctionnement
Chaque service installe un plist LaunchAgent launchd séparé dans ~/Library/LaunchAgents/ :
- Monitor : exécute
asiai monitor --quietà l'intervalle configuré (par défaut : 60s). Les données sont stockées dans SQLite. Si--alert-webhookest fourni, les alertes sont envoyées par POST lors des transitions d'état (pression mémoire, thermique, moteur hors ligne). - Web : exécute
asiai web --no-opencomme processus persistant. Redémarre automatiquement en cas de crash (KeepAlive: true,ThrottleInterval: 10s).
Les deux services démarrent automatiquement à la connexion (RunAtLoad: true).
Sécurité
- Les services s'exécutent au niveau utilisateur (pas de root requis)
- Le dashboard web se lie à
127.0.0.1par défaut (localhost uniquement) - Un avertissement est affiché lors de l'utilisation de
--host 0.0.0.0— aucune authentification n'est configurée - Les logs sont stockés dans
~/.local/share/asiai/
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 · 58 lines · 31 tokens per session scan A 366392f2b410
daemon.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.