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/daemongit clone --depth 1 https://github.com/druide67/asiaiWhat 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 | $0.00024 | $0.00521 |
| Opus 5 | $0.00012 | $0.00260 |
| Sonnet 5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
daemon 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 2d 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
Manage background services via macOS launchd LaunchAgents.
Services
| Service | Description | Model |
|---|---|---|
monitor |
Collects system + inference metrics at regular intervals | Periodic (StartInterval) |
web |
Runs the web dashboard as a persistent service | Long-running (KeepAlive) |
Usage
# Monitor daemon (default)
asiai daemon start # Start monitoring (every 60s)
asiai daemon start --interval 30 # Custom interval
asiai daemon start --alert-webhook URL # Enable webhook alerts
# Web dashboard service
asiai daemon start web # Start web on 127.0.0.1:8899
asiai daemon start web --port 9000 # Custom port
asiai daemon start web --host 0.0.0.0 # Expose on network (no auth!)
# Status (shows all services)
asiai daemon status
# Stop
asiai daemon stop # Stop monitor
asiai daemon stop web # Stop web
asiai daemon stop --all # Stop all services
# Logs
asiai daemon logs # Monitor logs
asiai daemon logs web # Web logs
asiai daemon logs web -n 100 # Last 100 lines
How it works
Each service installs a separate launchd LaunchAgent plist in ~/Library/LaunchAgents/:
- Monitor: runs
asiai monitor --quietat the configured interval (default: 60s). Data is stored in SQLite. If--alert-webhookis provided, alerts are POSTed on state transitions (memory pressure, thermal, engine down). - Web: runs
asiai web --no-openas a persistent process. Automatically restarts if it crashes (KeepAlive: true,ThrottleInterval: 10s).
Both services start automatically on login (RunAtLoad: true).
Security
- Services run at user level (no root required)
- Web dashboard binds to
127.0.0.1by default (localhost only) - A warning is displayed when using
--host 0.0.0.0— no authentication is configured - Logs are stored in
~/.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.
- 2d ago First seen · 58 lines · 24 tokens per session scan A 6f8a69b62019
daemon is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 521 once invoked, about $0.0001 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.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
scan
Scan AWS account for cost optimization.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.