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.kogit 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.ko)<a href="https://agentmods.dev/commands/druide67/asiai/daemon.ko"><img src="https://agentmods.dev/badge/commands/druide67/asiai/daemon.ko.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 | $0.00611 |
| Opus 5 | $0.00018 | $0.00305 |
| Sonnet 5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
daemon.ko 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 daemon
macOS launchd LaunchAgent을 통한 백그라운드 서비스를 관리합니다.
서비스
| 서비스 | 설명 | 모델 |
|---|---|---|
monitor |
정기적으로 시스템 + 추론 메트릭 수집 | 주기적 (StartInterval) |
web |
웹 대시보드를 영구 서비스로 실행 | 상주 (KeepAlive) |
사용법
# 모니터링 데몬 (기본)
asiai daemon start # 모니터링 시작 (60초마다)
asiai daemon start --interval 30 # 커스텀 간격
asiai daemon start --alert-webhook URL # 웹훅 알림 활성화
# 웹 대시보드 서비스
asiai daemon start web # 127.0.0.1:8899에서 웹 시작
asiai daemon start web --port 9000 # 커스텀 포트
asiai daemon start web --host 0.0.0.0 # 네트워크에 공개 (인증 없음!)
# 상태 (모든 서비스 표시)
asiai daemon status
# 중지
asiai daemon stop # monitor 중지
asiai daemon stop web # web 중지
asiai daemon stop --all # 모든 서비스 중지
# 로그
asiai daemon logs # monitor 로그
asiai daemon logs web # web 로그
asiai daemon logs web -n 100 # 마지막 100줄
작동 방식
각 서비스는 ~/Library/LaunchAgents/에 별도의 launchd LaunchAgent plist를 설치합니다:
- Monitor: 설정된 간격(기본: 60초)으로
asiai monitor --quiet를 실행. 데이터는 SQLite에 저장.--alert-webhook가 제공되면 상태 전환(메모리 프레셔, 서멀, 엔진 다운) 시 알림을 POST. - Web:
asiai web --no-open을 영구 프로세스로 실행. 크래시 시 자동 재시작 (KeepAlive: true,ThrottleInterval: 10s).
두 서비스 모두 로그인 시 자동 시작 (RunAtLoad: true).
보안
- 서비스는 사용자 수준에서 실행 (root 불필요)
- 웹 대시보드는 기본적으로
127.0.0.1에 바인딩 (로컬호스트만) --host 0.0.0.0사용 시 경고 표시 — 인증이 설정되지 않음- 로그는
~/.local/share/asiai/에 저장
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 · 37 tokens per session scan A 3556041effc3
daemon.ko 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 611 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.