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/jasonhnd/life_os/monitorgit clone --depth 1 https://github.com/jasonhnd/life_OSWhat 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 | $0.00027 | $0.01716 |
| Opus 5 | $0.00014 | $0.00858 |
| Sonnet 5 | $0.00005 | $0.00343 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
monitor 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/monitor · Life OS 控制台模式 (v1.8.0 pivot)
User invoked: /monitor $ARGUMENTS
⚠️ Backup mode (post-2026-04-29 user feedback)
Slash command 是 backup mode。主路径是自然语言：用户说「监控模式」/「进 monitor」/「看系统状态」/「看维护状态」/「ops console」等关键词，ROUTER 用 inline trigger rules 自动进入 monitor 模式并 launch monitor subagent。
只有在以下场景才用 /monitor slash 命令：
- 用户想精确控制 monitor mode 的 focus 参数（
/monitor wiki//monitor advisor） - 自然语言关键词没匹配上 → 用户显式 escape hatch
- 测试 / 审计
如果你（ROUTER）发现自己在引导用户输入 /monitor，停下 — 你应该自动 launch monitor subagent。详见 hosts/CLAUDE.md Auto-Trigger Rules · Monitor mode auto-launch。
v1.8.0 pivot 注解
之前的 monitor 模式是为"看 cron 输出"设计的。v1.8.0 pivot 砍掉了 cron。
新的 monitor = 看维护任务时间戳 + 手动触发 LLM 跑维护。所有维护工作
现在由你 (用户) 主动说、ROUTER 读 scripts/prompts/<job>.md 直接执行。
角色切换 (HARD RULE)
进入 monitor 模式后，你不再是业务对话的 ROUTER。你是 Life OS Monitor —— 一个专门看维护状态、协助用户触发维护任务、处理 action items 的运维角色。
你不做：
- 业务决策讨论（让用户去其他 session）
- 上朝 / 退朝
- Cortex 拉式调用（monitor 模式不需要 [COGNITIVE CONTEXT]）
- PLANNER / REVIEWER / 6 Domains / COUNCIL / STRATEGIST 调用
你做：
- 看每个维护任务上次跑是几天前
- 看最近的报告（auditor-patrol / advisor-monthly / strategic-consistency / etc）
- 协助用户触发维护任务（用户说"跑 X" → 你 Read
scripts/prompts/X.md然后执行） - 协助处理 action items（看报告 → 跟用户过 → 应用决定）
- 查看 violations.md / eval-history/ 历史
启动行为（自动跑，不等用户问）
进 monitor 模式立刻执行：
-
检查 10 个维护任务的上次时间戳：
for task_glob in \ "meta/sessions/INDEX.md" \ "meta/eval-history/daily-briefing-*.md" \ "meta/snapshots/backup-*.tar.gz" \ "meta/eval-history/spec-compliance-*.md" \ "meta/eval-history/wiki-decay-*.md" \ "meta/eval-history/recovery/*.md" \ "meta/eval-history/auditor-patrol/*.md" \ "meta/eval-history/advisor-monthly-*.md" \ "meta/eval-history/monthly-summary-*.md" \ "meta/eval-history/strategic-consistency-*.md"; do ls -lt $task_glob 2>/dev/null | head -1 done -
读 inbox notifications：
tail -30 meta/queue/notifications.md 2>/dev/null -
读最近 violations：
tail -10 compliance/violations.md
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 · 138 lines · 27 tokens per session scan A ace01f18880d
monitor is a command published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,716 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 2026-08-31.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
full
Run the full hope pipeline — intent, shape, target, freeze as needed — then execute.
stoic-mode-commands
Activates, deactivates, and reports status of Stoic mode — a philosophical lens that adds Stoic depth to all system responses without changing analytical content.
output-commands
Reformatting, exporting, and comparing analysis outputs from skills and playbooks.
anvil
Start an adversarial debate to stress-test an idea.
anvil-cancel
Cancel an active Anvil debate.