# Agent Bom Monitor

> Agent Bom Monitor is an Agent Skill for devops & security published in the LeoYeAI/openclaw-master-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Monitor agent fleet, track trust scores, and manage lifecycle states. Use when: "fleet", "watch agents", "runtime status", "trust scores", "fleet sync", "agent lifecycle", "serve dashboard".

- Skill name: `agent-bom-monitor`
- Category: [DevOps & Security](https://www.openparable.com/skill/devops-security/1)
- Source: https://github.com/LeoYeAI/openclaw-master-skills/blob/HEAD/skills/agent-bom/monitor/SKILL.md
- Repository: LeoYeAI/openclaw-master-skills (2,087 GitHub stars when collected)

## SKILL.md

# agent-bom-monitor — Agent Fleet Monitor

Monitor agent fleet health, track trust scores, and manage agent lifecycle
states across your AI infrastructure. Start a local dashboard server for
continuous monitoring.

## Install

```bash
pipx install agent-bom
agent-bom fleet sync         # sync fleet state with latest scan
agent-bom fleet list         # list all agents and trust scores
agent-bom serve              # start local monitoring dashboard
```

## When to Use

- "fleet" / "agent fleet"
- "watch agents" / "monitor agents"
- "runtime status"
- "trust scores"
- "fleet sync"
- "agent lifecycle"
- "serve dashboard" / "start dashboard"

## Commands

```bash
# Sync fleet state with latest scan
agent-bom fleet sync

# List all agents with trust scores
agent-bom fleet list

# Start local monitoring dashboard
agent-bom serve
```

## Examples

```
# Sync fleet
fleet_sync()

# List agents and trust scores
fleet_list()

# Start dashboard server
serve()
```

**Example fleet list output:**
```
Agent Fleet — 7 agents tracked
  filesystem   trust: 92  status: healthy   last-scan: 2m ago
  brave-search trust: 88  status: healthy   last-scan: 2m ago
  github       trust: 95  status: healthy   last-scan: 2m ago
  slack        trust: 71  status: warning   last-scan: 2m ago  [2 CVEs]
  postgres     trust: 84  status: healthy   last-scan: 2m ago
  linear       trust: 90  status: healthy   last-scan: 2m ago
  notion       trust: 67  status: at-risk   last-scan: 2m ago  [CRITICAL]
```

## Guardrails

- Fleet monitoring is read-only — no agents are modified.
- The dashboard server runs on localhost only — no external exposure.
- Confirm with the user before starting `agent-bom serve` — it binds a local port.
- Trust scores are derived from local scan data; they do not contact external services.

---

Source: https://www.openparable.com/skill/devops-security/agent-bom-monitor (OpenParable). Cite the canonical URL above.