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 skills add nanxiaoyao/network-huawei-skills --skill health-checkgit clone --depth 1 https://github.com/nanxiaoyao/network-huawei-skillsWrote 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/skills/nanxiaoyao/network-huawei-skills/health-check)<a href="https://agentmods.dev/skills/nanxiaoyao/network-huawei-skills/health-check"><img src="https://agentmods.dev/badge/skills/nanxiaoyao/network-huawei-skills/health-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nanxiaoyao/network-huawei-skills/health-check"><img src="https://agentmods.dev/badge/skills/nanxiaoyao/network-huawei-skills/health-check.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.01468 |
| Opus 5 | $0.00042 | $0.00734 |
| Sonnet 5 | $0.00017 | $0.00294 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
health-check 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 12d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
华为设备综合巡检技能 (health-check)
本技能对华为 VRP 设备执行一键综合体检，覆盖系统层、硬件层、接口层、路由层、安全层、日志层六大维度，自动采集 display 命令输出、分析关键指标、生成结构化巡检报告。
适用：路由器（AR/NE 系列）、交换机（S/CE 系列）、防火墙（USG 系列）。
触发场景
用户描述以下任一需求时加载此技能：
- "帮我巡检一下序号为 X 的设备"
- "对 LL-xcsyy-FW 做个体检"
- "看下这台设备健康状况"
- "device health check / inspection"
- "生成设备巡检报告"
- "查一下 CPU/内存/接口/日志"（综合查询时）
不适用： 单一协议排错（OSPF 邻居不通 → 用 ospf-config）、配置变更（→ 对应配置技能）。
工作流程
Step 1：确认目标设备
需要用户提供：
- 设备序号（对应 user.txt）或设备名/IP
- 巡检深度：快速（5 分钟）/ 标准（10 分钟）/ 深度（含日志分析）
- 输出形式：终端摘要 / Markdown 报告 / 两者
Step 2：登录设备
使用封装脚本 bin/hwssh.sh <序号> '<命令>'，禁止在命令行明文传密。
Step 3：按维度采集
执行 references/inspection-commands.md 中对应深度的命令集，逐条采集输出。
Step 4：分析与判定
对照 references/health-criteria.md 的健康阈值，给每项打 ✓ / ⚠ / ✗。
Step 5：生成报告
按 templates/report-template.md 输出 Markdown 报告，关键项前置告警。
巡检维度（六大类）
1. 系统层
- 设备型号、VRP 版本、运行时长、Patch 状态
- 主控/备控状态、主备一致性
- 时间同步（NTP）
2. 硬件层
- CPU 利用率（5s/1min/5min）
- 内存利用率
- 风扇、电源、温度
- 单板状态、光模块状态
3. 接口层
- 物理 up/down 状态
- 速率/双工/带宽利用率
- CRC/Input Error/Drop 计数
- 光模块收发光功率（阈值告警）
4. 路由层
- 路由表规模（IPv4/IPv6）
- 各协议邻居数（OSPF/BGP/ISIS）
- 默认路由是否存在
5. 安全层（防火墙专属）
- 会话表大小、新建速率
- 安全策略命中统计
- 攻击防范日志
6. 日志层
- 最近 24h ERROR/CRIT 日志数
- 异常事件（接口频繁 up/down、CPU 抖动）
健康判定原则
| 等级 | 标记 | 含义 | 触发条件示例 |
|---|---|---|---|
| 健康 | ✓ | 全部正常 | CPU<60%, 内存<70%, 无错包, 无关键日志 |
| 警告 | ⚠ | 需关注 | CPU 60-80%, 接口少量 CRC, 光功率边缘 |
| 异常 | ✗ | 立即处理 | CPU>80%, 接口 down, 风扇故障, 大量 CRIT |
快速入口
| 需求 | 入口 |
|---|---|
| 一键巡检（推荐） | scripts/full_inspection.sh <序号> [--depth quick|standard|deep] |
| 命令清单参考 | references/inspection-commands.md |
| 健康阈值定义 | references/health-criteria.md |
| 报告模板 | templates/report-template.md |
输出示例（摘要）
=== LL-xcsyy-FW 巡检报告 ===
时间: 2026-05-21 21:50:00
型号: USG6307E VRP: V600R007C20SPC600 运行: 43w6d
[✓] 系统层 版本正常, 主备一致, NTP 同步
[✓] 硬件层 CPU 12%, 内存 45%, 温度 38°C, 风扇正常
[⚠] 接口层 GE0/0/3 CRC 错包递增 (近1h +234)
[✓] 路由层 OSPF 邻居 3/3 Full, BGP 邻居 2/2 Established
[✓] 安全层 会话 12k/500k, 无攻击事件
[✓] 日志层 近 24h 无 CRIT 日志
总体: ⚠ 警告 (1 项)
建议: 检查 GE0/0/3 物理链路 / 光模块
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 147 lines · 83 tokens per session scan A 29d3a250ccc5
health-check is a skill published in the GitHub repository nanxiaoyao/network-huawei-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,468 once invoked, about $0.0004 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 skills, from other repositories
percepxion-oob
Manage Lantronix out-of-band (OOB) infrastructure via Percepxion central management platform: device inventory, serial port inspection via SLC CLI, firmware compliance, config management, security auditing, and closed-loop incident remediation. Use during outages, maintenance windows, compliance cycles, and…
meraki-security-appliance
Cisco Meraki MX security appliance (read-only) — L3/L7 firewall rules, content filtering, IDS/IPS and AMP settings, site-to-site VPN, traffic shaping via Cisco's official Meraki MCP. Use when auditing Meraki firewall rules, reviewing content filtering, or inspecting MX VPN configuration.
unifi-wifi
Use when UniFi Wi-Fi is slow, unstable, or being tuned: "my wifi is slow but speedtest on the router is fast", "great signal, terrible speed", "should I use 80MHz or 40MHz", "channel planning", "co-channel interference", "DFS channels", "my APs keep picking the same channel", "audit my SSIDs", "hidden SSID", or…
unifi-connect
Use when connecting an agent to a UniFi gateway (UDM Pro, UDM SE, Cloud Gateway) for the first time, or when API calls to one are failing: empty response bodies, curl returning HTTP 000, 401 on a key that works elsewhere, "how do I get a UniFi API key", "SSH is closed on my UDM", "connect to UniFi", "talk to my UniFi…
unifi-clients
Use when operating on UniFi clients, devices, switch ports, or DHCP: "block a device", "kick a client off wifi", "restart an access point", "power cycle a PoE port", "move a device to a different VLAN", "my device is on the wrong subnet after I changed the port", "set a DHCP reservation", "change DHCP DNS servers"…
unifi-context-map
Use when an agent keeps guessing wrong about a UniFi network, when starting recurring agent work against a gateway, or when asked to "map my network", "document my UniFi setup", "build a network inventory", "what's on my network", "why does the agent keep using the wrong AP", or "audit my reservations against…