Agent skill

Server Patrol

by openocta in openocta/openocta_skills

Linux 与网络设备只读健康巡检;直接运行 scripts/patrol.sh,配置由平台侧信道注入,Agent 不读取环境变量

MITAuto-check passedDatabases

Install Server Patrol

skills CLI
$ npx skills add openocta/openocta_skills --skill server-patrol -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openocta/openocta_skills server-patrol --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openocta/openocta_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'服务器巡检' .claude/skills/server-patrol && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
server-patrol
GitHub stars
166
Token cost
~522 tokens
SKILL.md length
152 words
Files
5 (incl. scripts)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Linux 与网络设备只读健康巡检;直接运行 scripts/patrol.sh,配置由平台侧信道注入,Agent 不读取环境变量

  • Works in 4 steps: 直接运行脚本,不要预先检查环境变量 → 进入 Skill 目录后执行(路径以实际挂载为准) → 若 --list 为空或脚本报「未配置目标」,告知用户:需在控制台 Config… → …
  • Databases work in your project
  • SKILL.md covers 何时使用, 用户目标, Agent 执行规则(必读) and 分析思路, plus 4 more sections
  • Runs Shell scripts from its folder

What it does

Server Patrol is an agent skill from openocta/openocta_skills. Linux 与网络设备只读健康巡检;直接运行 scripts/patrol.sh,配置由平台侧信道注入,Agent 不读取环境变量

Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `README.md` and `scripts/patrol.sh`).

It sits in Databases. It works with Linux. The repository describes itself as: 本仓库用于汇集第三方贡献的 OpenOcta 技能(Skill)资源,便于分享、版本管理与分发。 The licence is MIT.

When your agent uses it

  • Databases work in your project

Example prompts

  • “/server-patrol”

Requirements

  • A Bash shell
  • Docker

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 直接运行脚本,不要预先检查环境变量
  2. 进入 Skill 目录后执行(路径以实际挂载为准)
  3. 若 --list 为空或脚本报「未配置目标」,告知用户:需在控制台 Config Vault / Skill config.env 中配置巡检目标,不要自行构造 export PATROL_*。
  4. 根据脚本 stdout / reports/ 下报告解读结果,按下方「处理思路」给出建议。

What it can do on your machine

Read from SKILL.md and the folder at commit 6ac4479. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Server Patrol loads about 522 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 152 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~522

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from openocta/openocta_skills at commit 6ac4479, republished under its MIT licence (© openocta). 152 words, ~522 tokens.

Download SKILL.mdSave it as .claude/skills/server-patrol/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
server-patrol
description
Linux 与网络设备只读健康巡检;直接运行 scripts/patrol.sh,配置由平台侧信道注入,Agent 不读取环境变量

基础设施巡检 (server-patrol)

面向 Linux 服务器 与 网络设备(路由器、交换机、防火墙等)的只读巡检 Skill。

对象检查项
Linuxuptime、负载、CPU、内存、磁盘、systemd 服务、Docker
网络设备Ping 连通、TCP 端口、SNMP(可选)、SSH 只读命令(Cisco / 华为 / H3C)

何时使用

  • 「服务器巡检」「网络设备巡检」「路由器状态」「交换机健康」「定时巡检」
  • 不适用:改配置、重启设备、下发 ACL 等写操作

用户目标

  • 一份报告汇总 Linux 与网络设备的 OK / WARN / CRIT
  • 明确 unreachable、高 CPU、端口不通等风险及处理建议

Agent 执行规则(必读)

巡检目标与凭证由 OpenOcta 平台在运行 patrol.sh 前注入进程环境(来自 Skill 包内 config.env + Config Vault),不对大模型暴露。

  1. 直接运行脚本,不要预先检查环境变量:
    • 禁止 env、printenv、echo $PATROL_*、grep PATROL
    • 禁止 cat/read_file 读取 config.env
    • 禁止在对话中复述密码、密钥、community 等敏感值
  2. 进入 Skill 目录后执行(路径以实际挂载为准):
bash
chmod +x scripts/patrol.sh
./scripts/patrol.sh --list          # 查看已配置目标(无目标时再报错)
./scripts/patrol.sh --all           # 批量 Linux + 网络
./scripts/patrol.sh --servers       # 仅 Linux
./scripts/patrol.sh --network       # 仅网络设备
./scripts/patrol.sh --network --tag core
./scripts/patrol.sh --all --format json
  1. 若 --list 为空或脚本报「未配置目标」,告知用户:需在控制台 Config Vault / Skill config.env 中配置巡检目标,不要自行构造 export PATROL_*。
  2. 根据脚本 stdout / reports/ 下报告解读结果,按下方「处理思路」给出建议。

分析思路

  1. 运行 ./scripts/patrol.sh --list 或 ./scripts/patrol.sh --all
  2. Linux:磁盘/内存/负载超阈值 → WARN/CRIT(逻辑见脚本)
  3. 网络:Ping 丢包、RTT、端口、SSH 采集 CPU/内存 → WARN/CRIT
  4. 报告分「Linux 服务器」「网络设备」两节呈现

处理思路

发现建议
Ping CRIT查链路、ARP、ACL、设备电源
端口 closed确认服务监听、防火墙、安全组
Cisco/华为 CPU 高查会话数、路由震荡、广播风暴
接口 down查物理链路、光模块、对端端口
Linux 磁盘/内存 CRIT同服务器巡检常规处理
SSH/SNMP 失败查凭证、SNMP ACL、管理 VLAN(勿向用户索要明文密码)

输出要求

  • 以脚本输出为准,分 Linux / 网络两节
  • CRIT/WARN 项附简短 remediation
  • SSH/SNMP 失败单独说明,不阻塞其他目标

注意事项

  • 只读:禁止配置写入、reload、reboot
  • 网络设备 SSH 命令集因厂商/版本而异
  • 运维配置格式(PATROL_* 列表、Config Vault 引用)见 README.md 与 config.env,Agent 无需阅读

能力依赖

  • bash、ping、ssh;密码认证时需 sshpass(由运维在 Runtime 镜像中安装)
  • 可选:python3、nc、snmpwalk

© openocta, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts) in 服务器巡检 of openocta/openocta_skills.

  • SKILL.md
  • README.md
  • config.env
  • scripts/patrol.sh
  • server-patrol.zip

Open the folder on GitHubat commit 6ac4479

Compare with similar skills

Server Patrol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Server Patrol compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Server Patrol this skillopenocta/openocta_skills166—~522Automated safety check: PassMIT
Remote System Maintenanceaiskillstore/marketplace4301 repos~791Automated safety check: PassNone
DeepChat Data Import HelperThinkInAIXYZ/deepchat6.4k—~738Automated safety check: PassApache-2.0
Submit Product Directories V1 Batchflaqai/backlink_skills752—~1.7kAutomated safety check: PassMIT
Osquery Query Helpertsale/awesome-dfir-skills324—~1.5kAutomated safety check: PassApache-2.0
Flox Environmentsaffaan-m/ECC275k2 repos~3.5kAutomated safety check: NotesMIT

Similar skills

  • Remote System Maintenance

    aiskillstore/marketplace

    This skill should be used when performing maintenance or diagnostics on remote Linux systems.

    430 GitHub starsUsed in 1 repo~791 tokens
    DatabasesAuto-check passed
  • DeepChat Data Import Helper

    ThinkInAIXYZ/deepchat

    Guides building a third-party importer for DeepChat's local SQLite data, covering schema, encryption and safe read-only access patterns.

    6.4k GitHub stars~738 tokensUpdated today
    DatabasesAuto-check passed
  • SPD V1 Batch. An agent skill from flaqai/backlink_skills.

    752 GitHub stars~1.7k tokensUpdated 14 days ago
    DatabasesAuto-check passed
  • Osquery Query Helper

    tsale/awesome-dfir-skills

    Help users write, validate, and troubleshoot osquery SQL queries using provided osquery table schemas as the authoritative source.

    324 GitHub stars~1.5k tokensUpdated 4 mo ago
    DatabasesAuto-check passed
  • Flox Environments

    affaan-m/ECC

    Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager.

    275k GitHub starsUsed in 2 repos~3.5k tokens
    DatabasesAuto-check: notes
  • Flox Environments

    affaan-m/ECC

    Floxで再現可能なクロスプラットフォーム開発環境を作成します — Nixに基づく宣言的な環境マネージャー。次の場合は必ずこのスキルを使用してください: システムレベルの依存関係(コンパイラー、データベース、openssl・libvips・BLAS・LAPACKなどのネイティブライブラリー)を持つプロジェクトを設定する場合…

    275k GitHub stars~2.8k tokensUpdated 3 days ago
    DatabasesAuto-check passed

More from openocta/openocta_skills

All 8 skills in this repo
  • Mysql Full Inspection Skill

    openocta/openocta_skills

    对远程多实例MySQL数据库执行全方位深度巡检,覆盖基础健康、连接负载、性能慢查询、索引冗余、主从复制、容量空间、账号安全、配置风险八大维度,全自动完成巡检扫描、风险识别、问题定级、优化建议、报告归档与飞书推送,适用于生产/测试所有运行中MySQL实例常态化合规巡检。适用场景:用户要求进行 MySQL 全链路健康检查、MySQL 综合巡检、MySQL 风险扫描、MySQL 性能审计、MySQL…

    166 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed
  • Wechat Gzh Analyzer

    openocta/openocta_skills

    分析微信公众号后台数据,包括文章阅读量、评论、点赞等统计。当用户需要分析微信公众号数据、导出公众号文章统计报表时调用此技能。

    166 GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Mysql Deadlock Analyzer

    openocta/openocta_skills

    Full-chain MySQL deadlock analysis. An agent skill from openocta/openocta_skills.

    166 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Mysql Replication Lag Resolver

    openocta/openocta_skills

    Replication lag root cause analysis with automated resolution workflow.

    166 GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Mysql Slow Query Diagnose

    openocta/openocta_skills

    Slow query diagnosis with root cause analysis and index optimization recommendations.

    166 GitHub stars~2.7k tokensUpdated 3 mo ago
    Auto-check passed
  • Tidb Cluster Inspector

    openocta/openocta_skills

    Comprehensive TiDB cluster inspection. An agent skill from openocta/openocta_skills.

    166 GitHub stars~2.9k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about Server Patrol

What does Server Patrol do?

Linux 与网络设备只读健康巡检;直接运行 scripts/patrol.sh,配置由平台侧信道注入,Agent 不读取环境变量. Server Patrol is an agent skill from openocta/openocta_skills.

When should I use Server Patrol?

Server Patrol fits situations like: databases work in your project.

How do I install Server Patrol in Claude Code?

Run `npx skills add openocta/openocta_skills --skill server-patrol -a claude-code`. Or copy the skill folder (服务器巡检 in openocta/openocta_skills) into .claude/skills/server-patrol in your project. Claude Code loads it when a task matches its description.

How do I install Server Patrol in Codex?

Run `npx skills add openocta/openocta_skills --skill server-patrol -a codex`. Or copy the skill folder (服务器巡检 in openocta/openocta_skills) into .agents/skills/server-patrol in your project. Codex loads it when a task matches its description.

Can I use Server Patrol in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openocta/openocta_skills --skill server-patrol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/server-patrol, .gemini/skills/server-patrol, .github/skills/server-patrol and .opencode/skills/server-patrol in your project.

What does Server Patrol need to run?

Going by SKILL.md and its folder, Server Patrol needs a shell for the scripts in its folder. Our summary lists: A Bash shell; Docker.

Does Server Patrol access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Server Patrol safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Server Patrol use?

Server Patrol is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Server Patrol use?

About 522 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Server Patrol?

Skills that share tags, products or a category with Server Patrol: Remote System Maintenance (aiskillstore/marketplace, 430 stars), DeepChat Data Import Helper (ThinkInAIXYZ/deepchat, 6.4k stars), Submit Product Directories V1 Batch (flaqai/backlink_skills, 752 stars) and Osquery Query Helper (tsale/awesome-dfir-skills, 324 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Server Patrol?

openocta (a GitHub user) maintains it in openocta/openocta_skills, which has 166 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on June 22, 2026.

Source: openocta/openocta_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.