内存监控
MemWatch
by BytesAgain
Monitor RAM usage in real time and alert on high memory consumption thresholds. Use when tracking memory, identifying RAM hogs, setting alert thresholds.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/bytesagain/memwatch文档
MemWatch
Memory monitor: view usage, find top consumers, watch trends, inspect per-process memory, check swap, and alert on thresholds.
Commands
| Command | Description |
|---|---|
memwatch status | Current memory usage with visual bar and breakdown |
memwatch top [n] | Top N memory-consuming processes (default: 10) |
memwatch watch | Snapshot memory every 2s for 10 iterations |
memwatch process <pid> | Memory details for a specific PID (VmRSS, VmSize, PSS, etc.) |
memwatch swap | Swap usage details with top swap consumers |
memwatch alert <threshold> | Check if memory usage exceeds threshold % |
memwatch detailed | Full /proc/meminfo dump |
memwatch compare | Compare memory now vs 30 seconds later (delta) |
memwatch version | Show version |
Examples
memwatch status # → usage %, visual bar, total/avail/cached
memwatch top 5 # → top 5 RAM consumers (PID, %MEM, RSS, CMD)
memwatch watch # → 10 snapshots, 2s apart
memwatch process 1234 # → VmSize, VmRSS, VmSwap, PSS, threads
memwatch swap # → swap devices, usage, top swap consumers
memwatch alert 80 # → 🚨 if usage > 80%, ✅ if under
memwatch detailed # → full /proc/meminfo
memwatch compare # → two snapshots 30s apart with delta
Requirements
free,ps(standard)/proc/meminfo,/proc/[pid]/status(Linux)
相关 Skills
安全专家
by alirezarezvani
覆盖威胁建模、漏洞评估、安全架构设计、代码审计与渗透测试，内置 STRIDE、OWASP、加密模式和安全扫描流程，适合系统设计评审与上线前安全排查。
✎ 安全专家把威胁建模、漏洞分析到渗透测试串成一套流程，内置 STRIDE 与 OWASP 指南，做安全设计和排查更省心。
安全运营
by alirezarezvani
覆盖应用安全、漏洞管理与合规审计，支持代码/依赖扫描、CVE 评估、Secrets 检测和安全自动化，适合做安全基线落地、漏洞响应、审计检查与安全开发治理。
✎ 应用安全、漏洞管理和合规检查一套打通，还能自动化扫描与响应，帮团队更早发现并收敛风险。
安全审计
by alirezarezvani
安装前审计 Claude Code Skill 的代码执行、Prompt 注入和依赖供应链风险，支持本地目录或 Git 仓库扫描，输出 PASS/WARN/FAIL 结论及修复建议
✎ 把代码审查、漏洞扫描和合规检查串成一条线，帮团队更早发现风险，做安全治理更省心。
相关 MCP 服务
by Sentry
搜索和分析 Sentry 错误报告，辅助调试。
✎ 把零散的 Sentry 错误报告变成可检索线索，帮你在海量报错里更快定位线上故障，排障调试明显省时。
by sinewaveai
为 AI agents 提供安全层：拦截 prompt injection、识别伪造 packages，并扫描漏洞风险。
✎ 给 AI Agent 补上关键安全层，能拦截 prompt 注入、识别伪造包并扫描漏洞风险，把防护前置更省心。
by pantheon-security
强化安全性的 NotebookLM MCP，集成 post-quantum encryption，提升数据防护能力。