守护协议
aegis-protocol
by ankechenlab-node
Self-healing stability monitor for AI agents - 5 core checks + 15 extended checks, auto-recovery, health scoring
安装
claude skill add --url https://github.com/openclaw/skills文档
Aegis Protocol 🛡️
Self-Healing Stability Monitor for AI Agents
Version: 0.12.6
Author: Dream
License: MIT
Features
- 20-Dimension Monitoring: System, services, AI agent, security, maintenance
- Auto Recovery: Terminate stuck sessions, restart services, compact context
- Health Scoring: Quantified health score (0-100)
- Healing Memory: Record and learn from recovery strategies
- Result Caching: 5-minute TTL for reduced system calls
Commands
aegis-protocol init
Initialize configuration file
aegis-protocol status
Show system health summary
aegis-protocol check
Run full health check
aegis-protocol heal
Execute automatic recovery
aegis-protocol config
View current configuration
Usage Examples
# Initialize
python3 aegis-protocol.py init
# Check health
python3 aegis-protocol.py check
# Auto recover
python3 aegis-protocol.py heal
# View config
python3 aegis-protocol.py config
Configuration
File: ~/.openclaw/workspace/.watchdog-config.json
{
"thresholds": {
"sessionTimeoutMinutes": 60,
"pm2RestartAlert": 50,
"diskUsagePercent": 90,
"memoryUsagePercent": 95,
"contextUsagePercent": 80
}
}
Monitoring Dimensions
| Category | Checks |
|---|---|
| System | CPU, Memory, Disk, Zombies, FD, Connections |
| Services | PM2, Nginx, Docker, Cron |
| AI Agent | Sessions, Context, Tasks, Loops |
| Security | SSL, Updates, Git |
| Maintenance | Backup, Cleanup, Network |
Health Score
| Score | Status |
|---|---|
| 90-100 | Excellent |
| 70-89 | Good |
| 50-69 | Warning |
| 0-49 | Critical |
Testing
# Unit tests
python3 -m pytest tests/ -v
# Coverage
python3 -m pytest tests/ --cov=aegis_protocol -v
Coverage: 82%
Tests: 20+ passing
Quality Metrics
| Metric | Value |
|---|---|
| Type hints | >90% |
| Test coverage | 82% |
| Documentation | 100% |
| Bugs | 0 |
Version History
v0.7.0 (2026-04-05)
- Result caching with 5-minute TTL
- Type hints >90% coverage
- Exception classification (4 types)
- 20-dimension monitoring
- Health scoring system
Aegis Protocol - The Never-Sleeping Guardian 🌀
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。