nexus-brain
mrnsmh 作
DevOps & Cloud概要
Intelligent SRE Bridge for AI-driven system diagnosis and recovery.
説明
このスキルでできること
SRE orchestrator that diagnoses service failures using an AI reasoning engine before taking any recovery action. Redacts passwords, tokens, and emails from logs before sending them for analysis. Routes infrastructure failures to automatic restart and code bugs to user alerts.
Forces log analysis before any restart, preventing blind recoveries that hide bugs rather than fix them.
使いどころ
- Diagnosing why a Docker container keeps restarting
- Auto-recovering a crashed pm2 process after log review
- Distinguishing a code bug from an infra failure during an outage
- Reviewing redacted logs before they reach an external AI service
- Gating recovery actions behind a manual approval step
ワークフロー例
User asks: My API service is down, figure out what happened and recover if it's safe
- 1
Fetches recent logs for the affected service
- 2
Redacts sensitive fields (passwords, tokens, emails) from log content
- 3
Sends redacted logs to the configured AI reasoning service via bridge.py
- 4
Classifies the failure as infrastructure-related rather than a code bug
- 5
Restarts the service via docker or pm2, requesting /approve if configured
Service restarted after AI confirms infrastructure failure; a code bug would have triggered a user alert instead of a restart
要件
- opencode installed and accessible in system PATH or local user directory
- Docker
インストール
clawhub install mrnsmh/nexus-brainCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。