How do I install the Nexus Brain skill?

Run npx skillmds@latest add javimosch/nexus-brain in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Nexus Brain skill do?

Skill: Nexus-Orchestrator (V1.1) It is listed under Coding & Dev Tools on SkillMD.

Is Nexus Brain safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Nexus Brain?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Nexus Brain free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Nexus Brain?

javimosch (@javimosch) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Nexus Brain by javimosch — Agent Skill

Name: Nexus Brain
Author: javimosch

File contents

Skill: Nexus-Orchestrator (V1.1)

Intelligent SRE Bridge for AI-driven system diagnosis and recovery.

🛡️ Security & Privacy Protocols

Log Redaction: The orchestrator includes a redaction engine that masks passwords, tokens, and emails in logs before sending them to the reasoning service.
Generic Binary Support: No longer relies on root-home paths. It searches for opencode in your system PATH or local user directory.
Privacy Notice: This skill sends redacted log snippets to your configured AI reasoning service (e.g., OpenCode/Codex). Ensure your AI provider complies with your data policy.

📋 Capabilities

Reasoning-First Recovery: Blocks blind restarts. Analyzes logs to differentiate between code bugs (alert user) and infra failures (restart service).
Log Contextualization: Automatically fetches and redacts relevant logs for the AI.

⚙️ Logic & Safeguards

Manual Oversight: Critical actions still require /approve if configured in OpenClaw.
Diagnostic Step: The agent is forced to perform an analysis via bridge.py before any recovery action.

🚀 Installation

pip install psutil
Ensure docker, pm2, and opencode are installed.

Frequently asked questions

Nexus Brain