Agentic Os

This turns Claude Code into a persistent multi-agent operating system instead of treating it as a disposable chat. You get a kernel in CLAUDE.md that routes tasks to specialist agents (a @dev for code, a @writer for docs, a @researcher for analysis), slash commands for recurring workflows like /daily-sync or /outreach, and file-based memory in a data/ directory so state survives across sessions. No external databases, just markdown and JSON. It's overkill for one-off scripts but makes sense if you're building something like a personal automation system or a long-running project where you need agents to hand off work to each other and remember what happened yesterday. The architecture mirrors production agentic setups with clean separation between routing logic, agent definitions, and persistent state.

skills.sh installs: 5.5K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill agentic-os --agent claude-code

Installs into .claude/skills of the current project.

Files

Agentic OS

Treat Claude Code as a persistent runtime / operating system rather than a chat session. This skill codifies the architecture used by production agentic setups: a kernel config that routes tasks to specialist agents, persistent file-based memory, scheduled automation, and a JSON/markdown data layer.

When to Activate

Building a multi-agent workflow inside Claude Code
Setting up persistent Claude Code automation that survives session restarts
Creating a "personal OS" or "agentic OS" for recurring tasks
User says "agentic OS", "personal OS", "multi-agent", "agent coordinator", "persistent agent"
Structuring long-running projects where context must survive across sessions

Architecture Overview

The Agentic OS has four layers. Each layer is a directory in your project root.

project-root/
├── CLAUDE.md          # Kernel: identity, routing rules, agent registry
├── agents/            # Specialist agent definitions (markdown prompts)
├── .claude/commands/  # Slash commands: user-facing CLI
├── scripts/           # Daemon scripts: scheduled or event-driven tasks
└── data/              # State: JSON/markdown filesystem, no external DB

SKILL.md on GitHub