Skip to content
Get packs

Agentic OS Builder

Guides building a persistent multi-agent setup inside Claude Code using markdown files and scheduled jobs

Source Download skill
Repository
affaan-m/ECC
Stars
295,127
Licence
MIT
Files
1 file

What it does

This skill teaches Claude Code to act as a long-running assistant system rather than a single chat. It describes a folder layout with a central instruction file that routes requests to specialist agent prompts (such as developer, writer, researcher, ops), slash commands for repeatable workflows like a daily briefing, and a memory store made of plain JSON and Markdown files instead of a database. It also shows how to schedule these commands with macOS LaunchAgents, Linux systemd timers, or pm2 so they run automatically.

Great for

  • Developers who want Claude Code to keep project context and routines across sessions
  • Solo founders or freelancers who want a recurring daily briefing and a simple file-based record of decisions
  • People who want a worked example of organizing multiple Claude Code agent roles

Skip it if

  • Users who expect a ready-made app or installer; this is a set of instructions and templates that must be adapted by hand
  • Anyone who would schedule unattended runs of Claude with broad file or tool access without reviewing the prompts, since automated runs can act without oversight
  • Teams needing shared, concurrent, or access-controlled data; the file-based store has no database safeguards

Try asking

  • “Set up an agentic OS structure with a CLAUDE.md kernel and specialist agents for my project”
  • “Create a /daily-sync command that summarizes git status, open PRs, and blockers each morning”
  • “Schedule my daily sync to run at 8am on macOS using a LaunchAgent”
  • “Add a decision log and reflection notes so my assistant improves its routing over time”
Step-by-step guide: how to use Agentic OS BuilderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    agentic-os.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip agentic-os.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip agentic-os.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review every agent prompt and slash command before enabling scheduled runs, and keep the tool access lists narrow
  • Keep data/ out of Git or exclude secrets, since logs and contacts can contain sensitive information
  • Start with one or two agents and one command, then expand once routing works reliably

What's inside

  • SKILL.md

Redistributed unmodified from affaan-m/ECC under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.