Agentic OS
Turn Claude Code into a persistent multi-agent OS: kernel config, specialist agents, slash commands, file-based memory, scheduled automation.
- What
- Turn Claude Code into a persistent multi-agent OS: kernel config, specialist agents, slash commands, file-based memory, scheduled automation.
- Cost
- Free
- Needs
- Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me.
- Level
- Beginner — Pinned version: install the code at commit…
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: treat Claude Code as a persistent runtime and operating system rather than a chat session, codifying the architecture used by production agentic setups. Four layers, each a directory in your project root: the kernel (CLAUDE.md), which acts as the orchestrator with identity, routing rules, model policies and an agent registry; agents, the specialist identities with scoped tools and memory; commands, user-facing slash commands in .claude/commands such as /daily-sync; scripts, Python or JS daemons triggered by cron or webhooks; and state, an append-only JSON and markdown data layer with no external database. Configuration is git-tracked so the OS survives session restarts, while state can stay git-ignored. Covers when to build a personal OS for recurring tasks, structuring long-running projects where context must persist, and setting up scheduled automation that outlives any single session. From the affaan-m/ECC repository (MIT). Honest caveats: an architecture to build, not a one-click product; long-lived autonomous daemons need their own monitoring and cost controls. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Agentic OS is a free Muse skill that turns Claude Code into a persistent multi-agent operating system: kernel configuration, specialist agents, slash commands, file-based memory and scheduled automation. Its layers are the kernel CLAUDE.md as orchestrator, specialist agents with scoped tools and memory, user-facing slash commands, scripts triggered by cron or webhooks, and append-only state in JSON and markdown.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 4eb71d9Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Use "Agentic OS" with your Muse. 1. Open the skill: https://raw.githubusercontent.com/affaan-m/ECC/4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2/skills/agentic-os/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Scaffold an Agentic OS for [project]: kernel, two specialist agents, and a /daily-sync command" or "Review my CLAUDE.md kernel for routing gaps." 3. Build one layer at a time: kernel first, then agents, then commands, then scripts, then the state layout. Tip: write the kernel routing rules before adding agents; an OS with agents but no router is just a folder of prompts. Safety: a skill is plain-text instructions; it runs nothing by itself. Daemons and cron jobs act when you are away, so gate every destructive action behind an explicit approval.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 4eb71d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.