CodeyBox — Git skill for Claude Code

CodeyBox

**An autonomous coding orchestrator.** Hand it a task — a title and a prompt against one of your repos — and CodeyBox picks a coding agent, runs it inside a throwaway VM, reviews the result, resolves merge conflicts, and lands the change on your branch (and on GitHub, if you point it there). You stay in the loop for product decisions; it handles the delivery grind.

It drives a *fleet* of agent CLIs — Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Gemini, opencode, Antigravity, CrockCode — and routes each task to whichever one is best and available, falling back automatically when a provider hits a rate limit. No coding agent ever runs on your host: every model call that touches a repository happens through an agent CLI inside a sandbox.

Every agent is boxed in a real VM behind a host-enforced firewall, because the point is to be able to leave it running — see [Security: defense in depth](#security-defense-in-depth).

Built in C#/.NET 10. Managed repos can be any stack — Python, Node, Go, Rust, C#, or your own — through config-driven auditors.

Why you might want this

• You have more coding work than reviewer attention. Queue it. CodeyBox works items in parallel, runs the same audit gate a human reviewer would, and only bothers you when it genuinely needs a decision.
• You don't trust an LLM agent with sudo on your machine. Every agent runs in a real VM with kernel isolation and a host-enforced firewall — a compromised agent can't reach your host or exfiltrate past its allowlist.
• You pay for several coding subscriptions. CodeyBox pools them: one task queue, automatic routing across agents, quota-aware fallback, and per-agent cost tracking so you can see where the money goes.
• You want it to be hackable. Every subsystem sits behind an interface; add an agent, an auditor, a forge, or a credential backend without forking.

How it works

flowchart TD
    A["POST /workitems"] --> Q["Queue"]
    Q -