# auto-codex

> auto-codex — neonplants-auto-codex. Use this tool when you need to streamline your coding process with a token-efficient autonomous pipeline. The auto-codex tool solves problems related to coding efficiency and quality by planning, reviewing, and implementing code, with optional metric optimization. It takes in coding tasks and outputs implemented code, ideal for use cases where rapid and reliable coding is required, such as git-based projects.

Canonical page: https://skillsregistry.net/skills/neonplants-auto-codex  
JSON: https://api.skillsregistry.net/v1/skills/neonplants-auto-codex

## Description

Get the best of both worlds. Token-efficient autonomous coding pipeline for Claude Code. Codex plans, Opus reviews, Sonnet swarm implements, optional metric optimization (inspired by karpathy/autoresearch).

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** devops-ci
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/neonplants/auto-codex)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "neonplants-auto-codex"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/neonplants-auto-codex` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/neonplants-auto-codex/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt