# Codex CLI

> Use this tool when you need to automate code generation, review, and querying across your codebase. It solves problems such as streamlining coding workflows, improving code quality, and enhancing developer productivity by providing seven key tools with configurable model selection and timeout limits. The Codex CLI takes in environment variables and command-line inputs, outputting generated code, review results, and query responses.

Canonical page: https://skillsregistry.net/skills/miles0sage-codex-cli  
JSON: https://api.skillsregistry.net/v1/skills/miles0sage-codex-cli

## Description

Bridges OpenAI's Codex CLI (GPT-5.4) into any compatible client, exposing seven tools for automated code generation, repository-wide code review, read-only codebase queries, session resumption, session listing, reusable skill templates, and project-specific memory retrieval. Requires a globally installed Codex CLI binary and supports configurable model selection and timeout limits via environment variables.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/miles0sage-codex-cli)
- **Repository:** <https://github.com/miles0sage/codex-mcp>

## 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": "miles0sage-codex-cli"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/miles0sage-codex-cli` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/miles0sage-codex-cli/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