Codex CLI — Development agent for Claude Code
Codex CLI → any OpenAI-compatible endpoint.
How to install Codex CLI
Installs to ~/.claude/agents/henrikdukefoss-coding-agent-setups-codex-cli.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/henrikdukefoss/coding-agent-setups/HEAD/agents/codex-cli.md -o ~/.claude/agents/henrikdukefoss-coding-agent-setups-codex-cli.md Restart Claude Code, or start a new session, for it to be picked up.
What Codex CLI does
Codex CLI → any OpenAI-compatible endpoint
In `~/.codex/config.toml`:
[model_providers.myprovider]
name = "My provider"
base_url = "https://your-endpoint.example.com/v1"
env_key = "MYPROVIDER_API_KEY"
[profiles.myprovider]
model_provider = "myprovider"
model = "your-model-id"
export MYPROVIDER_API_KEY="your-key"
codex --profile myprovider
Docs: https://github.com/openai/codex
Alternatives in Development
- Agent Of Empires — Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and 1.2k ★
- Panel Artist A — 웹툰 패널 아티스트 A. scene 그룹 A에 배정된 패널들을 codex-image로 렌더링해 PNG로 저장한다 305 ★
- Codex Orchestrator — CLI tool for delegating tasks to GPT Codex agents via tmux sessions 263 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against
Independent Reviewer
Product-technical alignment reviewer. Spawned in a tmux pane via OpenAI Codex CLI with zero inherited context.
Provider Debugger
Diagnose live-provider compatibility failures for Kimi, GLM, and other OpenAI-compatible endpoints
Lmstudio Local
A locally-hosted model served through LM Studio's OpenAI-compatible API,
Model Runner
Deterministic wrapper that runs a prompt on a non-Claude model (OpenAI via Codex, Cursor's composer/grok/glm,
Dipeo Backend
Use this agent PROACTIVELY when working with DiPeO's backend ecosystem (server/ and cli/), including:\n- FastA
Related Skills
CliRelay
Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tena
Kaggle Tpu Lab
Qwen3.8-27B (bf16) on a free Kaggle TPU: OpenAI-compatible endpoint, 262k context, ~130 tok/s, works with Clau
Harness Bridge
Point any coding harness (Claude Code, Codex, OpenCode, Pi, OMP, Crush, Copilot, Grok…) at any OpenAI/Anthropi