codex-cli

An open-source AI coding agent that runs locally from the terminal and can read, change, and run code on a computer.

In plain words
What is it for?
Use it to modify and run local code, or connect its long-running app server to another program through JSON-RPC.
Why use it?
It lets developers work with an AI coding assistant directly in their project and choose from API-key or ChatGPT-based sign-in methods.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/marcinbunsch/overseer/codex-cli
Clone the repo
git clone --depth 1 https://github.com/marcinbunsch/overseer
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,352 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.05352
Opus 5 $0.00000 $0.02676
Sonnet 5 $0.00000 $0.01070
Haiku 4.5 $0.00000 $0.00535

Measured 2d ago against content hash 7692e8c69ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

codex-cli scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Stored in `~/.codex/config.toml` (global) or `.codex/config.toml` (project-scoped).

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

| `config/mcpServer/reload` | Reload MCP configuration |
docs/agents/codex-cli.md · 671 lines

How it starts

The opening of the file, as written. The whole thing — 671 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex CLI & App Server

OpenAI Codex is a coding agent that runs locally from the terminal. The CLI is open-source (Apache-2.0), written in Rust, and can read, change, and run code on your machine. For GUI integrations, Codex exposes an app-server subcommand — a long-running JSON-RPC 2.0 process over stdio.

Source: https://developers.openai.com/codex/app-server

Quick Start

Installation

# npm (recommended)
npm install -g @openai/codex

# Homebrew
brew install codex

# Or download a binary from the latest GitHub Release
# https://github.com/openai/codex/releases

Authentication

codex login                # Browser-based ChatGPT OAuth flow
codex login --with-api-key # Read API key from stdin
codex login --device-auth  # Device-code flow (headless environments)

Three auth modes:

Mode Description
API Key (apikey) Caller supplies an OpenAI API key
ChatGPT managed (chatgpt) Codex owns the OAuth flow, persists & refreshes tokens
ChatGPT external tokens (chatgptAuthTokens) Host app supplies idToken + accessToken directly

Codex is included with ChatGPT Plus, Pro, Business, Edu, and Enterprise plans.

Platform Support

  • macOS & Linux — fully supported
  • Windows — experimental (best via WSL)

CLI Commands

Interactive Mode

codex                           # Launch full-screen TUI
codex "Tell me about this project"  # Launch with initial prompt
codex --model gpt-5-codex      # Override model
codex -i screenshot.png "Fix this"  # Attach image

Non-Interactive (exec)

codex exec "fix the CI failure"
codex exec --json "summarize changes"   # JSONL event output
codex exec -o result.md "write docs"    # Write final message to file
codex exec resume --last "continue"     # Resume previous session

Session Management

codex resume              # Pick from recent sessions
codex resume --last       # Resume most recent
codex resume <SESSION_ID> # Resume specific session
codex fork --last         # Fork most recent session

Read the full file on GitHub · 671 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 671 lines · 0 tokens per session scan C 7692e8c69ed1

Subscribe to this mod's changes

codex-cli is an agent published in the GitHub repository marcinbunsch/overseer (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,352 tokens. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens