codex-cli

A guide to OpenAI Codex CLI, a terminal-based coding agent that can read, edit, and run code in a project. It covers interactive use, scripts, authentication, and permission settings.

In plain words
What is it for?
Use it to install and authenticate Codex CLI, start coding sessions, run non-interactive tasks in scripts or CI, and configure when the agent must ask for approval.
Why use it?
It explains how to run Codex safely and consistently instead of guessing at commands, approval modes, or configuration options.

Skill for Claude CodeCodex

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 skills/biggora/claude-plugins-registry/codex-cli
Any agent
npx skills add biggora/claude-plugins-registry --skill codex-cli
Clone the repo
git clone --depth 1 https://github.com/biggora/claude-plugins-registry

Made for: Claude Code, Codex.

Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00160 $0.02312
Opus 5 $0.00080 $0.01156
Sonnet 5 $0.00032 $0.00462
Haiku 4.5 $0.00016 $0.00231

Measured yesterday against content hash 31ec90ffe6d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-cli scanned grade B with 1 finding 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 yesterday.

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.

## Configuration (`~/.codex/config.toml`)
src/skills/codex-cli/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex CLI Skill

OpenAI Codex CLI (@openai/codex) is a lightweight, open-source AI coding agent that runs locally in the terminal. It can read, edit, and execute code in your project directory using GPT-5 models.

Quick Reference

Installation

npm install -g @openai/codex
# Authenticate (browser or API key)
codex           # launches TUI with browser auth
export OPENAI_API_KEY="sk-..."  # or use API key

Basic Usage

codex                              # Interactive TUI
codex "Fix the TypeScript errors"  # TUI with pre-filled prompt
codex exec "Run tests and fix failures"   # Non-interactive (CI/scripts)
codex e "Update CHANGELOG"         # Short alias for exec

Core Concepts

Approval Modes (-a / --ask-for-approval)

Controls when Codex pauses to ask before executing. The ONLY valid values are:

Mode Flag Config value Behavior
untrusted -a untrusted approval_policy = "untrusted" Max caution — approves almost everything
on-request -a on-request approval_policy = "on-request" Asks on sensitive actions (default for auto)
never -a never approval_policy = "never" Never asks — runs fully automated
reject -a reject approval_policy = "reject" Blocks all tool use

Note: --full-auto is a CLI-only shortcut (equivalent to -a on-request -s workspace-write). It is NOT a valid approval_policy config value. Values like "suggest", "auto-edit", or "full-auto" do not exist as config values.

Sandbox Modes (-s / --sandbox)

Controls filesystem and network access. The ONLY valid values are:

Mode Flag Access
read-only -s read-only Read files only, no writes
workspace-write -s workspace-write Write within working directory only
danger-full-access -s danger-full-access Full system access (use with caution)

Note: There is no --no-sandbox flag or sandbox = "none" config option. To bypass the sandbox entirely, use --dangerously-bypass-approvals-and-sandbox (alias --yolo).

Read the full file on GitHub · 266 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. yesterday First seen · 266 lines · 160 tokens per session scan B 31ec90ffe6d6

Subscribe to this mod's changes

codex-cli is a skill published in the GitHub repository biggora/claude-plugins-registry (2 stars, last pushed 4d ago), licensed MIT. It adds 160 tokens to every session and 2,312 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens