codex

A coding agent from OpenAI available as either a command-line tool for the terminal or a desktop app called ChatGPT. CCR supports both ways of opening it.

In plain words
What is it for?
Use it to create terminal or desktop profiles, set provider and model details, configure advanced options, and optionally connect an AgentClaw bot.
Why use it?
It lets you route Codex through another provider, choose a model, and maintain separate configurations for different projects or uses.

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/musistudio/claude-code-router/codex
Clone the repo
git clone --depth 1 https://github.com/musistudio/claude-code-router
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 1,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.01140
Opus 5 $0.00000 $0.00570
Sonnet 5 $0.00000 $0.00228
Haiku 4.5 $0.00000 $0.00114

Measured yesterday against content hash 442bc4a5179a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex scanned grade A with 0 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 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/src/content/docs/en/configuration/agents/codex.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Who this is for

Codex is OpenAI's coding agent. CCR supports both surfaces:

  • Codex CLI — the terminal agent.
  • ChatGPT app — the desktop app (the renamed Codex desktop app).

Use this page to route Codex to a non-OpenAI provider, pin a model, or run separate Codex/ChatGPT instances.

New to CCR? Add a provider and model first. See Add a provider and the Agent Config overview.

Prerequisites

  1. CCR Desktop is running with at least one provider + model configured.
  2. Codex CLI is installed (available as codex on PATH), or the ChatGPT desktop app is installed.
  3. You are on Agent Config and click Add profile.

Create the profile

  1. On Agent Config, click Add profile and choose Codex.
  2. Enter a Config name (for example Codex - Work).
  3. Choose Effect scope and Entry mode.
  4. Confirm Provider ID, Provider name, and Codex model.
  5. Adjust advanced settings only if your local setup needs them.
  6. If the entry mode includes App and you use AgentClaw, bind a Bot.
  7. Save, then open Codex from CCR (terminal button for CLI, play button for ChatGPT).

Configuration reference

Field How to set it Effect
Agent Choose Codex Creates Codex launch entries in CCR.
Config name Free text, e.g. Codex - Work Identifies the profile. Desktop commands use ccr-app "<name>"; CLI commands use ccr "<name>".
Enabled Toggle on/off Disabled profiles are not applied and not offered as launch entries.
Effect scope Only opened from CCR / System default Keeps changes limited to CCR launches, or makes this the system-default Codex profile. Only one enabled system-default Codex profile is allowed.
Entry mode CLI & APP / CLI only / App only Which launch entries (terminal command and/or ChatGPT app) are exposed.
Provider ID Alphanumerics, ., _, -; default claude-code-router Provider reference for this Codex profile. Keep it stable.
Provider name Free text; default Claude Code Router Display name shown in Codex.
Codex model Provider model or Fusion model Default Codex model. If left empty, CCR uses the first available default model.
Show all sessions Toggle Writes show_all_sessions so Codex lists all sessions.
Config file Path Used for the system-default Codex profile.
Codex CLI path Optional absolute path to the codex binary Fill only when Codex is not on PATH.
Codex home Optional directory Sets CODEX_HOME. Fill only when you need a specific home directory.
Remote frontend mode app / cli / claude-code Leave default unless you have a specific reason.
CCR managed compact Toggle Lets CCR manage context compaction for this profile.
Environment variables Key/value rows Optional advanced overrides; leave empty for normal use.
Bot Select a saved Bot (App entry only) Binds an AgentClaw IM bot to the ChatGPT app entry.

Read the full file on GitHub · 89 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 · 89 lines · 0 tokens per session scan A 442bc4a5179a

Subscribe to this mod's changes

codex is an agent published in the GitHub repository musistudio/claude-code-router (36,975 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,140 tokens. A static security scan graded it A with 0 findings. 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