Pushary
Connect Codex

Control Codex
from your phone.

Approve an escalated command, answer a question, or stop a runaway session from your lock screen. Codex keeps running on your machine.

Connect Codex
bash
npx @pushary/agent-hooks@latest setup

Pick Codex when prompted. Installs the hooks and connects over MCP.

Hacker NewsFeatured on Hacker News
Claude Code, Codex, Cursor, Gemini CLI and more
iPhone, Android and Mac
Your code never leaves your machine

Codex has an auto-reviewer. You should go first.

Left alone, Codex can hand an escalated command to its own reviewer, which decides without you and tells the model the action was rejected. Pushary answers the same event from your phone before the reviewer ever runs.

Codex on its own
Sit at the terminal to catch an escalation
The reviewer can refuse without asking you
Walk away and the turn stalls on a question
No record of what was approved, or why
Nothing stops a run that has gone wrong
With Pushary on your phone
Codex runs on your machine, as it always did
The escalation reaches you before the reviewer
Answer a question and the turn keeps going
Every decision lands in an audit trail
Kill switch stops it in one move

Blocks, not pings

Codex waits on PermissionRequest, so an escalated command sits unrun until you answer.

Before the reviewer

Your approve or deny settles the event and Codex's auto-reviewer is skipped entirely.

One setup

The same command covers Claude Code, Cursor, Gemini CLI and Hermes on that machine.

Let Codex run. Keep the last word.

One command to connect. Approve, answer, or stop from your phone.

Start your trial

Related

Codex notifications·Codex skip permissions·Control Claude Code from phone·Human in the loop·All agents

Frequently asked questions

Can I run Codex from my phone?

Yes. The Pushary app can start Codex on a connected computer, send it an instruction, approve or deny an escalated command, answer a question, and stop a running session. The computer has to be awake, logged in, online, and running the Pushary background service. Codex itself never leaves your machine.

Does this work with the Codex CLI or the ChatGPT Codex app?

The Codex CLI, on your own computer. Pushary installs Codex's native hooks and connects over MCP, so it reads the same PermissionRequest and Stop events the CLI already emits. Cloud tasks you start inside ChatGPT run on OpenAI's infrastructure and do not emit those hooks, so they are out of scope.

What happens to Codex's auto-reviewer when Pushary is connected?

You get asked first. Codex fires PermissionRequest for an escalated command before its auto-reviewer runs, and Pushary answers that event from your phone. An approve or deny from you settles it and the reviewer is skipped entirely. If you do not answer, the event falls through to the reviewer exactly as it would without Pushary.

Does an escalated command really wait for my answer?

Yes. Codex blocks on PermissionRequest, so the command sits unrun until the hook returns. That is an enforced gate on your machine, not a notification you might catch in time. You set the timeout and what happens when it passes: keep waiting, deny, or hand it back to Codex.

Does it work with codex exec in a script or CI?

Notifications and the audit trail do. Approvals do not gate it: codex exec reports bypassPermissions whatever approval policy is set, which is the correct headless answer. Use phone approvals for interactive sessions, and keep CI runs governed by the sandbox and the permissions you grant the job.

Do I need a separate setup if I also use Claude Code?

No. One run of the setup command lets you pick every agent on the machine, and one subscription covers them. Approvals, questions, and the audit trail work across Codex, Claude Code, Cursor, Gemini CLI, Hermes, VS Code, and MCP clients.