skills.rest
PolyArch
PolyArchOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ask-codex

Send questions to Codex and output responses to stdout.

1.4k|123|Updated Jan 12, 2026
Search Tags:#automation#codex#ai#plugin#query#shell#code-review
One-click install
npx skills add https://github.com/PolyArch/humanize --skill ask-codex-polyarch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ask-codex
Source: https://github.com/PolyArch/humanize/tree/main/skills/ask-codex
Command: npx skills add https://github.com/PolyArch/humanize --skill ask-codex-polyarch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Consult Codex as an independent expert to obtain Codex responses to questions or tasks.

Core Features & Use Cases

  • Sends a question or task to Codex and returns the response.
  • Supports optional flags like --codex-model and --codex-timeout; reconstructs the command so those flags remain separate shell arguments.
  • Outputs Codex's response to stdout and status information to stderr. The default model is gpt-5.5:high with a 3600-second timeout.

Quick Start

Run the scripted command with your question and any optional flags, and read Codex's response from stdout.

Frequently Asked Questions about ask-codex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query Codex from a shell script for code review?▼

You can query Codex from a shell script by running the command with your question, and the Skill returns the Codex response to stdout while sending status information to stderr.

What's the best way to automate deterministic Codex interactions for brainstorming?▼

Automating deterministic Codex interactions is done by executing the scripted command with your task, which preserves argument boundaries and outputs the response to stdout.

Can I specify a different model when consulting Codex as an independent expert?▼

Yes, you can specify a different model using the optional --codex-model flag when reconstructing the command, with the default model being gpt-5.5:high.

How do I prevent long-running Codex queries from hanging in my automation workflow?▼

You can prevent Codex queries from hanging by setting the optional --codex-timeout flag, which defaults to 3600 seconds, to limit the execution time.

Does this approach separate Codex response data from status logs for pipeline processing?▼

Yes, the approach separates Codex response data from status logs by writing the Codex response to stdout and emitting status information to stderr.

Are optional flags preserved as separate shell arguments when reconstructing commands?▼

Yes, optional flags such as --codex-model and --codex-timeout are preserved as separate shell arguments when the command is reconstructed.

Related Skills

Explore More Software Engineering Skills→
duanbiao2000duanbiao2000
3

shellcheck-configuration

Configure ShellCheck static analysis for shell scripts in CI/CD workflows.

Community
Advanced
sd0xdevsd0xdev
187

codex-cli-review

Automates Codex CLI review of uncommitted changes with structured summary output.

Community
Advanced
claude-worldclaude-world
81

changelog

Automate collection of code changes, test results, and commit history via Git hooks.

Official
Intermediate
intenet1001-commitsintenet1001-commits
1

cs-experiencing

Manage a centralized versioned experience knowledge repository across Claude Code plugins.

Community
Advanced