skills.rest
tense-i
tense-iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

codex-skill

Orchestrate Codex/GPT execution to turn high-level requests into working code.

1|Updated Mar 8, 2026
Search Tags:#automation#cli#codex#sandbox#code-generation#ai-coding#workspace-write
One-click install
npx skills add https://github.com/tense-i/stock-market-simulator --skill codex-skill-tense-i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: codex-skill
Source: https://github.com/tense-i/stock-market-simulator/tree/main/skills/codex-skill
Command: npx skills add https://github.com/tense-i/stock-market-simulator --skill codex-skill-tense-i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Codex-skill enables autonomous code implementation by orchestrating Codex/GPT-powered execution to turn high-level requests into working code.

Core Features & Use Cases

  • Autonomous execution: perform tasks from start to finish with minimal prompts
  • Output-driven progress: provides structured final summaries and JSON outputs
  • Safe modes and fallbacks: read-only vs workspace-write vs danger-full-access modes with safeguards
  • Use Case: automate feature prototyping, bug fixes, and codebase improvements across a repository using codex exec

Quick Start

Run codex exec --full-auto to begin autonomous coding in your project directory.

Frequently Asked Questions about codex-skill

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

FAQPage Schema
How do I automate code implementation for feature prototyping and bug fixes?▼

Autonomous code implementation uses Codex/GPT-powered execution to turn high-level requests into working code. You can run codex exec --full-auto to automate feature prototyping, bug fixes, and codebase improvements from start to finish with minimal prompts.

What are the safe operating modes for AI-driven code generation in a sandbox?▼

AI-driven code generation in a sandbox supports read-only, workspace-write, and danger-full-access modes. These operating modes provide safeguards and fallbacks to control execution autonomy and protect your codebase during automated coding tasks.

Can I use autonomous coding execution in both local and CI environments?▼

Autonomous coding execution works in both local and CI-enabled environments. It orchestrates codebase tasks such as refactoring and bug fixes across your repository using codex exec, providing structured JSON outputs and final summaries regardless of the environment.

How do I get structured output and summaries after an automated codebase refactoring?▼

Automated codebase refactoring provides structured final summaries and JSON outputs upon task completion. This output-driven progress tracking ensures you can verify the changes made by the autonomous execution without manually reviewing every modified file.

What is the best way to run autonomous code generation with minimal prompts?▼

The best way to run autonomous code generation with minimal prompts is executing codex exec --full-auto in your project directory. This triggers the Skill to perform tasks from start to finish, turning high-level requests into working code autonomously.

Related Skills

Explore More Software Engineering Skills→
djacobsmeyerdjacobsmeyer
3

sandbox-manager

Configure Claude Code sandbox policies in settings.json for secure code execution.

Community
Advanced
polsegupolsegu

prototype

Plan and execute throwaway game prototypes with a phased workflow and Prototype Report.

Community
Intermediate
AnveioAnveio
1

claude-agent-sdk

Build autonomous coding agents with the Claude Agent SDK for TypeScript.

Community
Advanced
Andy-HNUAndy-HNU

building-with-llms

Guide design and deployment of LLM-powered AI applications with structured prompts and architecture patterns.

Community
Intermediate