autonomous

Automate end-to-end Claude Code execution in autonomous mode from Codex CLI.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/krystophny/prompts --skill autonomous-krystophny
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autonomous
Source: https://github.com/krystophny/prompts/tree/main/skills/autonomous
Command: npx skills add https://github.com/krystophny/prompts --skill autonomous-krystophny

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates end-to-end Claude Code execution in autonomous mode from Codex CLI to handle both single prompts and multi-step todo-driven workflows.

Core Features & Use Cases

  • Single Prompt Execution: run a one-off task via Claude Code CLI in autonomous mode.
  • TODO List Execution: process multi-step TODO items from Markdown or GitHub issues with iterative reviews, commits, and pushes.
  • CLAUDE.md conformance: enforce documentation and safety checks post-run.

Quick Start

Provide a prompt string, a TODO file path, or a GitHub issue number to start autonomous Claude Code execution from Codex CLI.

Frequently Asked Questions about autonomous

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

FAQPage Schema
How do I automate Claude Code execution from Codex CLI for multi-step workflows?

Autonomous Claude Code execution from Codex CLI automates end-to-end workflows by processing multi-step TODO items from Markdown or GitHub issues, performing iterative reviews, commits, and pushes after each cycle.

Can I run a single prompt task autonomously with Claude Code CLI?

Yes, autonomous execution supports single prompt tasks by running a one-off task via Claude Code CLI in autonomous mode, handling the entire prompt execution without manual intervention.

Does autonomous Claude Code execution enforce CLAUDE.md compliance?

Autonomous execution enforces CLAUDE.md compliance by applying documentation and safety checks post-run, ensuring that all automated tasks adhere to the specified project constraints and standards.

What inputs are supported for starting autonomous Claude Code execution?

Autonomous execution accepts a prompt string, a TODO file path, or a GitHub issue number to start, satisfying inputs for explicit prompts, TODO files, or GitHub issues.

How does autonomous execution handle git commits and pushes?

Autonomous execution handles git commits and pushes iteratively by reviewing, committing, and pushing after each cycle of a multi-step TODO workflow, enforcing explicit file staging.

What is the best way to process GitHub issues with Claude Code CLI autonomously?

Processing GitHub issues autonomously involves passing a GitHub issue number to start the execution, which then extracts TODO items and iteratively reviews, commits, and pushes changes.