autonomous-skill

Orchestrate long-running Codex tasks with persistent state in .autonomous directories.

1|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/devkeni/Skills --skill autonomous-skill-devkeni
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autonomous-skill
Source: https://github.com/devkeni/Skills/tree/main/ai-apps/autonomous-skill
Command: npx skills add https://github.com/devkeni/Skills --skill autonomous-skill-devkeni

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires codex, and includes scripts (resource) components.

What problem does it solve?

Long-running Codex work across multiple sessions can lose context, require handoffs, and risk progress decay. This Skill provides a structured autonomous-task framework using an Initializer + Executor pattern with persistent state under .autonomous to resume, continue, and manage multi-session tasks without losing progress.

Core Features & Use Cases

  • Dual-agent orchestration: Split work between an INITIALIZER (breakdown) and an EXECUTOR (progressive execution) with automatic session continuation.
  • Session persistence: Stores task state under .autonomous/<task-name>/ to support resumable tasks across Codex sessions.
  • On-demand task data: Patterns for running tasks deterministically, resuming, listing tasks, and separating task tracking from project files.
  • Use Case: Long-running experiments, multi-session data gathering, or complex analyses that need pause/resume without losing state.

Quick Start

Start a new autonomous task by running the session runner with a description of the task.

Frequently Asked Questions about autonomous-skill

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

FAQPage Schema
How do I resume long-running Codex tasks across multiple sessions without losing progress?

To resume long-running Codex tasks across sessions, this framework persists state in `.autonomous` directories. It coordinates an Initializer and Executor to manage cross-session handoffs, ensuring deterministic task progression and pause/resume capabilities without progress decay.

What is the Initializer and Executor pattern for autonomous workflow orchestration?

The Initializer and Executor pattern splits autonomous workflow orchestration by breaking down work into tasks and progressively executing them. This dual-agent coordination enforces non-interactive execution and sandboxed execution via Codex.

How do I start a new autonomous task using Codex session management?

Start a new autonomous task using Codex session management by running the session runner with a task description. The framework creates a per-task directory under `.autonomous/<task-name>/` to track structured data and state separately from project files.

Does this autonomous task scheduler support non-interactive execution in a sandboxed environment?

Yes, this autonomous task scheduler enforces non-interactive execution and sandboxed execution via Codex. It applies to multi-session workflows requiring deterministic task progression, cross-session handoffs, and structured tracking through per-task directories.

When should I use a dedicated session management framework for multi-session workflows?

Use a dedicated session management framework for multi-session workflows when running long experiments, multi-session data gathering, or complex analyses. It prevents context loss and progress decay by persisting state under `.autonomous` for deterministic task progression.