skills.rest
whatasoda
whatasodaCOMMUNITY
Explore all skills by this author →
𝕏@whatasodaGitHub

soda-loop-setup

Generate a multi-session agent loop harness with PROGRESS.md, AGENT_PROMPT.md, and run-loop.ts.

Updated Jan 31, 2026
Search Tags:#automation#project setup#agent#vision#harness#loop
One-click install
npx skills add https://github.com/whatasoda/agent-extensions --skill soda-loop-setup
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: soda-loop-setup
Source: https://github.com/whatasoda/agent-extensions/tree/main/plugins/dev-workflow/skills/soda-loop-setup
Command: npx skills add https://github.com/whatasoda/agent-extensions --skill soda-loop-setup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of a robust, multi-session autonomous agent loop harness, transforming a high-level vision into actionable project structure and prompts.

Core Features & Use Cases

  • Automated Harness Generation: Creates PROGRESS.md, AGENT_PROMPT.md, and run-loop.ts from a vision blueprint.
  • Phase-Based Structure: Organizes tasks into logical phases with dependencies.
  • Validation Integration: Pairs implementation items with validation steps.
  • Context Bounding: Enforces session limits, budget caps, and inactivity timeouts.
  • Use Case: Kickstart a complex, long-running agent project by defining the overall vision, and let this Skill set up the entire execution framework, including progress tracking, agent instructions, and the core execution script.

Quick Start

Run /soda-loop-setup to generate the autonomous loop harness for your project.

Frequently Asked Questions about soda-loop-setup

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

FAQPage Schema
How do I set up an autonomous agent loop for a multi-session project?▼

An autonomous agent loop harness organizes long-running tasks into a phase-based structure with dependencies. It pairs implementation items with validation steps and enforces context bounding through session limits, budget caps, and inactivity timeouts.

How do I generate an agent execution script from a high-level project vision?▼

Context bounding enforces session limits, budget caps, and inactivity timeouts to prevent runaway processes. This ensures your autonomous agent loop operates within controlled resource constraints during multi-session execution.

What files are needed to start an autonomous agent project with phase-based tasks?▼

Yes, this setup handles complex, long-running agent projects by organizing tasks into logical phases with dependencies. It automatically generates the entire execution framework, including progress tracking and validation integration.

Can I configure session limits and budget caps for an autonomous agent loop?▼

Yes, you can configure context bounding mechanisms like session limits, budget caps, and inactivity timeouts. The harness generation offers advanced configuration options to enforce these constraints during multi-session execution.

Related Skills

Explore More Software Engineering Skills→
AesopScottAesopScott
1

phase-alignment

Establish the MAPS lifecycle structure by agreeing on phase names, order, and scope.

Community
Advanced
prulloacprulloac

ai-agent-implementation

Coordinate AI agents to batch feature tasks, track progress, and surface blockers.

Community
Advanced
rajveersingh11rajveersingh11

loop-budget

Monitor token spend against daily caps and exit loops early.

Community
Intermediate
marcospmailmarcospmail

yato-existing-project

Orchestrate existing codebase workflows with Yato and Python.

Community
Advanced