ralphex-auto

Create or resume repository work plans and launch ralphex execution.

1|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/materkey/cc-plugins --skill ralphex-auto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralphex-auto
Source: https://github.com/materkey/cc-plugins/tree/main/plugins/ralphex-auto/skills/ralphex-auto
Command: npx skills add https://github.com/materkey/cc-plugins --skill ralphex-auto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the back-and-forth normally needed to turn a coding request into an executable implementation plan. It infers intent from the current conversation, decides whether to continue an existing plan or create a new one, and starts ralphex immediately without asking follow-up questions.

Core Features & Use Cases

  • Automatic plan continuation or creation: Detects active work in docs/plans, reuses the most relevant unfinished plan when appropriate, or generates a new minimal plan from repository and conversation context.
  • Execution mode selection: Chooses between native execution and SBX sandbox execution based on task risk, user intent, and environment availability.
  • Operational safeguards: Applies fixed iteration limits, confirms launch through the progress log, and preserves host protection expectations when sandbox mode is selected.
  • Use Case: When a user says ralphex go after an interrupted coding session, this Skill can recover the likely plan, restart autonomous execution, and return the exact progress file to watch.

Quick Start

Ask the assistant to use ralphex-auto to continue the current work or create a plan from the conversation and start execution immediately.

Frequently Asked Questions about ralphex-auto

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

FAQPage Schema
How do I resume an interrupted coding plan and restart autonomous execution?

Autonomous execution resumes by detecting active work in docs/plans, reusing the most relevant unfinished plan, and immediately relaunching execution without asking follow-up questions. You simply prompt the assistant to continue, and it recovers the plan and restarts the workflow automatically.

What is the best way to turn a coding request into an executable implementation plan without back-and-forth?

Automated plan creation infers intent from the current conversation and repository context, then generates a minimal executable implementation plan immediately. It removes interactive clarification by deciding whether to continue an existing plan or create a new one based on repository context discovery.

Can I run risky builds and tests in a sandbox environment during autonomous workflow execution?

Yes, sandbox execution is supported for risky builds and tests. The workflow selects between native execution and SBX sandbox execution based on task risk, user intent, and environment availability, while preserving host protection expectations during the process.

Does autonomous execution apply safeguards like iteration limits when launching implementation workflows?

Yes, operational safeguards include applying fixed iteration limits, confirming launch through progress log verification, and preserving host protection expectations when sandbox mode is selected. These safeguards ensure controlled autonomous execution without runaway processes.

How do I track progress once an autonomous implementation workflow starts?

Progress tracking is handled through progress log verification, which confirms the launch and returns the exact progress file to watch. The workflow applies operational safeguards and fixed iteration limits to manage the execution lifecycle automatically.