safe-loop
CommunitySustain autonomous coding in a safe loop.
Authorlc0rp
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Keeps coding agents running through epic work and long repair sessions by providing a structured, evidence-driven autonomous loop with built-in safety checks and automated scaffolding when needed.
Core Features & Use Cases
- Maintains ongoing progress across multi-step tasks, red/green/fix/verify cycles, and epic delivery with concrete evidence at each step.
- Automatically installs missing scaffolding, dependencies, or fixtures to finish tasks without user intervention.
- Supports delegation to subagents for parallel or split tasks while preserving safety and alignment with goals.
- Use Case: When you have a long-running feature or epic and user responses are infrequent, this skill keeps working and reports progress with traceable results.
Quick Start
Start the safe loop with your epic task and instruct it to proceed until completion, reporting evidence after each cycle.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: safe-loop Download link: https://github.com/lc0rp/luke-agent-scripts/archive/main.zip#safe-loop Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.