ralph-wiggum-loop
Ralph Wiggum Loop - Enterprise Workflow Engine
Build powerful AI-driven development workflows that iterate until tasks succeed. Features a steering packet architecture for real-time workflow control, plugin system, agent orchestration, monitoring, and enterprise-grade workflow patterns including DAGs, state machines, and circuit breakers.
Prompt Architecture Overview
Ralph Loop uses stacked markdowns with a two-level architecture:
Level 1: System Context (Static - Always Loaded)
- AGENTS.md - Global project context for ALL agents (tech stack, conventions, how to run)
- System Prompts - Per-agent identity from config (who the agent is)
- These are NOT modified during execution
Level 2: Steering Prompts (Dynamic - Modified Each Iteration)
- PROMPT.md - Loaded by ALL agents (common execution context: current task, failures, evidence)
- PROMPT-BUILDER.md - Loaded ONLY by builder (builder workflow guide)
- PROMPT-VERIFIER.md - Loaded ONLY by verifier (verifier workflow guide)
- PROMPT-.md - Loaded ONLY by that agent role
More from wojons/skills
adversarial-thinking
Apply systematic adversarial thinking patterns including devil's advocate, assumption busting, red teaming, and white hat security approaches
45devils-advocate
Challenge ideas, assumptions, and decisions by playing devil's advocate to identify weaknesses and prevent groupthink
41redteam
Think and act like an attacker to identify security vulnerabilities, weaknesses, and penetration vectors through adversarial security testing
37code-migration
Guide framework and library migrations with incremental strategies, breaking change analysis, compatibility testing, and automated migration tools
35observability-logging
Use logs as part of comprehensive observability strategy including metrics, traces, alerts, and dashboards for system understanding and operational excellence
34white-hat
Build defensive security capabilities, implement security by design, and practice ethical hacking to protect systems proactively
34