Autonomous agentic loop that decomposes user queries into tasks, writes tests first, implements with fresh sub-agents, self-debugs on failure, and learns over time. Like the Ralph Wiggum loop, but it gets smarter.
npx claudepluginhub ashcastelinocs124/super-ralphSuper Ralph's cold analysis agent. Reads debug.md with fresh eyes after 3 failed worker attempts. Identifies root cause and writes a concrete fix plan. No ego, no sunk cost — just evidence-based diagnosis.
Super Ralph's universal quality gate. Evaluates every sub-agent's output against the task definition's quality standard, success criteria, and anti-patterns. Returns PASS or FAIL with specific, actionable feedback. Fresh context per evaluation — no bias.
Super Ralph's integration agent. Combines independently-built task outputs into one cohesive deliverable. Resolves conflicts, fixes integration issues, writes a run summary with timing, and produces a summary report.
Super Ralph's test-first agent. Writes strict, adversarial tests before any implementation exists. Tests enforce the quality bar — if they pass, the implementation is genuinely good.
Super Ralph's implementation agent. Reads tests first, then implements clean production-grade code that passes all tests. On retries, receives failure context. On attempt 3, writes debug.md before exiting.
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Uses power tools
Uses Bash, Write, or Edit tools
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use