Agents / Skills
Overnight Audit
An autonomous agentic workflow for overnight codebase auditing and repair.
Is this your creation?

Description
A sophisticated agentic system running in Claude Code that orchestrates a hierarchical team of models to audit apps while the developer sleeps. It uses a lead Fable 5.2 agent to manage Haiku explorer sub-agents for file mapping and Sonnet sub-agents for code fixes, prioritizing security holes and bugs through a rigorous scoring rubric and Git worktree isolation.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.