super-truth

What problem does it solve?

It prevents optimistic but unverified AI results from being treated as true by adding an adversarial check that asks whether the claimed outcome actually holds in reality.

Core Features & Use Cases

• Adversarial verification gate: Runs multiple sub-agents to try to disprove producer claims and identify concrete counterexamples.
• Multi-input validation: Supports claims originating from code review findings, fix commits, QA/spec artifacts, visual-diff verdicts, and feature-implementation reports.
• Confidence-based publish/halt decision: Returns a 0–100 confidence score plus a gate decision (publish, halt, or escalate-to-human) driven by agent agreement and contradictions.
• Evidence-oriented verdicts: Produces structured verdict YAML with counterexamples and logs suitable for downstream orchestration.

Quick Start

Ask your agent to run the command: /super-truth verify <input> using the producer artifact you want grounded in reality (such as a commit SHA, review comment URL, test spec path, or visual-diff log).