Evidence-gated Obsidian brain for bounded multi-agent improvement loops.
An agent skill that stops your AI from shipping its first draft. Packages Matt Shumer's Gauntlet Loop method for Claude Code, Cursor, Codex, Copilot and any SKILL.md agent.
Evidence-driven Gauntlet Loop Agent Skill for Codex and Claude Code: project context, fresh builder/critic rounds, resumable proof, and integration gates.
Deterministic single-file builder for Gauntlet Loop prompts, with a linter for the technique's documented failure modes. Bilingual UI (EN/PT-BR).
Turn any goal into a short prompt that makes your agent set a real quality bar, run builder and critic pairs, compare blind, and loop until it wins.
Открытая система из Wayfinder и Gauntlet: постановка новой задачи, многоагентная реализация, независимая проверка и доказательства
To associate your repository with the gauntlet-loop topic, visit your repo's landing page and select "manage topics."