Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Latest release v0.1.0 · 7 Jul 2026
5 files for Claude Code, Codex and OpenCode: elaboration, human-summary, initialize, write-paper and 1 more — 2,595 tokens loaded in every session.
AGENTS.md A 2,595 tok .agents/skills/elaboration/SKILL.md A 30 tok .agents/skills/human-summary/SKILL.md A 103 tok .agents/skills/initialize/SKILL.md A 141 tok .agents/skills/write-paper/SKILL.md A 106 tok These files are frenzymath/Danus's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.