14 files for Claude Code, Codex and OpenCode: case-studies, dataset-publishing, embedding-training, evaluation and 10 more — 8,293 tokens loaded in every session.
AGENTS.md A 7,713 tok CLAUDE.md A 580 tok .claude/settings.json A — .claude/settings.json A — .agents/skills/case-studies/SKILL.md A 128 tok .agents/skills/dataset-publishing/SKILL.md A 69 tok .agents/skills/embedding-training/SKILL.md A 143 tok .agents/skills/evaluation/SKILL.md A 79 tok .agents/skills/fine-tuning/SKILL.md A 113 tok .agents/skills/research-reporting/SKILL.md A 89 tok .agents/skills/transcript-distillation/SKILL.md A 136 tok .agents/skills/upload-deployment/SKILL.md A 90 tok .agents/skills/source-ingestion/SKILL.md A 85 tok .agents/skills/synthetic-data-generation/SKILL.md A 83 tok These files are ProfSynapse/Synaptic-Tuner'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.