Analyzing rationale of LLMs generated to answer forecasting questions from Metaculus
13 files for Claude Code, Codex and OpenCode: otel-expo-style, otel-fastapi-style, otel-flask-style, otel-generic-style and 9 more — 7,503 tokens loaded in every session.
AGENTS.md C 7,503 tok .agents/skills/otel-expo-style/SKILL.md A 33 tok .agents/skills/otel-fastapi-style/SKILL.md A 35 tok .agents/skills/otel-flask-style/SKILL.md A 34 tok .agents/skills/otel-generic-style/SKILL.md A 72 tok .agents/skills/otel-instrument-feature/SKILL.md A 92 tok .agents/skills/otel-livekit-style/SKILL.md A 31 tok .agents/skills/otel-nextjs-style/SKILL.md A 46 tok .agents/skills/otel-onboarding-style/SKILL.md A 33 tok .agents/skills/otel-python-style/SKILL.md A 31 tok .agents/skills/otel-supabase-edge-style/SKILL.md A 40 tok .agents/skills/superlog-debug/SKILL.md A 75 tok .agents/skills/superlog-onboard/SKILL.md A 71 tok These files are pareelamre/analyzing-llm-rationale'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.