A research lab for agentic coding - use it to verify of falsify, running various agentic setup against each other
11 files for Claude Code and OpenCode: agentic_coding_lab, build-overview, exact-coding-baseline-export, reanalyze and 7 more — 8,739 tokens loaded in every session.
CLAUDE.md C 8,739 tok .claude/settings.json A — .claude/skills/build-overview/SKILL.md A 36 tok .claude/skills/exact-coding-baseline-export/SKILL.md B 182 tok .claude/skills/reanalyze/SKILL.md A 81 tok .claude/skills/run-rq/SKILL.md C 100 tok .claude/skills/publish-site/SKILL.md C 88 tok .opencode/commands/build-overview.md A 5 tok .opencode/commands/exact-coding-baseline-export.md A 8 tok .opencode/commands/reanalyze.md A 8 tok .opencode/commands/run-rq.md A 7 tok These files are marcoemrich/agentic_coding_lab's own configuration — they tell Claude Code 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.