Evidence and verification for AI coding agents: map code, reuse concepts, finish migrations, and gate diffs.
4 files for Codex, Claude Code and OpenCode: scip-hyper-optimization, typescript, scip-query AGENTS.md, scip-query CLAUDE.md — 720 tokens loaded in every session.
AGENTS.md A 694 tok CLAUDE.md A 26 tok .agents/skills/scip-hyper-optimization/SKILL.md A 46 tok .agents/skills/typescript/SKILL.md A 57 tok These files are PlunderStruck/scip-query's own configuration — they tell Codex, 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.