Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing through structured intermediate artifacts.
1 file for Codex and OpenCode: research-units-pipeline-skills AGENTS.md — 423 tokens loaded in every session.
AGENTS.md A 423 tok These files are WILLOSCAR/research-units-pipeline-skills's own configuration — they tell 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.