Doctor
Gated Claude x Codex build loop for Claude Code: Codex plans and implements from one persistent thread, Claude approves the plan and reviews the diff. Zero deps, 20-test smoke suite.
npx -y skills add ozzaii/codex-claude-loop --skill doctorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Check the codex-claude-loop substrate (codex CLI, jq, git, repo, verdict schema)
SKILL.md
0.6 KB, as published. Nobody here has run it
Load the codex-claude-loop skill, source its lib, and run cl_doctor.
Report each check plainly. If codex is missing, point at npm install -g @openai/codex
then codex login. If the repo resolved is not the one the user means, tell them to set
CL_REPO. Do not start a wave until every check passes.
If the user is running this harness for the first time, offer cl_selfreview — Codex
adversarially reviewing this harness before they trust it with their tree.