codex-claude-loop
Use when driving a gated build loop where Claude orchestrates and Codex CLI implements — Claude plans and judges, Codex plans/implements from a persistent…
Check the codex-claude-loop substrate (codex CLI, jq, git, repo, verdict schema)
$ npx -y skills add ozzaii/codex-claude-loop --skill doctor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/doctorContext preview
The summary Claude sees to decide when to auto-load this skill.
Check the codex-claude-loop substrate (codex CLI, jq, git, repo, verdict schema)
name: doctor description: Check the codex-claude-loop substrate (codex CLI, jq, git, repo, verdict schema) allowed-tools: Bash, Read
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.
A gated build loop between Claude Code and Codex CLI. Codex writes the plan, Claude approves it, Codex implements that same plan from the same thread, Claude reviews the diff against it.
Repo: ozzaii/codex-claude-loop
Use when driving a gated build loop where Claude orchestrates and Codex CLI implements — Claude plans and judges, Codex plans/implements from a persistent…
Send an additional request to the exact Codex session for an implemented codex-claude-loop lane, sequenced behind its writer lock
Show every codex-claude-loop slug and where it stands (plan/review gates, impl marker, base)