claudex-loop
Harden a plan with independent Claude/Codex review, then optionally build and cross-inspect…
Have Codex implement a concrete work order and have Claude independently inspect the final changes. Preserves the explicit Codex builder choice; use claudex-loop for host-based planning and automatic reviewer selection.
$ npx -y skills add chaseai-yt/claudex-loop --skill codex-build --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/codex-buildContext preview
The summary Claude sees to decide when to auto-load this skill.
Have Codex implement a concrete work order and have Claude independently inspect the final changes. Preserves the explicit Codex builder choice; use claudex-loop for host-based planning and automatic reviewer selection.
name: codex-build description: "Have Codex implement a concrete work order and have Claude independently inspect the final changes. Preserves the explicit Codex builder choice; use claudex-loop for host-based planning and automatic reviewer selection."
Compatibility entry point: the builder is explicitly Codex. The shared workflow and executable live in the sibling `claudex-loop` skill; install that skill alongside this one.
Load the shared [build reference](../claudex-loop/references/build.md) and [runtime reference](../claudex-loop/references/runtime.md). Preserve `SPEC_FILE` (mapped to the runner's `--plan`), `LOG_FILE`, `PROOF_CMD`, `MAX_FIX_ROUNDS`, and explicit model/effort arguments. The spec may have any filename; never substitute PLAN.md silently.
Use the current valid plan approval when this follows claudex-loop. An explicitly requested standalone work order can use `--unreviewed-spec`, with that status recorded. If the spec still needs consequential decisions, settle those before delegating; do not build by inventing missing requirements.
Preserve unrelated changes, record the baseline, independently run the proof, inspect staged and new files as well as the unstaged diff, and keep fix rounds bounded. After a Claude takeover, require fresh Codex inspection of Claude's edits; if both contributed, log authorship and have each inspect the other's changes. Never present an earlier review as covering later fixes. Present the completed diff for any remaining sign-off required by the user's authorization.
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.
Repo: chaseai-yt/claudex-loop
Harden a plan with independent Claude/Codex review, then optionally build and cross-inspect…
Recommend a model and a scoped handoff for a task in Claude Code or Codex. Use when choosing…
Have Codex independently review an existing implementation plan while Claude coordinates a…