skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
chaseai-yt/claudex-loop241 installs

codex-review

Have Codex independently review an existing implementation plan while Claude coordinates a bounded revision loop. For automatic reviewer selection from either host, use claudex-loop with mode=review.

How do I install this agent skill?

npx skills add https://github.com/chaseai-yt/claudex-loop --skill codex-review
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubwarn

    The skill implements an automated review loop using an external CLI tool ('codex') to perform adversarial plan reviews. It involves executing shell commands with arguments parsed from previous tool outputs and provides an attack surface for indirect prompt injection by reading arbitrary repository files.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Codex Review

Compatibility entry point: explicitly use Codex as the plan reviewer. The shared workflow and executable live in the sibling claudex-loop skill; install that skill alongside this one.

In Claude Code, load claudex-loop and start at mode=review, host=claude, reviewer Codex. Preserve PLAN_FILE, LOG_FILE, MAX_ROUNDS / rounds, and explicit model/effort arguments. The invocation authorizes reviewing, not implementation. Do not restart an interview when the supplied plan is already adequate.

In Codex, explain that this explicit command would use the same provider for planning and review. Use the shared claudex-loop mode=review workflow with Claude as the independent reviewer unless the user specifically requested same-provider review. If they did, perform and label that as ordinary Codex review; do not claim cross-provider approval or use the cross-provider approval runner to certify it.

Read the shared runtime reference. Resolve the runner from the installed sibling skill, not the target repository. Use the actual resolved plan path on every round and build handoff. A valid completed result and APPROVED verdict are both required; failed, empty, blocked or malformed results are not approval. The host logs findings and dispositions, and stops at the round cap.

If implementation follows, use the shared build/inspection phase. An independent plan review does not replace independent review of the final code.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/chaseai-yt/claudex-loop/codex-review">View codex-review on skillZs</a>