Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By adrianleb
Invoke Codex CLI as a peer reviewer during planning phases. Get architectural critique before presenting plans to users.
npx claudepluginhub adrianleb/codex-plan-critique-skill --plugin codex-plan-critiqueA coding agent skill that invokes Codex CLI as a peer reviewer during planning phases. Get architectural critique on your implementation plans before committing to them.
Works with Claude Code and Codex (or any coding agent that supports skills).
When you're planning an implementation, this skill runs Codex in your project directory to review the plan with full visibility into your codebase. Codex acts as a senior architect and evaluates:
It returns a structured critique with a verdict (APPROVE or CONCERNS), strengths, and actionable suggestions.
In Claude Code:
claude plugin marketplace add adrianleb/codex-plan-critique-skill
claude plugin install codex-plan-critique
git clone https://github.com/adrianleb/codex-plan-critique-skill.git
# Copy into your global skills (available in all projects)
cp -r codex-plan-critique-skill/skills/codex-plan-critique ~/.claude/skills/
# Or copy into a specific project (available only in that project)
cp -r codex-plan-critique-skill/skills/codex-plan-critique your-project/.claude/skills/
The skill triggers automatically during planning phases. You can also invoke it explicitly:
> /codex-plan-critique
> critique this plan
> get a peer review
★ Codex Peer Review ─────────────────────────
## Verdict: APPROVE
## Strengths
- Clean separation between API and data layers
- Good use of existing middleware patterns
## Concerns
- Missing error handling for the webhook endpoint
- Consider using the existing EventBus instead of a new pub/sub
──────────────────────────────────────────────
If Codex is unavailable, the skill gracefully skips the review and continues without blocking.
.claude-plugin/
plugin.json # Plugin manifest
skills/
codex-plan-critique/
SKILL.md # Skill definition
scripts/
codex-critique.sh # Codex invocation script
OPENAI_API_KEY environment variable or codex loginIdeas for improvement:
PRs and ideas welcome. Open an issue to discuss before large changes.
MIT
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Give Claude Code a second opinion using OpenAI Codex - automatic plan review via hooks
Autonomous Claude + Codex review loop. Plan a feature with adversarial pushback, or audit code, all in one window.
Command-driven Claude/Codex review workflows for multi-round plan and implementation review.
Symmetric two-AI peer review using OpenAI Codex CLI. Both AIs review independently in a blind pass, then debate per-issue with terminal states until convergence. Catches significantly more issues than single-pass validation.
Auto-converge a Claude-written plan via Codex (gpt-5) review iterations until clean ALLOW or max-iter.
Independent plan/spec reviewer for AI coding agents. Verifies claims against the workspace and returns structured verdicts with findings.
Hammock Driven Development as a coding agent skill. Think before you code.
Hand off curated project context to ChatGPT Pro over plaintext HTTPS, then drive the chatgpt.com session via Browser Use.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim