AI Marketplaces Leaderboard

Loupe Code Review

ChatGPT plugin

Verified multi-reviewer review

View in ChatGPT directory
Featured
No

not on the featured shelf

Movement

From our daily snapshots over the last 30 days.

Rank by placement

#5491of 6,0222places up24h—7d
#5,443#5,588#5,733#5,878Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

Rank in Developer tools

#491of 537024h—7d
#488#499#510#521Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

In its category

How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.

Developer tools491st of 537 by placement
#PluginPosition7d
488EW EDC Protocol Mapper#5431—
489MOOS-IvP Skills#5436—
490Graphify#5475—
491Loupe Code ReviewThis page#5491—
492keelson#5500—
493Vibecode#5501—
494Beste#5510—

All 537 Developer tools plugins

Run independent specialist reviewers on a working tree, branch, commit, range, or pull request, then verify and consolidate their evidence into one structured review. Loupe uses bounded parallel Codex reviewers and can optionally add Claude reviewers when the user's authenticated Claude CLI is available, providing cross-provider diversity without requiring a separate Loupe account. Configure provider-specific reasoning effort while preserving reviewer attribution, duplicate relationships, rejected claims, and partial failures.

Loupe runs locally under the user's Codex session and permissions. It has no hosted service, developer authentication flow, telemetry collector, or external data store. Reviewers may inspect repository content and send it to the user's configured Codex or Claude provider, so users must be authorized to disclose the review material.

Example prompts

  • “Review my current uncommitted changes with independent reviewers and verify every finding.”
  • “Review the last commit with Loupe, emphasizing correctness and design evidence.”
  • “Review PR #123 with Loupe and consolidate duplicate or unsupported findings.”

Skills

  • loupe

    Run multiple parallel external code reviews for a given scope, then independently verify the findings and organize them into one final review. Possible scopes include uncommitted changes (default) or specific commits, commit ranges, branches, pull requests, or other custom textual review scopes.

Categories
Made by
Philipp Allgeuer · Website
Sign-in
On Install
Capabilities
Run independent specialist reviewers, Verify and consolidate review evidence, Review working trees, branches, commits, and pull requests, Use bounded parallel review and configurable reasoning effort
Availability
Available
Version
0.2.5
Keywords
codex code review, multi-agent code review, verification, false positives, language-agnostic
Created
September 30, 2026
More info