Zum Hauptinhalt springen
Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Second Opinion

Plugin Verifiziert Aktiv
Teil von:Trailofbits

Runs code reviews using external LLM CLIs (OpenAI Codex, Google Gemini) on uncommitted changes, branch diffs, or specific commits. Bundles Codex's built-in MCP server for direct tool access.

1 Skill 0 MCPs
Zweck

To provide users with an independent, LLM-powered code review capability, allowing them to compare different models and get detailed feedback on their code changes.

Funktionen

  • Runs code reviews using OpenAI Codex and Google Gemini CLIs
  • Supports review of uncommitted changes, branch diffs, and specific commits
  • Bundles Codex's built-in MCP server for direct tool access
  • Allows selection of review scope, context, and focus areas
  • Presents side-by-side comparison of results from multiple LLMs

Anwendungsfälle

  • Getting a second opinion on code changes from a different LLM
  • Reviewing branch diffs before opening a Pull Request
  • Checking uncommitted work for issues before committing
  • Performing focused reviews on security, performance, or error handling

Nicht-Ziele

  • Providing reviews using Claude's own models
  • Reviewing non-code files
  • Acting as a replacement for local linters or static analysis tools

Installation

Zuerst Marketplace hinzufügen

/plugin marketplace add trailofbits/skills
/plugin install second-opinion@trailofbits

Enthält 1 Erweiterungen

Skill (1)

Second Opinion Skill

Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion.

97

Qualitätspunktzahl

Verifiziert
96 /100
Analysiert about 11 hours ago

Vertrauenssignale

Letzter Commit3 days ago
GitHub-Inhaber trailofbits (opens in new tab)
Sterne5.2k
LizenzCC-BY-SA-4.0
Status
Quellcode ansehen

Ähnliche Erweiterungen

Review Agent Governance

99

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.

Plugin
wshobson

Performance Testing Review

99

Performance analysis, test coverage review, and AI-powered code quality assessment

Plugin
wshobson

Comprehensive Review

99

Multi-perspective code analysis covering architecture, security, and best practices

Plugin
wshobson

Skill Improver

99

Automatically reviews and fixes Claude Code skills through iterative refinement until they meet quality standards. Requires plugin-dev plugin.

Plugin
trailofbits

Codex Hud

99

Display OpenAI Codex API usage and costs inside Claude Code

Plugin
davepoon

Nanobanana

99

Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro). Supports text-to-image, image editing, aspect ratios, and 2K/4K output.

Plugin
ReScienceLab