second-opinion-skill

second-opinion-skill

A universal multi-engine plugin that routes code reviews to the AI engine of your choice — Gemini, opencode, Codex, Claude Code, Copilot, Qwen, Kilo, Antigravity, Command Code, Cursor.

No single model catches everything. This plugin makes cross-engine review a first-class part of your workflow: pick an engine, optionally pick a model, get an independent perspective in seconds.

This repo also ships plugin manifests for Claude Code and Codex, so the same bundle can be recognized across both ecosystems.

Engines

Engine	Model selection	Read-only flags
Gemini CLI	Automatic	-s --approval-mode plan
opencode	Provider → model (from registry)	--agent plan
Codex CLI	Optional (type-in)	-s read-only
Claude Code	Optional (type-in)	--print --permission-mode plan
GitHub Copilot CLI	Optional (type-in)	--plan --deny-tool=write --allow-all-tools
Qwen Code CLI	Optional (type-in)	-s --approval-mode plan
Kilo	Provider → model (free shown first)	--agent plan
Antigravity (agy)	Optional (agy models, or default)	--sandbox
Command Code (cmd)	Optional (cmd --list-models, or default)	--print --permission-mode plan --skip-onboarding
Cursor (agent)	Optional (agent --list-models, or default)	--print --plan --trust

All engines launch from the repo directory (--cwd) and read content via native filesystem tools — no stdin piping.

Beyond the read-only flags above, review.js auto-applies a few functional flags so non-interactive runs don't hard-fail or hang (these survive --unrestricted): codex gets --skip-git-repo-check (so a non-git --cwd doesn't abort), gemini gets --skip-trust (bypasses the "untrusted directory" gate), and opencode gets --dir <cwd> (scopes its sandbox file-access root so subtree reads aren't rejected as external_directory).

Note: opencode's big-pickle model is high-latency on review-sized prompts and may approach the default 600s timeout. Prefer a faster model, or raise --timeout, when using it.

Skills

Skill	Trigger phrases
second-opinion	"second opinion", "independent review", "cross-model review"
gemini-review	"ask Gemini", "review with Gemini", "Gemini's take"
opencode-review	"use opencode", "ask opencode", "review with opencode"
codex-review	"ask Codex", "review with Codex", "Codex's take"
copilot-review	"ask Copilot", "review with Copilot", "Copilot review"
qwen-review	"ask Qwen", "review with Qwen", "Qwen's take"
kilo-review	"ask Kilo", "review with Kilo", "Kilo's take"
agy-review	"ask Antigravity", "agy review", "review with agy"
cmd-review	"ask Command Code", "cmd review", "review with cmd"
cursor-review	"ask Cursor", "cursor review", "review with cursor"

Use cases

• Code review — senior-engineer-style critique with parallel sub-agent coverage (security, test coverage, regression, design)
• Second opinion — independent take on an architectural or design decision
• Security review — scan for injection, auth flaws, data exposure, input validation
• General consultation — any technical question with a structured answer

Requirements

• Node.js (for running bin/review.js and bin/list.js — any modern version)
• The CLI for each engine you want to use:
  • Gemini CLI — gemini-review
  • opencode — opencode-review
  • Codex CLI — codex-review
  • Claude Code — claude-review
  • GitHub Copilot CLI — copilot-review
  • Qwen Code CLI — qwen-review
  • Kilo — kilo-review
  • Antigravity (agy) — agy-review
  • Command Code (cmd) — cmd-review
  • Cursor CLI (agent) — cursor-review

You only need the CLIs for the engines you actually use.

Versioning

Release versions are managed by GitHub Actions. The workflow updates package.json, the Claude marketplace metadata, and the Codex plugin manifest together, so you do not need to edit version numbers by hand.

Permissions

All engine execution goes through bin/review.js, and all provider/model discovery goes through bin/list.js — grant permissions once instead of per-engine or per-CLI:

{
  "permissions": {
    "allow": [
      "Bash(~/.claude/plugins/cache/second-opinion-skill/second-opinion-skill/*/bin/review.js*)",
      "Bash(node ~/.claude/plugins/cache/second-opinion-skill/second-opinion-skill/*/bin/list.js*)"
    ]
  }
}

Installation

Claude Code

If you are using Claude Code, install the plugin through the marketplace: