By fingerskier
Teaches Claude Code to consult other AI coding CLIs (Gemini, Codex, Grok, Aider, Warp, vibe-tools, and more) to get an independent second opinion on a question, design, review, or bug.
A Claude Code plugin that teaches Claude to consult other AI coding CLIs — Gemini, OpenAI Codex, Grok, Aider, Warp, and vibe-tools — to get an independent second opinion on a question, design, code review, or bug, then synthesize their input with its own.
Cross-checking against independent models catches blind spots, surfaces alternative designs, and builds (or breaks) consensus before you commit to an approach.
| Component | Name | What it does |
|---|---|---|
| Slash command | /second-opinion [question] | Probes which AI CLIs are installed, queries them non-interactively, and synthesizes their answers. |
| Skill | second-opinion | Reference Claude loads automatically when you want cross-model review: exact non-interactive invocations, auth requirements, and install hints for each tool. |
| Subagent | second-opinion | Delegate target for gathering and reconciling outside opinions in its own context. |
From the fingerskier-plugins
marketplace:
claude plugin marketplace add fingerskier/claude-plugins
claude plugin install second-opinion@fingerskier-plugins
/second-opinion is a global mutex the right way to make this cache thread-safe?
/second-opinion review the diff in src/auth.ts for security issues
/second-opinion get Gemini's take on this error: <paste stack trace>
You can also just ask Claude in plain language — "get a second opinion on this from another AI" — and the skill/subagent will kick in.
The plugin detects which tools are installed (command -v) and only uses those,
and it verifies flags with each tool's --help before calling, so it stays
robust as the tools evolve. Expected non-interactive invocations:
| Tool | Headless call | Auth |
|---|---|---|
| Gemini CLI | gemini -p "…" | GEMINI_API_KEY |
| OpenAI Codex CLI | codex exec "…" | codex login / OPENAI_API_KEY |
| Grok Build (official xAI CLI) | grok -p "…" | browser sign-in / GROK_CODE_XAI_API_KEY |
| Aider | aider --message "…" --chat-mode ask | provider key |
| Warp (Oz CLI) | oz agent run --prompt "…" | WARP_API_KEY / Warp login |
| vibe-tools | vibe-tools ask "…" · vibe-tools repo "…" | provider key(s) |
Fallbacks the plugin will also use if present: llm
and a local model via ollama.
Note on cost & keys: these tools call third-party APIs and usually need an API key in your environment. If a tool isn't installed or isn't authenticated, the plugin reports it and moves on rather than failing.
Note on Aider: Aider edits files. The plugin uses
--chat-mode askfor opinion-only queries; it only lets Aider modify your tree when you explicitly want its proposed implementation as the "opinion".
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub fingerskier/claude-plugins --plugin second-opinionExegetical theology research — rigorous, multi-perspective Biblical exegesis with historian, linguist, author, theologian, disciple, shepherd, numerology, and full research skills.
CAD modeling with build123d — create, inspect, and export parametric 3D models using Python.
Design electronic schematics and PCB layouts using SKiDL — create circuits with Python code, validate designs, and export to KiCad.
Subagents for literature research — search PubMed, format citations, and synthesize a verified corpus into prose. Zero-install: uses public APIs, no bundled servers.
OpenSCAD parametric modeling — generate, edit, and visually inspect 3D models
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.