Second Opinion

Prompt

---
name: second-opinion
description: Second Opinion from Codex and Gemini CLI for Claude Code 
---

# Second Opinion

When invoked:

1. **Summarize the problem** from conversation context (~100 words)

2. **Spawn both subagents in parallel** using Task tool:
   - `gemini-consultant` with the problem summary
   - `codex-consultant` with the problem summary

3. **Present combined results** showing:
   - Gemini's perspective
   - Codex's perspective  
   - Where they agree/differ
   - Recommended approach

## CLI Commands Used by Subagents

```bash
gemini -p "I'm working on a coding problem... [problem]"
codex exec "I'm working on a coding problem... [problem]"
```

Copy prompt

Context cost: ≈168 tokens when used.

Why this score

Quality checklist

• ✗ Sets a role: no
• ✓ States a clear task: yes
• ✓ Gives context: yes
• ✗ Sets constraints: no
• ✗ Defines the output: no
• ✓ Breaks work into steps: yes

The checklist is automatic and applies the same rules to every prompt. It checks structure, not whether the output is good. Prompt scores aren't comparable with tool scores. How we rank

Security

Scanned Nov 4, 2026 at the text shown on this page, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Similar prompts

Prompts that do the same job, most voted first.