second-opinion

second-opinion is a skill for Claude Code, Codex from backspacevenkat/polydev-claude-code-plugin. It costs 61 tokens per session (568 once invoked), scanned A, original, MIT.

When and how to ask other AI models (GPT, Gemini, Grok and more) for a second opinion through Polydev. Use when the user asks for other models' views, or when offering one would clearly help with a stuck bug, a design trade-off or a review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install with agentmods
npx agentmods add skills/backspacevenkat/polydev-claude-code-plugin/second-opinion
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add backspacevenkat/polydev-claude-code-plugin --skill second-opinion
Clone the repo
git clone --depth 1 https://github.com/backspacevenkat/polydev-claude-code-plugin

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for second-opinion

README.md
[![agentmods](https://agentmods.dev/badge/skills/backspacevenkat/polydev-claude-code-plugin/second-opinion/github.svg)](https://agentmods.dev/skills/backspacevenkat/polydev-claude-code-plugin/second-opinion)
Your own site
<a href="https://agentmods.dev/skills/backspacevenkat/polydev-claude-code-plugin/second-opinion"><img src="https://agentmods.dev/badge/skills/backspacevenkat/polydev-claude-code-plugin/second-opinion/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for second-opinion

Your own site · 80×15
<a href="https://agentmods.dev/skills/backspacevenkat/polydev-claude-code-plugin/second-opinion"><img src="https://agentmods.dev/badge/skills/backspacevenkat/polydev-claude-code-plugin/second-opinion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00568
Opus 5.5 $0.00024 $0.00227
Sonnet 5.5 $0.00012 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured today against content hash 561a067c646f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

second-opinion scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

example in a sandbox without npm access), use the curl fallback below or `/polydev:login`.
plugins/polydev/skills/second-opinion/SKILL.md · 55 lines

What it actually says

Second opinion with Polydev

Polydev asks the models set up in the user's Polydev account the same question and returns each answer. Its tools come from this plugin's MCP server (mcp__plugin_polydev_mcp__*). If they are missing (for example in a sandbox without npm access), use the curl fallback below or /polydev:login.

When to use it

Polydev sends the prompt it is given to other model providers, so call it only when the user asks for it (for example "ask other models", "get a second opinion", /polydev:ask) or agrees when you offer.

You may offer a second opinion, without calling the tool, when it would clearly help:

  • the user is stuck or two approaches have already failed;
  • an architecture, design or technology choice with real trade-offs;
  • a code review or security question where independent views help.

Ask first, for example: "Want me to ask a few other models through Polydev?" Call mcp__plugin_polydev_mcp__get_perspectives once the user says yes. Include only the context the question needs; leave out secrets, keys and unrelated code.

Curl fallback for get_perspectives (when MCP tools unavailable)

If MCP tools are not available but the user has authenticated:

# Load token if not in env
[ -z "$POLYDEV_USER_TOKEN" ] && [ -f "$HOME/.polydev.env" ] && source "$HOME/.polydev.env"

curl -s -X POST "https://www.polydev.ai/api/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $POLYDEV_USER_TOKEN" \
  -H "User-Agent: polydev-mcp/1.9.0" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "get_perspectives",
      "arguments": {
        "prompt": "YOUR QUESTION HERE"
      }
    },
    "id": "1"
  }'

After the answers come back

Summarise where the models agree, where they differ, and what you recommend. Setup and sign-in: /polydev:login (or npx -p polydev-ai polydev-login).

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 55 lines · 61 tokens per session scan A 561a067c646f

Subscribe to this mod's changes

second-opinion is a skill published in the GitHub repository backspacevenkat/polydev-claude-code-plugin (1 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 568 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Related

second-opinion compared with skills from other repositories

second-opinion next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
second-opinionbackspacevenkat/polydev-claude-code-pluginSkill1todayMITA61Claude Code, Codex
sync-bridgechromium/chromiumSkill25ktodayBSD-3-ClauseA109Claude Code, Codex
sync-model-processorchromium/chromiumSkill25ktodayBSD-3-ClauseA98Claude Code, Codex
adversarial-revieweremdash-cms/emdashSkill14ktodayMITA72Claude Code, Codex
gsd-ns-reviewopen-gsd/gsd-coreSkill11kyesterdayMITA16Claude Code
gitnexushashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A58Codex
issuejeremylongshore/tons-of-skills-marketplaceSkill2.9ktodayMITA115Claude Code