second-opinion

second-opinion is a skill for Claude Code from pandysp/claude-plugins. It costs 116 tokens per session (1,128 once invoked), scanned A, original, MIT.

A request for an independent review of the agent’s reasoning before it presents a non-trivial answer or plan.

In plain words
What is it for?
Use it to validate designs, plans, and other decisions that would benefit from another perspective.
Why use it?
A fresh reviewer can spot mistaken assumptions, missing alternatives, or weak reasoning that self-review may overlook.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the second-opinion plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/pandysp/claude-plugins/second-opinion
Any agent
npx skills add pandysp/claude-plugins --skill second-opinion
Clone the repo
git clone --depth 1 https://github.com/pandysp/claude-plugins

Made for: Claude Code.

Or install second-opinion, the plugin that ships this one along with the rest of its 1 skill.

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/pandysp/claude-plugins/second-opinion.svg)](https://agentmods.dev/skills/pandysp/claude-plugins/second-opinion)
Your own site
<a href="https://agentmods.dev/skills/pandysp/claude-plugins/second-opinion"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/second-opinion.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00116 $0.01128
Opus 5 $0.00058 $0.00564
Sonnet 5 $0.00023 $0.00226
Haiku 4.5 $0.00012 $0.00113

Measured 5d ago against content hash ea0bae181a7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

second-opinion scanned grade A with 0 findings 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 5d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/second-opinion/skills/second-opinion/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Second opinion: independent review before presenting

Before presenting non-trivial thinking to the user, get an independent review of it. A second opinion is what a second doctor does: look at the situation fresh, form an independent view, say where they agree and where they'd do differently. The output is for you. The user sees the result of your improved reasoning, not the raw review.

What a valid second opinion is

Bind to the strongest channel available in this session that satisfies all three properties. The properties are fixed; the mechanism is whatever best provides them.

  • Independent: produced by something that didn't do the work and isn't anchored on your reasoning. Self-review wearing a reviewer hat is not a second opinion.
  • Fully informed: sees as much of the real context as possible. Prefer a channel that reads the full transcript over one you hand a summary: a distillation is curated by the same mind being reviewed, so your blind spots survive it. Distill only when the channel can't take the whole context.
  • At least peer-strength: a weaker model reviewing a stronger one mostly generates noise. Match or exceed your own capability.

Choosing the channel

In rough order of preference:

  1. A dedicated reviewer/advisor tool the harness exposes that sees the full transcript: best on the "fully informed" axis, no distillation loss.
  2. Fresh-context subagents at peer strength, given a faithful distillation, when no full-transcript channel exists. Spawn more than one for high-stakes or genuinely multi-faceted decisions; run them in parallel when the host supports it. Their convergence or divergence is itself signal.
  3. No independent channel available: say so plainly and fall back to a structured self-critique, labeled as such. A self-review honestly named beats one dressed up as independent. Don't simulate a second opinion that isn't there.

Let the stakes drive depth (a quick sanity check versus a full adversarial pass), not a fixed reviewer count.

Read the full file on GitHub · 53 lines

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. 5d ago First seen · 53 lines · 116 tokens per session scan A ea0bae181a7f

Subscribe to this mod's changes

second-opinion is a skill published in the GitHub repository pandysp/claude-plugins (5 stars, last pushed 14d ago), licensed MIT. It adds 116 tokens to every session and 1,128 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens