consult-second-opinion

consult-second-opinion is a skill for Claude Code, Codex from ThrownLemon/claude-code-plugins. It costs 70 tokens per session (560 once invoked), scanned A, original, MIT.

A skill for asking another AI model for an independent view of code, design, or a technical decision. It can send questions or branch reviews to GLM through z.ai or to Google Gemini.

In plain words
What is it for?
Use it for free-form second opinions, third-party pull-request reviews, or focused reviews such as security checks.
Why use it?
A second model can provide another perspective when you want to challenge an approach or review a change.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the consult plugin — 1 skill, 3 commands 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/thrownlemon/claude-code-plugins/consult-second-opinion
Any agent
npx skills add ThrownLemon/claude-code-plugins --skill consult-second-opinion
Clone the repo
git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins

Made for: Claude Code, Codex.

Or install consult, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 consult-second-opinion

README.md
[![agentmods](https://agentmods.dev/badge/skills/thrownlemon/claude-code-plugins/consult-second-opinion.svg)](https://agentmods.dev/skills/thrownlemon/claude-code-plugins/consult-second-opinion)
Your own site
<a href="https://agentmods.dev/skills/thrownlemon/claude-code-plugins/consult-second-opinion"><img src="https://agentmods.dev/badge/skills/thrownlemon/claude-code-plugins/consult-second-opinion.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 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 $0.00070 $0.00560
Opus 5 $0.00035 $0.00280
Sonnet 5 $0.00014 $0.00112
Haiku 4.5 $0.00007 $0.00056

Measured 3d ago against content hash ced1c2cea8c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consult-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 3d 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/consult/skills/consult-second-opinion/SKILL.md · 60 lines

What it actually says

Consult — Second Opinion Skill

This skill activates when the user wants another model family to weigh in. The plugin ships a small CLI (scripts/consult.mjs) that hits z.ai's GLM-5.2 or Google Gemini directly. No extra CLI binaries needed — just an API key in env.

When to use

  • "Get a second opinion from GLM on this design"
  • "Ask Gemini whether this migration is safe"
  • "What would z.ai do here?"
  • "Run a third-party review of this PR"

How to invoke

For free-form questions:

node ${CLAUDE_PLUGIN_ROOT}/scripts/consult.mjs ask --provider zai "<the question, with all needed context inlined>"

For a code review of the current branch (auto-gathers git diff):

node ${CLAUDE_PLUGIN_ROOT}/scripts/consult.mjs review --provider zai
node ${CLAUDE_PLUGIN_ROOT}/scripts/consult.mjs review --provider gemini --focus "security"

Use --provider gemini when the user explicitly asks for Gemini, otherwise default to zai.

Important context guidelines

  • The remote model has no access to the local filesystem. Inline every piece of relevant code or context into the prompt argument. Don't reference files it can't see.
  • Keep prompts focused. Long context dumps are fine when justified, but trim to what's load-bearing.
  • For reviews, the script handles diff extraction — don't paste a diff manually.

Provider keys

Verify with /consult:config. If missing, ask the user to set:

  • ZAI_API_KEY for z.ai (GLM)
  • GEMINI_API_KEY for Google Gemini

Output handling

Show the model's response verbatim. Surface its verdict (if any) at the top of your reply so the user sees it without scrolling. If it's a code review and the verdict is BLOCKER or NEEDS WORK, list the cited issues clearly.

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. 3d ago First seen · 60 lines · 70 tokens per session scan A ced1c2cea8c7

Subscribe to this mod's changes

consult-second-opinion is a skill published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 560 once invoked, about $0.0003 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens