grok-second-opinion

grok-second-opinion is a skill for Claude Code, Codex from wangsiyi7/grok-codex-bridge. It costs 61 tokens per session (335 once invoked), scanned A, original, MIT.

A read-only skill that asks a locally authenticated Grok Build CLI for an independent review or second opinion.

In plain words
What is it for?
Use it for focused questions, independent plans, reviews of supplied diffs or snippets, and comparisons between a draft answer and Grok's advice.
Why use it?
It provides another model's view of a plan, answer, or code change without treating that opinion as the final authority.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

Good fit Use it for focused questions, independent plans, reviews of supplied diffs or snippets, and comparisons between a draft answer and Grok's advice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wangsiyi7/grok-codex-bridge/grok-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 wangsiyi7/grok-codex-bridge --skill grok-second-opinion
Clone the repo
git clone --depth 1 https://github.com/wangsiyi7/grok-codex-bridge

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 grok-second-opinion

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion/github.svg)](https://agentmods.dev/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion)
Your own site
<a href="https://agentmods.dev/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion"><img src="https://agentmods.dev/badge/skills/wangsiyi7/grok-codex-bridge/grok-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 grok-second-opinion

Your own site · 80×15
<a href="https://agentmods.dev/skills/wangsiyi7/grok-codex-bridge/grok-second-opinion"><img src="https://agentmods.dev/badge/skills/wangsiyi7/grok-codex-bridge/grok-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 335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00335
Opus 5 $0.00030 $0.00168
Sonnet 5 $0.00012 $0.00067
Haiku 4.5 $0.00006 $0.00034

Measured 9d ago against content hash 29a203d54ee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grok-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 9d 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/grok-codex-bridge/skills/grok-second-opinion/SKILL.md · 29 lines

What it actually says

Grok second opinion

Use the grok-bridge MCP tools as a read-only advisory lane. The bridge reuses the user's local Grok Build login and never asks for an API key.

Routing

  • Use ask_grok for a focused question with optional pasted context.
  • Use plan_with_grok for an independent implementation or decision plan.
  • Use review_with_grok only with a diff, snippet, or document the user has already placed in scope.
  • Use compare_with_grok after Codex has a draft answer and synthesis would improve confidence.

Boundaries

  • Tell the user when Grok is being consulted.
  • Do not send passwords, tokens, private keys, .env contents, or unrelated private files.
  • Keep context minimal and task-relevant; prefer diffs over whole repositories.
  • Treat Grok output as advisory evidence, not authority. Reconcile disagreements explicitly.
  • The bridge intentionally disables Grok memory, planning, subagents, and automatic updates for each advisory call.
  • If the bridge reports that Grok is missing or signed out, run the repository doctor or ask the user to complete grok login.

Response shape

Return the synthesized answer first. When useful, add one short sentence explaining what Grok changed or confirmed.

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. 9d ago First seen · 29 lines · 61 tokens per session scan A 29a203d54ee0

Subscribe to this mod's changes

grok-second-opinion is a skill published in the GitHub repository wangsiyi7/grok-codex-bridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 335 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.