cross-model-review

cross-model-review is a skill for Claude Code, Codex from hashgraph-online/awesome-codex-plugins. It costs 56 tokens per session (1,051 once invoked), scanned A, original, Apache-2.0.

A second-opinion code review that asks a different AI model to independently inspect a change, then compares both reviews. It focuses on logic, security, consistency, and omissions.

In plain words
What is it for?
Use it for high-risk code changes, large diffs, security-critical paths, database migrations, API contract changes, and unresolved critical review findings.
Why use it?
Having the same model write and review code can leave systematic blind spots. An independent review can expose disagreements or risks in sensitive changes such as authentication, payments, migrations, and breaking API changes.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for gstack. Also seen: built for gstack.

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/hashgraph-online/awesome-codex-plugins/cross-model-review
Any agent
npx skills add hashgraph-online/awesome-codex-plugins --skill cross-model-review
Clone the repo
git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins

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 cross-model-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/cross-model-review.svg)](https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/cross-model-review)
Your own site
<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/cross-model-review"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/cross-model-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 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 $0.00056 $0.01051
Opus 5 $0.00028 $0.00526
Sonnet 5 $0.00011 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured yesterday against content hash 584ebacfaafe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cross-model-review 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 yesterday.

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/Colin4k1024/tsp/skills/cross-model-review/SKILL.md · 108 lines

What it actually says

Cross-Model Review

用途

  • 把"同一个模型既写又审"改成"用不同模型交叉审查,降低系统性盲区"。
  • 适合高风险改动(鉴权、支付、数据迁移)、架构决策、安全关键路径。
  • 作为可选增强层叠加在 multi-perspective-reviewcode-reviewer 之上。

自动检测触发

以下条件命中时,建议 cross-model review(不强制):

检测条件 风险原因
改动涉及 auth/permission/security 路径 鉴权逻辑错误可能导致越权
改动涉及 payment/billing/transaction 路径 资金相关错误代价极高
改动涉及数据库 migration 或 schema 变更 不可逆的数据结构变更
改动涉及 API 契约的 breaking change 影响所有下游消费方
单次改动超过 500 行 大范围变更的审查覆盖率下降
代码审查中发现 CRITICAL 级别问题 需要独立确认修复的正确性

检测到时输出:

💡 检测到高风险改动:{原因}
建议启用 cross-model review 获取第二意见。
是否启用?[Y/n]

默认做法

1. 准备审查上下文

从当前改动中提取:

  • 变更的 diff(精简到相关部分)
  • 涉及的接口契约
  • 相关测试
  • 已有的 review 意见

2. 构建独立 prompt

为第二模型构建独立审查 prompt,要求:

  • 不包含第一模型的审查结论(避免锚定)
  • 只包含代码变更和背景上下文
  • 明确审查维度和期望输出格式

3. 审查维度

第二模型审查聚焦在:

  • 逻辑正确性:边界条件、状态转换、错误路径
  • 安全性:输入验证、权限检查、数据泄露
  • 一致性:与现有模式、命名规范、架构约定的一致性
  • 遗漏:第一模型可能忽略的场景

4. 意见对比

将两个模型的审查意见合并对比:

## Cross-Model Review 对比

### 共识项(两个模型都发现)
- {问题描述}:高可信度,优先处理

### 仅模型 A 发现
- {问题描述}:需要确认是否为真实问题

### 仅模型 B 发现
- {问题描述}:需要确认是否为真实问题

### 冲突项(两个模型意见相反)
- {问题描述}:需要人工仲裁

5. 最终建议

  • 共识项 → 直接按 Revision / Abort Gate 处理
  • 单方发现 → 由 code-reviewertech-lead 确认后决定
  • 冲突项 → 升级给 tech-lead 仲裁

与 model-profiles 的关系

cross-model review 使用 manifests/model-profiles.json 中的模型配置:

  • 默认使用与主模型不同的模型作为第二意见(如主用 Sonnet,第二用 Opus)
  • quality-first profile 下自动启用 cross-model review
  • cost-optimized profile 下默认关闭,仅对 Abort Gate 项启用

触发信号

  • 自动检测命中(上述检测条件)
  • 用户显式要求"第二意见"或"cross review"
  • /team-review 中发现 CRITICAL 问题后的确认审查
  • 架构方案评审中的分歧点

配套约束

  1. 可选能力:cross-model review 永远是建议而非强制,用户可以拒绝。
  2. 成本意识:每次 cross-model review 会额外消耗 token,需要在风险收益之间权衡。
  3. 不替代人工判断:冲突项最终由人类裁定,不依赖模型投票。
  4. 不循环引用:第二模型不审查第一模型的 review 意见,只审查原始代码变更。
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. yesterday First seen · 108 lines · 56 tokens per session scan A 584ebacfaafe

Subscribe to this mod's changes

cross-model-review is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (935 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,051 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 2026-09-05.

Related

Other skills, from other repositories

search

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

taishi-i/awesome-ChatGPT-repositories · 57 tokens

review-prs

Triage open PRs — screen from the diff, delegate the admission judgment to audit-the-list, then merge or close on GitHub. Fire when the maintainer asks to review PRs, process the PR queue, or judge whether a specific PR should be merged.

vinta/awesome-python · 58 tokens

preview-verdicts

Generate the interactive keep/drop verdict preview (HTML page with per-row feedback controls) whenever a prune sweep, batch entry edit, or restructure needs maintainer review before touching README.md — and process the feedback JSON the maintainer pastes back.

vinta/awesome-python · 53 tokens

sprr

Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".

wilsonfreitas/awesome-quant · 60 tokens

bprr

Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.

wilsonfreitas/awesome-quant · 61 tokens

check-mcp-json

Safely review, triage, repair, and merge ToolSDK MCP Registry package JSON pull requests. Use when an agent needs to validate files under packages/, detect duplicate registry keys, classify community PRs, make authorized fixes on contributor branches, close invalid or duplicate PRs, or squash-merge approved PRs.

toolsdk-ai/toolsdk-mcp-registry · 68 tokens