为什么值得关注

它直接解决了单模型代理编码的结构性盲点——确保编写代码的模型永远不会批准自己的成果，从而减少相关误差和自我评估偏差。

适合谁使用

希望获得多模型监督的 Claude Code 开发者
从事高风险或正确性关键代码变更的团队
使用 Agent Skills 主机（Cursor、Copilot、Gemini CLI 等）并寻求外部审查循环的用户
对结构化、可验证的 AI 编码工作流程感兴趣的工程师

典型使用场景

添加带有可检查验收标准的新功能，由独立审查者验证
高风险变更（认证、支付、数据迁移），需要第二双眼睛监督
需要网络搜索但不涉及代码更改的研究和调查任务
在单个编码会话中集成多个前沿模型以提高质量

项目优势

角色分离：Claude 规划/审查，Sol 实现——审查者从未编写代码
可验证的验收标准：每个标准都是可运行的命令，而非散文，审查者可独立检查
上限为两轮的修正循环，避免无限消耗令牌，同时允许精确修复
精心设计的选择：无自动调用、不信任实现者的报告、研究模式只读

使用前须知

执行缓慢：xhigh 推理模式下单文件变更可能需要 8 分钟以上
需要两个单独订阅（Claude Code 和具备 Codex 权限的 ChatGPT 计划）
仅适用于 git 仓库，因为审查依赖差异隔离和检查点

README 快速开始

/sol: Claude plans, Sol implements, Claude reviews

Two frontier models, one job each. The model that wrote the diff never grades it.

A Claude Code skill for multi-model AI coding: Claude writes the brief and reviews the real diff, while GPT-5.6 Sol writes the code through the OpenAI Codex CLI.

🚀 Get started · Why this exists · How it works · A real run · Setup · FAQ

🚀 Quick start

1. Install. /sol drives the Codex CLI, so that goes first:

npm i -g @openai/codex && codex login

Then the skill, in Claude Code:

/plugin marketplace add ozankasikci/claude-plugins
/plugin install sol

2. Use it. In any repo, on a clean tree:

/sol add rate limiting to the upload endpoint

Claude writes the brief → Sol implements → Claude reviews the real diff and re-runs your tests before telling you it worked.

Other hosts (Cursor, Copilot, Gemini CLI, ~50 more): npx skills add ozankasikci/sol-skill -g. Requirements, a preflight check, and all install surfaces are in Setup. Expect it to be slow: xhigh reasoning took 8m02s for the one-file change documented below.

Why this exists

Single-model agentic coding has a structural blind spot: the model that wrote the code also decides whether the code is good. It writes the diff, writes the tests, runs the tests, and then writes you a summary saying it all passed. You are reading a self-assessment from the author.

That is not a small bias. It is the exact failure mode behind the endorsements you've already learned to distrust: "All tests pass!" (it didn't run them), "Fixed!" (it changed the test), "Done, fully working" (one path works). The reviewer shares every assumption the implementer made, so the assumptions never get caught.

/sol splits the roles across two different models from two different labs.

	Model	Job	Never does
Planner / reviewer	Claude (your Claude Code session)	Writes the brief, reviews the real diff, re-runs the checks i

项目描述

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI — Claude plans and reviews the diff, Sol writes the code. Multi-model AI coding where the model that wrote the diff never grades it.

sol-skill