0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It directly addresses the structural blind spot of single-model agentic coding by ensuring the model that writes the code never approves its own work, reducing correlated errors and self-assessment bias.
Who it is for
- Developers using Claude Code who want multi-model oversight
- Teams working on high-risk or correctness-critical code changes
- Users of Agent Skills hosts (Cursor, Copilot, Gemini CLI) seeking external review loops
- Engineers interested in structured, verifiable AI coding workflows
Use cases
- Adding a new feature with acceptance criteria that are checkable by an independent reviewer
- High-risk changes (auth, payments, data migrations) where a second set of eyes is essential
- Research and investigation tasks that require web searches but no code changes
- Integrating multiple frontier models in a single coding session for better quality
Strengths
- Role separation: Claude plans/reviews, Sol implements – the reviewer never wrote the code
- Verifiable acceptance criteria: each criterion is a runnable command, not prose, so the reviewer can independently check
- Capped correction loops (max 2 rounds) prevent infinite token burning while allowing targeted fixes
- Deliberate design choices: no auto-invocation, no trusting the implementer's report, read-only research mode
Considerations
- Slow execution: xhigh reasoning can take 8+ minutes for a one-file change
- Requires two separate subscriptions (Claude Code and a ChatGPT plan with Codex access)
- Only works in git repositories because review relies on diff isolation and checkpointing
README quick start
/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 |
Description
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.
Related repositories
Similar projects matched by category, topics, and programming language.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.