AI Review Local — AI skill for Claude Code
Run AI code review locally using Codex CLI or OpenAI API before opening a PR.
How to install AI Review Local
Installs to ~/.claude/commands/igerber-diff-diff-ai-review-local.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/igerber/diff-diff/HEAD/.claude/commands/ai-review-local.md -o ~/.claude/commands/igerber-diff-diff-ai-review-local.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Review Local does
description: Run AI code review locally using Codex CLI or OpenAI API before opening a PR argument-hint: "[--backend auto|codex|api] [--context minimal|standard|deep] [--include-files ] [--token-budget ] [--force-fresh] [--full-registry] [--model ] [--timeout ] [--dry-run]"
Local AI Code Review
Run a structured code review using either the **Codex CLI** (agentic, matches CI quality) or the **OpenAI Responses API** (single-shot, faster). Reviews changes again
Alternatives in AI
- CLI 代理 API — English 中文 一个为 CLI 提供 OpenAI/Gemini/Claude/Codex 兼容 API 接口的代理服务器 19k ★
- Codex — openai-codex Adversarial code review, Codex CLI integration, cross-model analysis 9.6k ★
- Rb Setup — First-time setup 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
GPT Cc
Local Python gateway that lets Claude Code run on OpenAI Chat Completions-compatible models or a locally authe
Codex Plan Review
Adversarial Codex review of a PLAN or design (not code) via the local Codex CLI. Read-only second-model challe
Codex Model Router
Codex 多模型路由:在 Codex Desktop 使用 Claude、第三方 API 和自定义模型。Local LLM proxy for OpenAI Responses / Chat Completions &
LLM Bridge
Local OpenAI-compatible LLM API gateway for Google Antigravity (AGY), multi-account Gemini, Claude Code and Co
Which Model
Which model actually answered your coding agent, from your own machine: Claude Code and Codex transcripts read
Peek API
Discover internal APIs from any website. Captures XHR/fetch calls, extracts auth headers, outputs structured e
Related Agents
Lmstudio Local
A locally-hosted model served through LM Studio's OpenAI-compatible API,
Codex Debugger
Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA
Codex Orchestrator
CLI tool for delegating tasks to GPT Codex agents via tmux sessions. Designed for Claude Code orchestration wi