Tula is an open-source collection of OpenClaw skills, configurations, and patterns designed to transform a general-purpose AI agent into a personal health intelligence assistant.

MCP server that wraps the xAI Grok CLI. Lets Claude Code, Cursor, Cline, and any MCP host use Grok as a peer code reviewer, adversary, and second-opinion consultant.

A cross-agent consultation bus: a CLI coding agent asks a different-provider agent for a second opinion — one advisor, or a multi-agent council that audits code and verifies every finding against its file:line. 12 agents: Claude, Codex, Gemini/agy, Grok, OpenCode, Hermes, Kimi, Cursor, Kilo, Cline, Goose, Pi.

Independent, evidence-first second opinions on decisions, docs, research, data, and code. A rival-provider AI reports read-only findings; the host verifies and reconciles them, and escalates only the genuine disputes that need a human.

Claude has friends. On the calls that matter it asks AIs from other families — Gemini, a fresh-eyes second Claude, optionally GPT — who catch the blind spots one model can't see alone.

Claude Code skill for cross-model review. One command packages files + prompt for ChatGPT Pro deep reasoning.

Multi-model advisory board for Claude Code — get second opinions from Codex and Gemini

Bridge Claude Code and Codex on the same machine — second opinions, brainstorms, and direct MCP tool access between two AI coding agents.

Claude Code skill: hand code/plans to Codex (codex CLI) for an independent second-opinion review

Secure orchestrator for MRI second opinion. Clinician-in-the-loop workflow: Ingest -> QC -> AI Draft -> Mandatory Review -> Export. Features a state-machine API (TS), Python worker loops, and DICOM SR/FHIR support. Research Use Only (RUO). Designed for security, auditability, and verifiable AI-assisted diagnostic pipelines.

Claude Code plugin: a four-command suite (/agy, /agy-review, /agy-debug, /agy-panel) that fronts Gemini, Claude, and GPT-OSS models through the Antigravity (agy) CLI for inline second opinions, diff review, debugging, and cross-model panels.

Use Google Gemini (3.x Pro/Flash) as a headless tool, builder, or judge from Claude Code — via Google AI Pro OAuth, no API key.

Claude Code skill implementing Andrej Karpathy's LLM Council methodology. Runs any decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor), anonymous peer review, and chairman synthesis. Outputs HTML report + full markdown transcript.

Automatic code review for Claude Code, powered by OpenAI Codex CLI. Like having a senior engineer review Claude's work.

Claude Code plugin: Gemini as second-opinion assistant (validator, challenger, researcher, summarizer subagents + auto-trigger hooks)

Claude Code skill for OpenAI Codex CLI (GPT-5.4). Three modes: Quick, Analysis, Delegated. xhigh reasoning by default.

Cross-model SDLC review council for Claude Code — Claude drafts, OpenAI Codex/GPT critiques as 17 SDLC experts. Two-axis model routing, bounded debate, hardened read-only engine, structured verdicts.

🥊 Decide between 2-4 ideas with a structured tournament of independent fresh-context AI judges. Auditable, evidence-based verdicts. Claude Code skill.

Multi-model orchestration skill for Claude Code (babel + cdx-sol + agy): 5-model debate/build-debug/acceptance-gate pipeline

Codex skill for a fresh critical second-opinion review, fix, and re-review loop.