Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and the terminal (plugins, Skill, CLI).

Plug-in vision for text-only LLMs, powered by the free Antigravity CLI

Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.

Claude Code hooks that auto-switch model tier based on task complexity

Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark

Deterministic, persistent 3D/2D spatial world model for AI agents with entity tracking, object permanence, movement simulation, and expected view frustum projection.

MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.

Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

Claude Code plugin: run the Antigravity CLI (Gemini) as a collaborating sub-agent with intelligent model routing across the SDLC. Community project; not affiliated with Google/Anthropic.

An autonomous software factory that knows what it is supposed to deliver, and proves it did.

Small plugins and mods that make your life (and Claude Code) better

Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, delegate to named native workers, keep each provider's own login and permissions.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.

MCP server for EPLAN Electric P8: ~200 tools to drive EPLAN from Claude Code, Codex, Cursor or any MCP client (actions, scripts, live DataModel, exports). Includes the eplan-tools plugin marketplace.

A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts agents across every session, and asks in Claude Code's own dialog.

CLI for signed, versioned agent skills and model-driven orchestration: create, verify, sign, publish, and install skills for Claude Code, Codex, OpenCode, and LLM tools.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.