Claude Code Model Router Mods

Use ChatGPT, Cursor, Zen, Antigravity and Grok models in one Claude Code session

Set reasoning effort, subagent model and skill for every prompt you type

Assign a model and effort to five subagent roles and inspect routing

Runs data-grounded biblical study, exegesis and passage analysis inside Claude Code

Route each turn to a Claude model picked by TypeSafe's Jev

Route each session to Haiku, Sonnet, Opus or Fable from the first prompt

Routes each task to the smallest sufficient loop of workers

Hand tasks to cheaper models through a local proxy from Claude Code

Run search-only subagents on Haiku instead of your main model

Show each turn's effort and model, and route light prompts to low effort

Start a prompt with + and that turn runs at max effort

Ask a council of models about a hard problem and write one verdict

Pin subagent models to a routing policy and log every subagent spawn

Routes subagent models down the capability graph and tracks per-agent token budgets

Switch Claude Code settings profiles from a sidebar, one press, every change undoable

Rate each prompt with a small model and run the turn at matching effort

Pick cheaper models for subagents that name none, and show what each one cost

Move context compaction off Claude and onto Gemini to cut Claude usage

Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, Kimi, any model OpenRouter routes to, plus codex, antigravity, grok, kimi and…

Generate and edit images using Google Gemini, OpenAI GPT Image, xAI Grok Image, and OpenRouter APIs

Claude Code의 명령어 설명과 /config 설정 항목을 한국어로 표시합니다

Jev Gate in one plugin: the orchestration gate, the extractive compactor and the Jev effort and model router

Runs long Claude Code jobs overnight within your usage limits: pauses just before the 5-hour or weekly limit, resumes the same session after the…

Talk to OpenAI Codex from Claude Code: live peer messaging over a local pipe, plus headless delegation (ask)

Each Claude subagent's model and effort in the native agent list, beside its task

Open-source Claude Code plugin — 54 MCP tools and 37 slash commands, hybrid LLM summarization (Anthropic Haiku 4.5 default + ONNX offline + local…

After a turn that edited files or ran commands, Haiku lists the choices Claude made that you did not state

Picks low, medium or high effort for each prompt, keeping the prompt cache warm

A prompt-cache countdown in the prompt footer, beside the model and effort: how long until your next message has to re-cache the whole conversation

Console: limits, cache timer + alert, model/effort pickers, side pane

Session dashboard under the prompt: usage limits, context, cost, model, effort, session stats, git status, file changes, and an animated Clawd

Difficulty-based routing for Claude Code

Picks low/medium/high/xhigh effort per prompt for Opus/Sonnet/Haiku 5.5+ and Fable/Mythos 5.1+ by how uncertain and costly the work is, raising it…

Make your Claude Code usage go up to twice as far

Routes each Claude Code turn to the model and effort TypeSafe's Jev picks, weighed against what a switch costs, and compacts with Jev instead of a…

Sets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent conversation context

Pixel-art progress bar with the Claude mascot and a side panel that turns your subagents into a crew of characters (developer, artist, researcher…

Watch Claude Code's background work: subagents, Codex jobs, shells, monitors, cron jobs and workflows

On every prompt, asks Jev which skills fit, shows them ranked above the prompt, and passes them to the model as suggestions

One local conversation archive for Claude Code, Codex, Pi and dsh harness