Claude Code Model Router Mods

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

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

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

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…

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

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

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

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

Time awareness for coding agents, in Claude Code and Codex: in Claude Code, stamps every message with the local time and how long the turn took; in…

Clawd, a token-saving assistant: trims noisy tool output and pasted logs before they fill your context, tells you when to compact (and does it in one…

入力欄の上に使用量メーター（ctx・5h・7d・モデル別の週枠）と effort の切り替えを出す

A view-only pixel office pane showing which agents (lead, subagents, Codex, Cursor) are working, with your checklist and this branch's PR

Claude·Codex 구독 계정별 남은 한도 띠 + 클릭 한 번 계정 전환(같은 tmux 칸에서 대화 이어가기)

Turns voice-mode dictation into clean, clear prompts: detects which prompts you spoke, then has Haiku remove filler, apply self-corrections and…

Answers permission prompts for you: regex layers allow routine tool calls and always ask on pushes to protected branches, and haiku judges the rest…

Paste a link with a short question and Claude's answer opens with a verdict for your projects: use it, later or skip, the effort, the cost and one…

Routes each prompt to Haiku, Sonnet or Opus by how hard it is

Enhance button above the prompt: Sonnet sharpens your draft using the recent conversation

Your Codex pet, living above the Claude Code prompt: it works while Claude works, waits when you are needed, and celebrates when a turn is done

Second opinions inside Claude Code: GPT as fresh eyes when you go in circles, Codex acceptance of every handover, and Codex+Claude review of each…

A Claude Code mod for Eunuch Mode: while the skill is on, the palace adviser stands above the prompt in pixel art, posing for what the agent is…

A live monitor for Claude Code: model, effort, context, 5h/7d usage limits, task progress and a subagents panel, in one responsive card

Side panel that suggests the right Claude model (Haiku, Sonnet or Opus) for each task, with pixel-art characters, a 6-second choice and a one-off…

Routes every message to the cheapest model that can do it (Haiku, Sonnet or Opus) and shows three pixel workers, their cost and your savings in a…

On demand via /rewrite: classifies a prompt into role + task personas, adds recent web context, and rewrites it with Haiku for review

Claude가 한 일을 전부 일러바치는 Claude Code mod: 상태줄(모델, effort, 요금제 한도, 세션 작업량), 대시보드 패널(/snitch, 에이전트 현황, 변경 파일별 변경 이유, 커밋별 누적, 전체화면이면 우측에 자동 표시)

Picks the model and reasoning effort of every subagent: a recommendation by task kind, a band above the prompt, and a saved default that wins

A /usagemeter pane with cost, tokens and plan limits across Claude Code, Codex, OpenCode and Antigravity, read from local history and a CLIProxyAPI…

Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt (new, resumed, forked), resolved model…

Buddy is back: the retired /buddy terminal companion as a Claude Code mod, with new sprites and Haiku writing its lines

Trajectory segmentation for long Claude Code sessions: every N steps a model of your choice (haiku by default) reads the previous segments and the…

Classifies the user's prompt with Haiku against a few yes/no questions in one call and attaches a rough, non-binding hint for the main agent

Progress bars from your todo list at zero extra tokens, a router where you pick the model and effort for quick, normal and hard prompts, and a…

/flow 面板查看和停止本会话派出的 Codex 任务，任务跑满 15 分钟时提醒主 Agent 排查

An always-on companion for Claude Code, after OpenAI's dots: a named avatar that keeps standing responsibilities, runs them on schedules in the…