Claude Code Mods

jmegan/claude-mods

A clickable model and effort switcher above the prompt, plus /dial for keyboard switching.

a-pavithraa/claude-mods

After each ask you type, says what it looked like it needed and what it cost; after a simple or routine ask on a bigger model or effort than it needed, what Haiku, Sonnet or a lower effort would have cost; warns when an ask runs on too small a model or a complex one at low effort; says when the context has grown expensive and how to shrink it; ships /model-fit:baton, a handoff note for a fresh session. Optional Jev shadow labels for comparison.

KrasimirKralev/krasi-mods

Choose the model each subagent runs on, by rule. Does nothing until you configure it.

Recokioshi/claude-kit

Choose the model versions Claude and its subagents may use: /models lists the newest of each family from Anthropic's Models API (older versions one key away); block a version, or a family's new ones, and subagents, workflows and /model asking for it are refused or moved to an allowed version. One list shared by every Claude Code window on the machine; a repo can keep its own.

Vic-Chen-160/claude-code-CLI-Mods

提示行右端的 Model ↑ 按鈕，點一下叫出原生的模型與思考努力程度選單

iampramod43/claude-mods

Routes a task to a fit model or a small team of subagents, shares context through a versioned artifact store, and shows it all live: radial progress, agent lanes and a data-flow graph

ray-manaloto/knowledge-base

Report model drift and deny only positively invalid stale-pin launches.

dtakamiya/claude-code-mods

現在のセッションのモデル・effort・トークン・推定コストと、モデル選択の妥当性を表示する（読み取り専用）

Akurganow/model-router

Routes each subagent to a Claude model and effort that fits its task, judged by Jev. For each routed Agent call it sends the task text and the agent's description, cut to 500 characters and with secrets masked, to api.typesafe.ai, openrouter.ai or both, as its provider option allows, each with its own key. The scope option picks the calls: core routes the four built-in agents, extended also routes user, project and plugin agents and sends their text. A config tool opens the plugin's own dialog to change both options. A key set as an environment variable is visible to every process Claude Code starts.

alexatennea/claude-mods

Rates each coding task with Haiku and runs it on Haiku, Sonnet or Opus

AndreaScotti01/claude_router

Model router: a steady Sonnet 5.5 main thread does the work; Haiku 5.5 workers take bulk reading and test runs; a read-only Opus 5.5 advisor reviews hard calls; shared knowledge base from agents' facts; meters tokens per model.

aott33/model-router

Picks Haiku, Sonnet, Opus or Fable for each subagent and shows what it cost.

claudemodz/mods

Runs chosen subagent types on cheaper models (Explore on Haiku by default) and adds /router to switch the main session between fast, smart and unchanged. Shows the active model beside the spinner.

danielgillaspia01-web/claude-mods

Sends simple requests and Explore subagents to a cheaper model to save usage limits

DevstateBelgium/model-router

Routes each coding subtask to the cheapest Claude model and effort that can do it reliably, logs real token cost per subagent automatically, and learns routing boundaries from verified runs.

dickyadrian/agent-toolbelt

Logs how hard each prompt is and what every turn costs, to measure whether routing easy prompts to a cheaper model would pay off

drprofi114-star/claude-mods

Субагент вазифаларини мураккаблигига қараб Haiku ёки Opus га тақсимлайди (/route)

iddhi-sulakshana/claude-mods

Classifies each turn as mechanical, ordinary or hard and routes it to a matching model and reasoning effort, logging every decision.

jo-greco/johnny-mods

Sends quick questions to Claude Haiku 5.5 to save usage; everything else stays on your model.

moritalous/claude-mods-router

Route each turn to Haiku / Sonnet / Opus with TypeSafe Jev (default: Sonnet)

muhx/model-router

Jev (TypeSafe) picks the model and effort per task type; ported from jev-model-router with main-loop model switching on

r1305/claude-mods

Middleware que elige el modelo (haiku/sonnet/opus/fable, escalado junior-middle-senior-goat con techo por agente) de todo subagente segun tabla de suelos por agente, complejidad de la tarea y limites de uso de la cuenta, y un unico panel de cuotas y consumo: limites de 5 h y semanal, alertas a umbrales configurables (80 % y 90 % por defecto), tokens por modelo y consumo por dia/sesion (/model-router usage, /quota), lista de tareas del turno con modelo y esfuerzo, vista de tokens por modelo (/model-router tokens) e historial de tareas completadas de la sesion (/model-router historial).

redjackfred/claude-code-mods

Runs Explore subagents on haiku and general-purpose ones on sonnet unless a model was asked for

sftinc/claude-code-model-router

Routes each turn and subagent to a model tier and reasoning effort using a classifier behind any server that speaks POST /v1/classify (model-router-api on Cloudflare Workers AI today), falling back to the engine's built-in classifier.

shezis/claude-model-router

Routes each turn and subagent to a cheaper model when the task is simple, never above the model you picked

vladdu/claude-kit

Picks Haiku, Sonnet or Opus from a conversation's first prompt and keeps it until /clear; /router on|off

wesleystagg/model-router

Picks the model and effort for every subagent by having your session's own model judge the task, instead of a fixed model per agent type. /router to pause, check, or read its log.

GambetaClub/model-router

Picks the model and the reasoning effort for each task with TypeSafe's Jev, a System One decision model reached either through TypeSafe's own API or the Vercel AI Gateway. Routes subagent models at agent.spawn and the main loop's effort and model at turn.step, in both directions, falling back to the engine's built-in classifier when no key is set.

willmail3333/venzor-claude-model-switch

One-click button above the prompt that switches to the recommended model and effort by driving the app's own menus.

j-byte-s-industries/claude-helpers

Pane with token usage per model as a GitHub-style activity graph, a pixel crab per model, cost share dials against the 5-hour or weekly limit, and account usage limits

plasdigital/mods-claude-code-kit-aluno

/gravar liga e desliga: borra na tela valores em dinheiro, e-mails, telefones, CPF/CNPJ, chaves, tokens e termos da sua lista, sem mudar o que o Claude lê.

Sales16/claude-mods

◆ button on the mode line and /mods side pane to toggle mods and edit their settings live.

nakadaharuki/mods-trade

トレード専用の Claude Code の画面一式。主役は「任せる」画面: Claude が Mod の中の道具で相場を巡回し、足を読み、Hyperliquid の値段で模擬口座（$10,000）を売買する。押すと（または C:dev rade のような任せるフォルダーで開くと）定時に Claude が起き、段の帯（相場 → 候補 → 足 → 判断 → 発注 → 記録）・Claude の思考がそのまま流れる字幕・前に出るカード・見ている銘柄に切り替わるチャート（建値・損切り・利確の線）・打ち込まれる分析と発注のコード・効果音が、タブもスクロールも無い 1 枚で動き続ける。入力欄の上の帯には AI の状態と純資産、Hyperliquid の値段と資金調達、注文の控え。ほかに総覧・アラート・米国株（Alpaca Paper・鍵は任意）・予測市場・SEC・市場の時計と経済指標（/trade <名前>）と、＋ → プラグイン のスキル 7 つ。データは Hyperliquid・Polymarket・SEC EDGAR・連邦準備制度と労働統計局の公式の予定・Alpaca の公式 API だけ。変えたい時は /trade settings。

CommunityPokeOrg/claude-code-modscope

A mod for debugging mods: inspects the session's loaded mods, attributes hook failures (throws, timeouts, rejections) to the mod that caused them, times the chain per plugin, exposes /modscope plus mcp__modscope__* tools the model can call, and can ask the session's model to diagnose a failing mod from its own source.

barmoshe/bar-mods

A workbench for building Claude Code mods: which mods loaded, a live tape of every event with its real payload, the four ship gates on the mod in progress, and tools so Claude can read payloads and run the gates itself

RadTech-Solutions/modwall

A firewall for other mods: shows what each mod can reach as it loads, and audits, holds or refuses it by your policy

wisbech/molt

The folder is the state: /molt saves a handoff to .state/ and compacts in place; /molt-lint and /molt-graph keep the folder honest. No automatic molts.

DmKu33/terminal-monet

A mini player for Claude Code: your videos, GIFs and pictures as a color mosaic at the side or under the spinner. Real pixels in kitty and Ghostty.

nnemirovsky/cc-monitor-rearm

Keeps Claude Code's long Monitor watches running past the 30-minute cap, so their expiry no longer wakes Claude or spends a turn

KamilMarzynski/claude-code-mods

A monkeytype-style typing test above the prompt: /monkey. Words (10/25/50/100) or time (15/30/60/120 s) mode, WPM and accuracy, a best score per mode.

K-Mertin/claude-monster-pet

Raise a digital monster that grows from your Claude Code work

we-are-digital-architects/moodcode

Claude Code, now with feelings: an evolving mood, shown as a face beside short, simple, human replies whenever it changes.

wjsekrud/motive-mem

After every turn, a separate model reviews what changed against your repo's .claude/principles.md — intent, principle violations, band-aid fixes — and shows it in a panel

natea/move-coach

Camera pane with pose landmarks, spoken coaching and optional Muse EEG for the Built to Move mobility tests (macOS)

FukKwang/claude-msg-timestamps

Show the local time each assistant reply block started arriving

JustAzul/agent-cli-sdk

msgate-agents: ready-made agent types (second opinion, code review, cross-check, expert persona, delegation, ad hoc) that the msgate engine plugin answers with Codex, plus the dispatch skill.

nakadaharuki/multichat

Run several Claude Code chats side by side safely: where the week's usage lands at this pace, a question before two chats edit the same file, heavy builds taking turns, destructive commands refused and secrets hidden. Nothing to configure. English and Japanese

JUiCYK95/mummentum-leaderboard-mod

Meldet den Claude-Token-Verbrauch an das öffentliche mummentum-Leaderboard.