Claude Code Mods

nullphase-net/enfurbish

Ambient language learning. Hooks weave vocabulary into ordinary Claude Code sessions — stale items you are forgetting, a small budget of new terms drawn from the work itself, and anything you use unprompted recorded rather than taught back at you. The ledger is a markdown file you own, written by a CLI rather than by hand.

S-kkipie/pastor

El centro de mando de tus agentes de Claude Code en el móvil: sesiones de todas tus PCs, permisos, git, terminal, previews, navegador en vivo, rutinas y un agente por WhatsApp

matecocidocontortafritas/growth-lab-mods

/pedidos: panel con los pedidos de hoy de tu Tiendanube y cuánto vendiste, sin gastar tokens

Firefade0329/claude-code-pet

Maid mascot in the prompt band: reacts to Claude state, shows CTX/5H/7D usage, keeps an affection counter.

LupusMalusDeviant/mod-box

A desktop pet and little companion on the Windows desktop, always on top and in front of borderless games: a cardboard box or one of twelve figures (cat, dog, fox, bunny, hamster, owl, penguin, frog, axolotl, dragon, robot, ghost; cat, dog and bunny in nine coats). It says in a speech bubble what Claude is doing and sums up each answer; Claude's questions, Next Steps' suggestions and reply options are buttons in the bubble, and with typing on a hotkey opens a box to answer without leaving the game. A click on the pet shows the last answer in short; an unanswered bubble shrinks to one line. Optionally one pet per active session, each with its own figure and a name tag, asleep while its prompt cache is cold; it warns before the cache goes cold, and its menu keeps the cache warm (1 h, 3 h, always, off). Other mods at the pet: a command Blast Radius holds, a task from Human in the Loop (done or an option with one click) and the CI Watch result come up in the bubble, and stand in short beside its name. Built once with the C# compiler that ships with Windows and signed when a signing script is there. /pet shows it, /pet cat calico picks a figure, /pet stop sends it off.

EmmaNguyen/mod-pet

Tells the floating Mochi app what each Claude chat is doing

ajbarea/techne

Opt-in Claude Code hooks: refuse attribution lines in commits and PRs, refuse staging COMMITS.md, refuse commits and pushes that carry a secret, refuse issue and PR bodies past their length budget, warn on commits in a main checkout, refuse a subagent call that would silently inherit the session's model, restart idle sessions onto an updated Claude Code, and route work to cheaper models while the usage allowance burns too fast.

nicopalazzo/pin-mods

Keep steps above the prompt while the chat scrolls: a Pin button under any reply, or /pin. Show the original reply, find it in the chat.

nicopalazzo/pin-mods

Plan C test: ask Claude to pin a short checklist above the prompt. Claude picks the lines; you tick them off.

visiblesoft-es/claude-mods

Pins the step-by-step procedures Claude gives you above the prompt, so you can follow them while the conversation moves on, and stacks the ones that interrupt them

chrisluo5311/Pixel-Play

A pixel-art music player pane that streams a playlist through mpv

cglremrcn/pixlings

A tiny pixel creature that lives above your Claude Code prompt. It counts down your prompt cache and guards it on model switches, wakes Claude when your usage limit resets, brings a helper for every subagent, makes sound on Windows and Linux, yelps before risky commands, rolls its eyes at "You're absolutely right", and brings back your old /buddy.

zhitongLIU/claude-code-mods

/plan-control opens a live map of Obeya tickets and local plans: dependencies, the interfaces each provides and consumes, mismatches, pull requests. One map per session.

eddundead/claude-poker

Claude Poker — 8-bit Texas Hold'em in a Claude Code side pane: 1–6 AI opponents, three skill levels, win odds, 10 languages. By Edd.

sneycampos/claude-pomodoro

Button-first Pomodoro timer above the Claude Code prompt: one-click focus blocks, a live countdown band, break reminders and a config pane.

emilthaudal/claude-plugins

Draws a PR card under git push and gh pr commands: commit graph by branch, merge state and conflicts, CI checks; plus the PR's status above the prompt

void2610/dotfiles

現在ブランチの OPEN PR を常駐監視し、CI fail / Copilot レビュー到着でセッションを起こす (pr-create の background スクリプト置き換え)

sfrodilla/claude-code-mods

Reviews unpushed commits against REVIEW_GUIDELINES.md before Claude runs git push

edupegoretti/fluidz-mods

Antes do Claude commitar ou enviar: bloqueia segredos (GitHub, AWS, OpenAI, Anthropic, Brevo, Bitrix24, Meta…), arquivos de segredo, conflitos e arquivos grandes; no push roda typecheck, lint e testes em paralelo e devolve o erro ao Claude para corrigir.

Entwining/mods

Lets Claude Code auto mode run the steps of the task you gave without the classifier: a model judge allows what is reversible or what you explicitly asked for

enes/proctree

Live process tree, RAM and CPU of your Claude Code session and everything it spawns

ewxgwy1987/claude-code-progress-board

A pane showing every task and subagent as a colored progress bar with percentage and estimated time left

Bocskay-Botond/claude-code-mods

A folder-tree card beside the status bar listing your projects by category, read from ~/.claude/project-box.json.

RenegadeRocks/claude-mods

A Links pane on the right of Claude Code listing your project's artifacts and important links, read from dashboard/links.json in the project; /links prints them.

tripolskiydigital/claude-tabs

Pinned projects as horizontal tabs in Claude Desktop's Code tab (macOS): project icons, live session status, one click to a project's last session. Reads Claude Desktop's local session records and Claude Code's running-session files; no network. Optional ⌃1–9 shortcuts build and run a small launchd helper (off by default).

Nasrallah-Adel/claude-prompt-cache-control

Prompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and setting) and corrects itself from request timing. /cache opens a per-turn table. A Clear button writes a handoff brief from the transcript with a cheap model, runs /clear, and sends the brief to the fresh conversation.

kadaliao/claude-mods

English under each prompt: a translation when you write in another language, corrections or other ways to say it when you write in English, and a vocabulary book to review them. Or the same in Japanese

tomikng/prompt-forge

Spends your Claude Code tokens where they count: moves a new task into a fresh session (a new terminal window, or its own git worktree) instead of dragging a long conversation along, and runs small, clear tasks on Sonnet.

Ron-Nefyodov/prompt-library-mod

Save, search and reuse your best prompts

AdamCaviness/prompt-marks

Marks your prompts in the transcript with a colored bar and tinted row, and jumps between them with Option+Up and Option+Down

AJclemendor/my-mods

Prev chat and Next chat buttons that jump between your prompts and leave the transcript still at its end.

matr1xp/local-mods

Two-line status above the prompt: model, directory, git branch, context fill and rate-limit usage

cfrs2005/claude-prompt-translator

Translate prompts before Claude Code using your own OpenAI-compatible API.

brunolca/claude-plugins

Flag a project for prototype mode: no git worktrees, Claude edits the current checkout directly. Works for background jobs too.

maxsoldev/pstash

Stash prompts for later and pop them back into the input box. Instant, no model call.

gfsaaser24/claude-code-mod-examples

Pulse: a Node sidecar feeds a live CPU, memory and git pane

magnuswiderberg/claude-code-mods

Tile puzzles of Obol's shades art while your agents work: swap the pieces until the picture is whole.

wukonigcom/quanta-costa

Quanta Costa: your Claude subscription period, weekly limit with a pace forecast, session cost and plan value, as bars right above the Claude Code prompt.

geethasagarb/query-guard

Stops risky SQL and dbt commands in Bash and asks you before they run.

bilal-psd/skills

ask_many: the built-in question dialog for more than 4 questions

FrogAi/Xenopus

Queues messages sent while Claude is working and sends them one per turn, like Codex

crebot51/jack-mods

在模型名右边加一个 按钮，点开面板用点选代替手打斜杠命令，并可直接点选修改 /config 设置；支持中英文界面

oobg/claude-code-mods

전역과 로컬(저장소별) 프리셋 문구를 입력창 위에 버튼으로 표시합니다. $4처럼 입력하면 해당 문구로 바뀌고, 문구를 클릭하면 바로 보냅니다. /스킬도 실행할 수 있으며, $e로 편집 화면을 열거나 $0으로 프리셋을 한 줄로 접을 수 있습니다

kuan0808/cliproxy-kit

Account, quota, context and cache cards above the Claude Code prompt, with handoffs and a warning before a turn rewrites the prompt cache; quota and routing come from CLIProxyAPI with the quota-pilot plugin

ohjohnnyoh/claude-mods

Реакции на сообщения, как в мессенджере: на любое сообщение Claude, не прерывая его работу; метки → и реакции Claude на твоих сообщениях

tanujarun/it-speaks

Reads Claude's replies and your prompts aloud on request, with the open-source Kokoro TTS model.

LupusMalusDeviant/mod-box

Holds a whole-file Read (no offset/limit) of a file above the limit, a lockfile, minified code or a source map, and the same via cat, type or Get-Content in the shell; tells Claude the size, a token estimate and a better way (Grep, offset/limit). A second try at the same file goes through, and so does a Read with allow_large. Claude Code itself stops only at about 25,000 tokens.

alex4o/system-one-mods

On a full Read of a big source file, a System One model (Jev, or the open-source decider) decides per function/method/const whether to include it; the rest become stubs.