All mods
3,209 mods. Every one passed the check.
- taskcut 0.9.1 Compacts when the work moves on from one sub-task to the next instead of when the context window fills, including in the middle of a long turn. Once the context is past a floor, a model judges each step, reading what you asked for and where Claude has got to but never any tool output, for whether... 7
- taskcut-replaycheck 0.0.0 Benchmark harness, not a plugin to install: records the judge's prompt at every step of a live session, to check the replay against. 7
- md-prompt 0.2.0 Paints Markdown onto Claude Code's prompt box as you type: fenced code becomes a syntax-highlighted card (even before you close the fence), and inline code, bold, italic, lists, task lists, quotes, tables, links and headings are styled. Paint only, your text is never changed. 7
- whats-agent-doing 0.4.3 A small box above the prompt that always says what the agent is doing right now (reading, thinking, writing, running a tool, waiting for you) and expands to show what it has done. 7
- statuspane 1.3.3 A floating status card above the Claude Code prompt — model, effort, context, 5h/week limits, cost, directory and branch, GitHub CI and deploys — with clickable settings and a progress-row API any script or mod can feed. 7
- usage-hud 0.16.4 输入框下方是三列对齐的模型/用量/状态面板,上方是一只会按工具做动作、带着子代理小螃蟹来回走的像素螃蟹(终端;Windows / macOS / Linux);配速预警和螃蟹情绪、每轮收据、一键压缩、额度恢复提醒、子代理看板 (/hud agents)、点档位切换 7
- html-shelf 0.7.1 终端里 Claude 的回复更顺手:文件路径单击打开(HTML、文档 md/pdf/txt/json/csv/Office、图片、音视频、文件夹;脚本只在文件夹里选中不运行);代码块画成卡片,一键复制,单条 shell 命令可 Insert 到输入框;文字里 `反引号` 写的命令也补一张卡片;悬停回复右上角 Copy all;Write/Edit 工具行带 Open;/open [N|list] 打开最近的文件(Windows / macOS / Linux) 7
- compost 0.4.0 mod + skill One software-engineering workflow composted from Matt Pocock's skills, superpowers, pstack, Imbue's blueprint, and autonomous-sdlc: specs with BDD acceptance criteria, tracer-bullet issues in your tracker, builds that fit tests into the existing suite, automatic subagent review, and a turn skill ... 7
- mod-usage 1.0.0 Shows Claude context, 5-hour and 7-day usage as gradient progress bars above the prompt (Claude Code Desktop / VS Code / mobile). 12 languages. 7
- taxi-meter 0.3.4 프롬프트 위 택시 미터기 패널: 세션 요금(API 정가 환산)과 방금 요청 요금, 모델 이름·차종·할증 키, 5시간·주간 한도와 리셋 시각, /meter·/receipt 7
- taxi-blackbox 0.2.1 Claude의 도구 호출을 블랙박스처럼 녹화: 오류·거부(사고) 직전 동작을 /blackbox에서 돌려보기, 토큰·비밀번호는 가려서 기록 7
- taxi-navi 0.2.0 Claude의 할 일 목록을 내비게이션처럼: 진행 경로·다음 안내 표시, 계획이 바뀌면 '경로를 재탐색합니다', 끝나면 도착 안내 7
- taxi-speedcam 0.2.0 위험한 Bash 명령 앞의 과속 단속 카메라: force push·rm -rf·DB 삭제·변경 폐기·운영 배포를 찰칵 잡아 [가주세요]/[세워주세요]로 묻습니다 7
- figures 0.1.0 mod + skill Draw diagrams, LaTeX math, and tool-result images inline in kitty-graphics terminals 7
- activity 0.1.1 Live panel of what Claude is doing: running tools with real commands and timers, what is waiting for your approval, subagents, and its current todo plan. 6
- hud 0.11.2 claude-hud 0.10.0 as a mod: model, project, git, context, usage, tools, agents and todos, plus alerts, budget, history, a task summary, a detail pane and switchable themes 6
- p1 0.0.1 aside probe 1: fork shape, budget, continuation, store, messages 6
- secret-guard 0.1.8 Keeps secrets out of the conversation: hides API keys and private keys before the model or the transcript sees them, and blocks reads of credential files and commands that print secrets 6
- notify 0.1.3 Notification inbox + native OS notifications when a long turn ends, a subagent or background task finishes, or Claude is stuck waiting for your approval. 6
- prompt-coach 0.1.2 Before a vague prompt is sent, suggests a sharper rewrite; you choose: send improved, send yours, or edit the suggestion. Never rewrites silently. 6
- ts-band 0.8.1 Tailscale nodes' state in a band above the prompt, with a toast when a node comes up or goes down 6
- asd-ste100 2026.10.2+20 mod + skill ASD-STE100 (Simplified Technical English) and 80% Karpathy Mode plugin, mod, and skill for Claude Code. Enforces clean, unambiguous technical explanations. 6
- quickbar 0.1.1 A one-line launcher above the prompt: live context %, and one-click buttons for every claude-mods panel you have installed. 6
- turn-budget 0.4.0 When one turn uses more than +5 session points or 500,000 uncached input tokens, writes a handoff from exact session data and copies it for a new session; the old session is never cleared. No model calls. 6
- open-science 0.3.5 mod + skill Onboarding for the open-science framework: asks which components you want, checks your machine, and sets up tokens safely. Install this first. Also dispatch: start an agent in a new tmux window when you ask. 6
- honmoon-redact 0.1.1 Client-side secret/PII redaction hooks: keep API keys and sensitive identifiers out of Claude Code's model context by redacting Read/Bash/Grep tool output, blocking prompts that carry secrets, and denying reads of known credential files. Session-transcript scrubbing verified on Claude Code 2.1.26... 6
- p6 0.0.1 aside probe 6: mid-turn fallbacks (session.messages + model.complete) vs fork 6
- search-meter 0.1.0 Counts the model's searches and colors each one: green found first try, yellow found after misses, red found nothing 6
- turn-timeline 0.1.8 Draws the current turn as a timeline in a pane (/timeline): model requests and tool calls per loop, where the time went, and the slowest steps 6
- receipt 0.2.1 What each turn did, in a band above the prompt once it ends (files changed with lines, commands and failures, reads, subagents), and a toast when the model goes in circles; read from the turn's own tool calls: no tool, no prompt, no tokens 6