#ModGitHub stars

1. 1009zh-bridgeRinne414/zh-bridgeType in Chinese, talk to the model in English: translates prompts and replies with local Ollama, falling back to Google Translate
2. 1010zh-replyPeterTing/claude-modMakes Claude and its agents reply in Chinese (Traditional by default), and asks for a rewrite when a reply comes back in another language.
3. 1011ziel-graphTzy197/claude-modsDer Plan eines Repos in zwei Ansichten, mit GOAL.md als Anker: /graph zeigt schmal die laufenden Chats und den Plan als Graph, /orchestrator breit denselben Plan als Prozesskarten
4. 1012command-hubmishgoldenberg/claude-modsDiscover slash commands: essentials explained in plain language, searchable list of everything installed, a form to create your own, and tips when a command fits what you just typed.14
5. 1013gemini-compactKilimcininKorOglu/claude-code-modsMoves compaction from Claude to Gemini: in summary mode Gemini summarizes the conversation and the newest messages stay verbatim, in prune mode every message stays and Gemini keeps, cuts or drops older tool calls. Off until /gemini-compact on; gemini-core holds the key, tier, model and thinking level.13
6. 1014think-hardmidudev/better-claudeStart a prompt with + and that turn thinks at max effort. Other prompts keep the session's effort.280
7. 1015lemo-lotlemomo-ai/lemo-mod抽签：给 Claude 增加抽签工具 draw_lot，抽到的签显示为签文卡片 · 默认关闭，在「安全」页开启 / Lots: adds a draw_lot tool for Claude and shows drawn lots as fortune cards · off by default, switch on in Safety71
8. 1016desk-planKyongSik-Yoon/cc-desktop-modClaude Code mod that asks for plan approval (ExitPlanMode) in a card above the prompt instead of the full-screen engine dialog, with the plan open in desk-look's preview pane: 1 approves, 2 views the plan, type what to change or comment on plan lines in the pane (c, then 3) to send it back, 9 for the engine dialog. Needs desk-look11
9. 1017model-routerpromptadvisers/claude-mods-starter-kitRoute supported subagent work to Sonnet or Haiku while keeping the main conversation on its model. /router for controls.23
10. 1018env-doctorYeonwooSung/my-claude-code-modsEnv Doctor874
11. 1019taxi-blackboxdevbrother2024/devbrothers-modsClaude의 도구 호출을 블랙박스처럼 녹화: 오류·거부(사고) 직전 동작을 /blackbox에서 돌려보기, 토큰·비밀번호는 가려서 기록9
12. 1020next-stepshamzafer/claude-code-modsAfter each turn, 2 or 3 likely next prompts above the prompt. Press 1, 2 or 3 in an empty prompt to draft one, 0 to dismiss.474
13. 1021delegatewdsewdser-bit/claude-code-modsHand a task to a cheaper model (any OpenAI chat-protocol provider) through a local Anthropic-to-OpenAI proxy; /delegate manages providers, keys and models.7
14. 1022fork-tabzhebil/claude-code-pluginsAdds a /fork-new-tab command that forks the session into a new terminal tab (Warp, cmux or iTerm).7
15. 1023test-ledgerwhyashthakker/awesome-claude-code-modsRecord likely test, lint, and build commands and their tool status.120
16. 1024imagenekyialabs/claude-code-toolkitAn image tool for the agent: make or edit pictures through a pluggable engine (default: the official OpenAI Images API). Room to grow into video.15
17. 1025mission-controlhamzafer/claude-code-mods/mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files they touch.474
18. 1026smart-routerPlagemes/claude-modsRoutes every subagent to the right model for the task's difficulty, runs independent work in parallel and starts workflows when a job needs one.6
19. 1027vellumbengous/claude-code-pluginsPlan at the frontiers and review the plan in the browser: decisions and interfaces before mechanics, vertical slices each closed by a check. /vellum:start opens a planning mode of its own: Claude writes the plan and its mockups and grills the reviewer on the open choices; the reviewer comments, edits or approves in a page, and the answer reaches Claude as a prompt.6
20. 1028compact-keeperVedantAndhale/claude-pro-kitAfter a compaction, adds one message with exact facts from before it: your latest prompt in full, up to 4 earlier ones, the files edited, the todo list and the last failed shell command. At most 4,000 characters. No model calls.13
21. 1029lemo-watchlemomo-ai/lemo-mod定时提醒：N 秒后代你给 Claude 发消息，请它汇报进度 · 点了才开始 / Reminder: sends Claude a message for you after N seconds, asking for a progress update · starts only when you press it71
22. 1030conflict-radarwhyashthakker/awesome-claude-code-modsList unresolved paths and count conflict markers in tracked files.120
23. 1031client-pulseNicoSKOOL/seo-modsShows a client's live Search Console, rank tracking and AI visibility numbers from DataWise above the prompt.5
24. 1032prompt-bouncerray-amjad/claude-code-modsBounces vague prompts before Claude sees them, and suggests the project's own term115
25. 1033run-commandbendrucker/claudePick a reply's `! <command>` suggestion by click or digit to fill it into the shell prompt18
26. 1034next-stepsDarioFontanel/claude-code-modsTre bottoni sopra il prompt a fine turno: i due prossimi passi naturali della conversazione e Replay4
27. 1035reflect-modpartalemre/MODZclaude-reflect as a Claude Code mod: notices when you correct Claude (a quick word check in Turkish and English, then one small model check) and offers, on a card above your message box, to save the correction as a lasting rule in the instructions file you choose (CLAUDE.md); /mine finds what keeps going wrong across past chats and suggests rules, automations (hooks), skills or mods4
28. 1036taxi-navidevbrother2024/devbrothers-modsClaude의 할 일 목록을 내비게이션처럼: 진행 경로·다음 안내 표시, 계획이 바뀌면 '경로를 재탐색합니다', 끝나면 도착 안내9
29. 1037session-saverhamzafer/claude-code-modsNames untitled sessions through unpause. /park saves where you left off, and a resumed session shows it.474
30. 1038framenekyialabs/claude-code-toolkitAdds your own operating frame (a markdown file) to the system prompt in sessions that were not launched with it.15
31. 1039repo-heatmappromptadvisers/claude-mods-starter-kitWatch where Claude looks: a live treemap of the repo that lights up as files are read, searched and edited.23
32. 1040agent-modelsalex2481kobe/claude-modsEach Claude subagent's model and effort in the native agent list, beside its task3
33. 1041catalyst-refusal-watchTransmuteLabs/CatalystMakes every response the service filter stopped visible at once and adds a rule: report it, do not drop work silently.3
34. 1042image-librarynerevar48/nerevar-modsПанель «Библиотека»: галерея изображений проекта, сессий Claude Code и Codex с миниатюрами, фильтром и сортировкой по дате3
35. 1043next-stepsdrdickgraysonjr/chalkeryA What next? button above the prompt: on press, suggests up to three next prompts; 1, 2 or 3 puts one into the input box as a draft, 0 hides them. A fork of Thariq Shihipar's next-steps, which suggested after every turn.3
36. 1044papeleraGrandullon/diariovida-modsCuando Claude va a borrar algo, en vez de borrarlo lo manda a una papelera (~/.papelera-claude) para que puedas recuperarlo. /papelera te enseña qué hay dentro.3
37. 1045paste-peekMankhongGarden/claude-code-mods-field-notesWindows only: a small floating strip over Windows Terminal that previews each [Image #N] you paste or drop, until you send3
38. 1046session-modelsAbhiramDwivedi/claude-opsShows the main model and its effort, the live agents by model and effort, named agent crews, and the working directory, and warns about agent crowds and huge contexts3
39. 1047streamer-modeSeongGwangJu/k-mods유튜브·라이브 방송, 화면 공유 회의, 페어 프로그래밍 중에 화면에서만 비밀 키·주민번호·전화번호·이메일 같은 민감한 값을 가려요. 화면만 바꿀 뿐, Claude가 읽는 내용과 저장되는 대화 기록은 그대로예요.3
40. 1048witnessXabilimon1/emcc-claude-code-modsA live view of Claude's work: the goal, a ribbon of what it spent its time on, what it is doing now, and each step marked proven, unproven, stale or flagged.3
41. 1049bughuntKilimcininKorOglu/claude-code-modsRuns proof-driven bug hunt rounds with /bughunt: each round proves one bug with a failing command the mod runs itself, fixes it, and proves the fix, and the loop stops on a blocked or unverified round. /bughunt collab runs a read-only scanner, planner and critic in sequence.13
42. 1050fleet-statusescapeboy/claude-code-kitFleet P1/P2 counts from ~/.continuity/FLEET-STATE.md in the status line; /fleet and /ports commands.98
43. 1051agent-narratorOneWave-AI/claude-code-modsWatch the agent work: every step in plain English, with a live time-saved counter29
44. 1052command-centerT-AI-Labs/claude-code-modsOne row above the prompt with a source filter, an agent dropdown and one dropdown for skills and commands, and Insert and Run buttons that put the pick into the prompt or start it.6
45. 1053goblin-utilJasonWarrenUK/goblin-modeTwo mods for the machine you run Claude Code on: /pain logs friction with the tool itself without a turn, and /fleet shows every session on the machine and lets you message one.6
46. 1054loadbendrucker/claudePace Claude's heavy work to the machine it runs on, with configurable hard caps18
47. 1055plain-viewice-lfernandes/claude-code-modsA quiet transcript: tool rows step aside and the agent's plan shows as a card above the prompt, with the current step, progress bars and a summary when the turn ends11
48. 1056where-am-ihamzafer/claude-code-modsA live recap above the prompt: goal, doing now, waiting on you, next. /where for a longer one.474