#ModGitHub stars

1. 865quiet-transcriptkevlar10x/quiet-transcriptQuiets everything in the transcript except Claude's answers: narration, tool calls and command output draw in a faint tinted italic.
2. 866radio-multitomato3017/tomato-claude-mods/radio-multi lists radio stations (add/delete from the menu) and opens the chosen one in the default browser
3. 867raily-matchesrailyai/claude-code-modsRaily is a personal AI agent that finds people worth meeting for you (friends, dates, business contacts) and handles the first contact. This mod shows your Raily inbox above the Claude Code prompt: new matches with name, city and score, contact requests, unread chats and questions from your agent, with a toast for each new event. Read-only. Needs a Raily account (18+) and the Raily MCP server connected.
4. 868read-aloudtgralex/claude-modsReads Claude's replies and plans aloud, whole or just the text you selected, with a Stop button while it reads.
5. 869read-fencevarunmoka7/read-fenceStops Claude from opening your skill, rule and plugin folders file by file while you have the fence switched on. Skills still run normally.
6. 870readoutlucenity0/claude-readoutShows which files Read opened, which lines, and what each search looked for, on the folded tool line
7. 871rec-modesimplybychris/claude-code-modsRecording mode: blurs emails, keys, IP addresses and user names on screen; hover over a blurred spot to reveal it. /rec turns it on and off.
8. 872recaplokki007/claude-code-modsNext-prompt builder after real work: 28-40 customer-focused options in eight color-coded directions, ranked 80/20, with ready-made packages to take whole or save for later; Claude can interview you with clickable questions.
9. 873receiptsphilm123/claude-code-receiptsReceipts for consultants: a scope creep siren for change orders, and undo receipts that turn rm into a move to trash with a Restore button.
10. 874receiptsshawnpetros/claude-receiptsUNVERIFIED when Claude claims done without a check: a receipt line under every answer that claims done, naming the test or build that ran after the last edit, or saying nothing did. Plus a progress band with an estimate that names its basis.
11. 875recording-modehugo88/claude-code-recording-mode/rec przed nagrywaniem: maskuje sekrety, dane osobowe i kwoty na ekranie i zamyka prywatne pliki (/rec on|strict|off|config)
12. 876red-squiggleccdwyer/red-squiggleType-checks and lints the file Claude just edited and puts the errors in that same tool result
13. 877redbox-relayccdwyer/redbox-relayAttaches fresh React Native redboxes and native crash logs from running simulators and emulators to your prompt, and warns when an edit needs a native rebuild
14. 878reecrireChrlstopher-c/reecrireBouton « Reprompting » au-dessus du prompt : Haiku 5.5 réécrit votre brouillon en direct dans le champ, au format de prompting du modèle actif (CLI + Desktop)
15. 879reefdavidcoulson/crab-workshopYour homelab as an aquarium (/reef): every Docker container is a fish coloured by its stack, unhealthy ones float belly-up, the Ollama GPU is a heater that glows while a model is loaded, Home Assistant is a lighthouse that blinks red with repairs, and a crab walks the sand for each side session at work.
16. 880reels-while-you-waitjemsley06/reels-while-you-waitOpens Instagram Reels in a small centered Safari window while Claude works, autoscrolls, and closes it when Claude finishes.
17. 881reflect-bridgesmhasan-yad/claude-mod-reflect-bridgeReflect, adapted: spots reusable corrections in your short prompts (one small Haiku call, only on prompts that read like a correction) and saves them on one press to auto-memory, the shared Claude CLAUDE.md, or the AGENTS.md all your agents read. Based on claude-reflect's mod by Bayram Annakov (MIT).
18. 882relayhal-9/claude-modsRole buttons above the prompt: check or adversarially review the working tree with Codex, hand a task over to Codex, or verify with a second Claude model. A pane streams the run and turns findings into fix prompts.
19. 883relevogabrielespelleta94/relevoConecta chats abiertos entre sí y delega tareas a otros modelos (Haiku, Sonnet, Opus, Fable)
20. 884rename-session-modmrayyan911/claude-code-modsNames a session after a summary of its work when it ends (exit or /clear), and only when work happened since the last rename.
21. 885replykrishna-goutham-tls/cc-modsHighlight part of Claude's answer and reply to it. The text goes into your prompt as a quote.
22. 886reply-highlightLegendSilvia/claude-code-modsSets Claude's replies apart in the transcript: a rainbow edge, a violet tint, and bold text and headings in a rainbow
23. 887reply-timestampjohnlewczuk/claude-modsAdds the reply's time to the turn line when Claude Code leaves it off (while background agents run)
24. 888repo-radarrabanderlipe/claude-code-modsLive map of the repo that lights up as Claude and its subagents read, edit and fail on files
25. 889resource-watchtartinerlabs/claude-code-modsShows which Claude Code session is using each booted Apple simulator, Claude Design project and the Xcode app, above the prompt, and when another session already holds one this session picks up, toasts, messages that session and tells this session's agent.
26. 890revo-flowLilianMLG/revo-flow/revo-flow <demande> : l'orchestrateur lit les specs, fait un plan, répartit les tâches entre des sous-agents (modèle et effort choisis pour chacun) et affiche une barre de progression par agent dans le panneau latéral ; un cache par projet (graphe des fichiers et fiches de features apprises en fin de flow) lui évite de relire le code : /revo-flow cache. Un agent peut en attendre un autre (relancé quand il a fini) et reçoit l'extrait de fiche qui le concerne, qu'il vérifie et rafraîchit. Un flow vérifié : revo-flow apprend les commandes de vérification du projet (lint, typage, tests ciblés), les lance lui-même en fin de flow et refuse de le déclarer terminé tant qu'elles sont rouges (erreurs nouvelles seulement, base de référence prise pendant la planification) ; critères d'acceptation, vérificateur indépendant et tests gelés en option. Le score CRAP (complexité × couverture des tests liés) fait respecter la règle du scout : une fonction modifiée par le flow au-delà de 30 bloque la porte, une fonction ancienne qu'il ne touche pas jamais. Les agents installés sur votre Claude Code (projet, dossier personnel, plugins activés) sont proposés à l'orchestrateur : un sous-agent peut en prendre le type, avec son modèle et son effort. /revo-flow doctor montre ce que le mod a détecté sur le projet (stack, commandes de vérification, base de référence, cache, agents installés) et ce qu'il y fera ; un flow interrompu par un redémarrage peut être repris ou abandonné ; chaque flow laisse un rapport en markdown (plan, fichiers, verdict de la porte, critères, CRAP, coût). Preuve à l'exécution, choisie selon le projet : web (package.json avec serveur de dev) ou mobile (Flutter, React Native, Expo). Web : sur un critère observable, le vérificateur demande le serveur de dev, revo-flow le démarre sur votre accord et lui donne l'URL ; il navigue (console, réseau, capture par critère). Mobile : revo-flow choisit l'appareil (téléphone branché, sinon émulateur ou simulateur démarré avec sa fenêtre), lance l'app sur votre accord et le vérificateur l'observe en direct (capture, arbre des vues, journal, gestes). Les captures vont dans le rapport ; serveur, app et émulateur démarrés par revo-flow sont arrêtés en fin de flow.
27. 891ringsideChiFungHillmanChan/ringsideRingside: a ringside seat on every Claude Code session on your computer and what each one started (subagents, background shells, loops), what needs you or may be stuck, a Peek on any of them with Jump there, a task checklist and an agent launcher. Formerly Agent Map.
28. 892roll-calldim-owl/roll-callShows which other Claude Code sessions on this machine are waiting for you, and what they are working on.
29. 893rook4DvAnCeBoY/rook-claude-pluginrook by TestMu AI inside Claude Code: Claude runs rook against the agent it is building and gets failures back grouped into root-cause clusters with rook's remedies, writes scenarios, a live pane with per-scenario lanes and openable failures, re-test prompts after agent edits, a status line score, /rook commands and a production-target guard.
30. 894routeHarzerHeribert/claude-modpackOptional, and the one mod that needs an outside classifier model: hands feature and test work to delegate's cheaper worker. A fast classifier (TypeSafe's Jev or ScaleDown, with your API key) reads your prompt, and only where it is feature or test work does Claude get the order to implement it through a hand-off. Off until you turn it on and give it a key for one of them.
31. 895routine-watchseanyyoo/claude-code-modsYour scheduled routines at a glance from a Notion database: today's haul by source, the last 7 days, sources that went quiet and next runs
32. 896rtlAliakbarNateghi/cc-rtlDraws Persian/Arabic text in Claude's replies joined and in right-to-left order on terminals that do no bidi or shaping. Terminal only; the transcript is untouched. Toggle with /rtl on|off.
33. 897rtl-kitbarmoshe/bar-modsRight-to-left for Claude Code mods: one file to copy into a mod that orders Hebrew and Arabic right on every surface, aligns wrapped text right, draws markdown, cards, tabs, tables and SVG headers, and reorders text for the terminal
34. 898rtl-questionsitaym967/rtl-questionsShows Claude's questions, and plans awaiting approval, right-to-left (Hebrew/Arabic) in the desktop app
35. 899ruahruah-dev/ruah-mapSee the architecture of any repo, code and cloud, right inside Claude Code. /ruah:map scans packages, imports, Terraform, Kubernetes, Compose, Cloudflare, Vercel and CI, then opens a live map above the prompt.
36. 900sanchojacobomatadev/sanchoTu escudero en Claude Code: una sola fila que aparece solo cuando hace falta. Avisa antes de continuar una conversación cara, resume y deja revisar los cambios uno a uno, sigue a los subagentes, señala riesgos y guarda tus correcciones como reglas.
37. 901scope-creep-receiptmofocm/scope-creep-receiptAfter every turn, Claude Code prints you a receipt for everything it did while you asked for one thing.
38. 902scout-routerMohabYasser2/claude-code-modsBefore a subagent starts on Opus, a Haiku judge reads its task and moves it to Sonnet unless it needs Opus's judgment.
39. 903scratchLutifya/claude-code-modsA scratch pad to draw on with the mouse: /scratch opens it with the keyboard and pointer already in it, no click to focus.
40. 904screen-cloakJJenglert1/claude-modsHides emails, phone numbers, money, account numbers and names you list from what is drawn on screen, so you can share your screen. Claude still sees everything.
41. 905sdd-control-planefib1618agent/claude-mod-speckitSDD capability 10: aggregate read/delegate view, derived nextAction and configuration view. Not an orchestration engine; owns no approval.
42. 906sdk-syncYuehengHan/my-claude-modsAfter an SDK release (v* tag): /release-check gathers what changed and asks Claude for a read-only audit of the sibling SDKs, docs and examples. Never acts while you work.
43. 907seekHarzerHeribert/claude-modpackHas Claude look around your code in few, lean steps. Every request re-reads the whole conversation, and whatever Claude reads stays in it for every later request; so your prompt, and the task of a subagent Claude starts, carries your setting to batch the searches and reads Claude can already name, to read definitions or line ranges instead of whole files, and not to read again what the session already holds. Once per session, and again after a compaction or another 150k tokens. Optional, off: a code search's result also names the definitions that hold its hits. Nothing leaves your machine.
44. 908semanafllag/claude-modsPainel com a sua semana: reuniões do Google Calendar e tarefas do Basecamp num lugar só, na identidade da Hospedin. Abra com /semana. Precisa de setup: Google Calendar conectado no claude.ai e CLI do Basecamp autenticada.
45. 909server-farmpierregoutheraud/claude-modsAn idle server farm above the prompt: daemon bots collect data from your racks, and your Claude work boosts it
46. 910session-barbetoescobar46/pitutoA bar under the prompt with compact, clear, effort, model and a color per folder, plus a side chat for quick questions that don't interrupt the task.
47. 911session-briefcoil398/claude-session-briefSummarizes Claude Code sessions and tracks subagents, background tasks, hook activity, and Codex runner jobs.
48. 912session-busyojoaquin/claude-session-busLets Claude Code sessions (cloud and local) message each other and set each other's model and effort over an encrypted relay channel.