#ModGitHub stars

1. 769model-routerclaudemodz/modsRuns 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.
2. 770model-routeriddhi-sulakshana/claude-modsClassifies each turn as mechanical, ordinary or hard and routes it to a matching model and reasoning effort, logging every decision.
3. 771model-routermuhx/model-routerJev (TypeSafe) picks the model and effort per task type; ported from jev-model-router with main-loop model switching on
4. 772model-routerr1305/claude-modsMiddleware 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 95 % 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).
5. 773model-routerredjackfred/claude-code-modsRuns Explore subagents on haiku and general-purpose ones on sonnet unless a model was asked for
6. 774model-routershezis/claude-model-routerRoutes each turn and subagent to a cheaper model when the task is simple, never above the model you picked
7. 775model-routervladdu/claude-kitPicks Haiku, Sonnet or Opus from a conversation's first prompt and keeps it until /clear; /router on|off
8. 776model-routerwesleystagg/model-routerPicks 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.
9. 777model-router-slimGambetaClub/model-routerPicks 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.
10. 778modscopeCommunityPokeOrg/claude-code-modscopeA 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.
11. 779modsmithbarmoshe/bar-modsA 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
12. 780monkeyKamilMarzynski/claude-code-modsA 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.
13. 781moodcodewe-are-digital-architects/moodcodeClaude Code, now with feelings: an evolving mood, shown as a face beside short, simple, human replies whenever it changes.
14. 782msgate-agentsJustAzul/agent-cli-sdkmsgate-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.
15. 783native-editspadezhnov/claude-code-modsFile changes through Edit and Write, not sed -i and heredocs: rewrites auto mode's shell-first advice and refuses Bash commands that write project files, so every change has a diff, can be rewound and follows the path's rules.
16. 784nerd-fontAH-Merii/claude-pluginsWorks out once whether a Nerd Font is installed, with a setting to force it on or off, so mods that draw Nerd Font glyphs know when to fall back
17. 785new-projectDanielGarcia-Carrillo/claude-improvements/new-project bootstraps a repository from the claude-improvements baselines, in Claude Code or Codex: proposes the kickoff answers from your description and asks only the open ones, copies the web, Rust or Python template, writes CLAUDE.md and the stack ADR, then installs and runs verify
18. 786next-actionclassA19/claude-skills-and-modsA one-line banner above the prompt showing your single next step. Set it with /next, finish it with /next done.
19. 787next-promptsr-gene/gene-claude-modsBetter guesses for your next prompt: several ranked choices, cleaned up, and learned from what you actually type.
20. 788next-stepsinematds/5-modsAfter each turn, up to three suggested next prompts as buttons above the prompt: press one to send it, or dismiss (/next on|off)
21. 789next-stepsMJEWebWohnRaum/claude-modsAfter each turn, 2 or 3 likely next prompts above the prompt, numbered 1, 2, 4. Press their sum in an empty prompt to draft them together (3 = 1+2, 6 = 2+4, 7 = all), 0 to dismiss. Fork of hamzafer/next-steps 0.2.1 (MIT).
22. 790next-steps-desktopshichang4fun/claude-modsSuggests up to three next prompts above the input after each turn; works in the desktop app (click to send, or copy to edit first). Adapted from next-steps by Thariq Shihipar.
23. 791next-steps-pluseldiablo-1226/next-steps-plusAfter each turn, suggests up to three next prompts above the input, in the terminal and in the desktop Code tab. Based on Anthropic's next-steps (MIT).
24. 792next-steps-stickymrayyan911/claude-code-modsnext-steps, but the suggestions stay up after you pick one: click another to replace the draft. Based on next-steps by Thariq Shihipar (MIT).
25. 793next-unreadsanderjn/claude-next-unreadConductor-style unread threads for the Claude desktop app: a notice when another thread finishes or asks a question while you were elsewhere, and Option+L to jump to it.
26. 794now-doingjoanvelja/claude-modsA briefing card above the prompt: the session's state and how long it has held, its mission, the open asks it is waiting on you for (kept until a quoted reply closes them), what is burning money, what it found since you last sent a prompt, what comes next, plan progress, and each agent with its last activity. `/now-doing asks` lists every open ask; `/now-doing sync` opens the full briefing in a pane. Written by Claude Haiku 5.5 on the session's own credentials.
27. 795nuetmmedum/nuetA dim time above each prompt and each reply in the Claude Code transcript, written the way your own clock setting writes it
28. 796nukeyarifamir/nukeyNukey, a little microwave with a face in its window, sits above the prompt and acts out what Claude is doing, goes DING! when a turn is done, and shows a control-panel meter for context and rate limits, in five colour themes.
29. 797octopus-crewEmanueleNene/claude-modsShows a walking pixel creature above the prompt for each summoned subagent or firstmate crew worker.
30. 798offene-punktehb03/claude-modsFührt, was in der Sitzung noch offen ist – Entscheidungen, Freigaben und Aufgaben des Nutzers –, fragt es über der Eingabe ab und gibt die Liste je Projekt in die nächste Sitzung mit (offen.md, offen.json für claude-web). Claude trägt Punkte als Block in seiner Antwort ein und schließt Erledigtes per „erledigt: #N“; Haiku fasst nur nach, gleicht stündlich mit Commits ab und schreibt den Überblick fort. /offen zeigt und bedient alles, /offen übergabe schreibt eine Übergabe für die nächste Sitzung, /offen kosten zeigt Kosten und Nutzung; Einzelheiten in der README des Plugins.
31. 799office-spacerbrtcnkln1/office-spaceSubagents as 16-bit office workers above the prompt, plus external workers from a watched folder. Toggle with /office-space.
32. 800okbBilel-Gh/okbOpen Knowledge Brain: ingest sources, search with evidence, and propose reviewed changes to an OKF knowledge bundle.
33. 801omni-cataloki-alok/omni-catA pixel cat above the prompt that runs an OmniDimension test call and reports how it went.
34. 802oni-haloviik2k/oni-haloONI Section Three RCON console for Project Reclaimer (Halo 3) dedicated servers, inside Claude Code
35. 803open-in-vscodebanzhe/claude-open-in-modAdds an "Open in VS Code" button above the prompt that opens the session's workspace in VS Code.
36. 804optimize-promptkelokchan/optimize-promptOptimize prompt button above the prompt box: a model (Haiku by default) rewrites your draft in place
37. 805opum-loreopum-ai/lore-cliDrive the lore CLI: author, retrieve, and maintain OKF documentation bundles, including explicit multi-repository workspaces. Cut from the same lore-cli repository and tag as the CLI itself, so this skill can never describe a version you don't have. Also ships the Lore pane: a pane that browses, reads (rendered and raw), searches, creates and edits the repository's documentation bundle through the lore CLI, editable in the session's own repository.
38. 806opum-questopum-ai/quest-cliDrive the quest CLI: create, list, view, edit, complete, and archive tasks, drafts, milestones, and decisions in a Quest-initialized workspace instead of editing tracker state directly. Cut from the same quest-cli repository and tag as the CLI itself, so this skill can never describe a version you don't have. Also ships the Quest board: a pane listing the tasks being worked on in the session's own repository, editable there.
39. 807opus-conductorokashiina/illa-modsOpus 5.5 conducts a mission: plans sized tasks, delegates hard labor to Sonnet 5.5 workers and narrow jobs to Haiku 5.5 scouts at the reasoning effort each task needs, shows every agent and the mission's % in a live pane, shows "cooking" with live-moving bars while agents work, and holds its autopilot while Opus waits on the outside world instead of nudging it
40. 808painel-modsYgor-Silva/modelo-projeto-claudeComando /mods: painel com os mods instalados pelo app e os plugins da conta, com botão para ligar e desligar cada mod
41. 809parkedBuddyLim/claude-code-mod-parkedA backlog of items needing your attention, parked by you or the orchestrator, kept per session and listed across them
42. 810pass-or-bustilovepixelart/pass-or-bust-modSlots for your test runs: the reels spin while Claude runs the tests and stop on the real result. Fake credits only.
43. 811paste-preview0010aor/claude-paste-previewPreview the images you paste into Claude Code: hover a label above the prompt, click to open
44. 812path-buttonsgottesgerl/claude_mod_pathbuttonsFarbige Buttons und Vorschaubilder über dem Prompt für die im Claude-Text genannten Pfade: Linksklick öffnet (Ordner in Directory Opus, Bilder und Videos im Chaos Player, .md/.txt im Sidepanel), Rechtsklick kopiert den Pfad, Überfahren zeigt den Dateinamen.
45. 813personal-computerph3on1x/agent-plugins-skillsKeeps personal data out of Claude: every tool output is scanned on your machine (OpenAI Privacy Filter and PII-Tracer), and output with personal data is processed by a private model you choose through anymodel, while Claude orchestrates.
46. 814pi-outlinerfloat-ritual-stack/pi-herdr-outlinerPi Outliner integration for Claude Code, following the outline the session folder is bound to: typed outline, workboard and door tools for agents (read, find, edit, comment, changes, draft.patch, ep0ch act), clickable references, and completed responses that mention [[pages]], ((block ids)) or Work IDs in the Outliner's Recent Mentions navigator.
47. 815picklePickleBoxer/pickleEngineering workflow skills for Claude Code, built on agent-skills and picked per task by one entry skill
48. 816pinliquid1982/claude-pluginsMarks conversation content wrapped in <pin>...</pin> tags as compaction-proof: pinned content is re-injected verbatim into the transcript after every compaction (manual /compact, auto-compaction, plugin-triggered, or precompute).