#ModGitHub stars

1. 97cache-bellhollerbell/cache-bellCache & context manager for Claude Code. Once the context passes a size you choose, Claude compacts after a finished piece of work, and you get time to cancel. While you're away, the plugin keeps the prompt cache warm or compacts before it expires.5
2. 98cache-keeperahmadhammoud56/MOAAShows when this chat's prompt cache goes cold and what re-warming costs; keeps it warm on request; suggests a strata handoff when a cold cache meets a full context5
3. 99effort-cycleAnerco/claude-code-effort-cycleChange Claude Code's effort level per agent: Ctrl+↑ and Ctrl+↓ step the main thread or the subagent in view, shown as a colored meter in the footer (‹ › to click on hover) and in the tasks list's subagent rows5
4. 100flowYing-Kai-Liao/flowClaude Code agents that work like a company, with Jev picking the right model for each task to keep cost down.5
5. 101nextcostHMarzban/claude-modSee what your next message costs: a live band above the prompt with the prompt-cache countdown, the re-warm price, session cost, context and your 5h/7d limits.5
6. 102opmharshadmadaye/OPMAn opinionated engineering workflow for Claude Code: brainstorm -> plan -> TDD execution with fresh-context subagents -> verification -> captured learnings. Lean reviewers, stack-specific patterns for TypeScript/React, Python and Flutter, and six light safety hooks.5
7. 103squad-chatchrisluo5311/squad-chatThe all-in-one Claude Code plugin. Talk with your squad, share code, and keep live rooms (usage, git, weather, lo-fi and more) next to your session. Zero tokens, zero leaks to Claude.5
8. 104usage-hudlucassimzq/claude-usage-modA pixel Clawd above your prompt whose mood follows your context, session and weekly usage5
9. 105vitalsnaicud/cc-vitalsA light, framed live dashboard above the prompt, in the terminal and in the desktop app: model and effort, context and account-wide plan-limit meters (5-hour, weekly, per model, usage credits), cost and burn rate, tokens and cache per turn and session, auto-compaction, live tools, background shells and every subagent with its model and effort, plus weekly and monthly usage and the account's plan limits by product. Two columns on wide terminals, sized to the rows it has, never scrolling. Requires ccusage (npm i -g ccusage) for the usage section. /vitals-low, /vitals-medium and /vitals-high set the detail level; /vitals pane full view, /vitals report usage report.5
10. 106wavy-usageBatuhanCakmakk/wavy-usageLiquid-filled rings above the Claude Code prompt for the 5-hour and 7-day limit windows, context fill and prompt-cache lifetime, a fighter jet that shows the model's effort, and a pane of recent turns, their cost, their share of the 5-hour window and what filled it.5
11. 107agent-graphCalvoSeko/claude-factory-modDefine agents with skills and context on a drag-and-drop graph, connect them, and run them locally or as Claude Managed Agents.4
12. 108am-context-barromnycristopher/claude-am-modsA context card above the prompt with a collapsed and an expanded view: zone-coloured token count (dumb zone from 50% or 250k tokens, compact or clear from 70% or 400k), context bar with the dumb zone, where to compact or clear and auto-compact marked, breakdown by category, limits, model, thinking, compactions, git, and progress through a plan's phases. Three layouts. /am-context-bar on | off | layout v1|v2|v3 | plan on|off.4
13. 109clawd-hud-spikesoulrocha/Claude-code-hero-journeySpike da HUD RPG: sondas no app real para os itens A VALIDAR (sem gastar tokens)4
14. 110cost-ledgerFynnXland/fynn-modsCost ledger across all chats: after every answer it records the chat cost (as /cost), tokens per model and model calls made by other mods. /ledger shows today, 7 and 30 days, total, history by model (days or weeks), projects and the most expensive chats; /ledger limits shows the API value in the current 5-hour and weekly window and in your subscription month, plus an estimate of the usage outside the ledger (claude.ai, phone); /ledger sync <folder> merges your devices through a shared folder (amounts only: no paths, projects or chat titles); /ledger help lists all commands, the current state and your settings. Observer only, no model calls.4
15. 111crab-camsTomerG/agent-kitA crab above the prompt acts out what Claude is doing: reading, writing code, thinking, searching and more. A shell beside it shows context and rate-limit usage, and the Crab crew pane gives every subagent a crab of its own.4
16. 112idle-compactukwhatn/.claudeCompacts the main conversation once it has sat idle for idleMinutes, while the prompt cache is still warm, and hands every compaction of the main conversation (manual, auto, plugin, precompute) the Compact Instructions section of the user's AGENTS.md. Skips while a turn runs, below minMessageTokens of conversation, and past cutoffMinutes (a wake from sleep, when the cache has likely expired), saying which in the transcript; a reload of the plugin keeps the pending idle stretch.4
17. 113mioddelexw/miodGenerative music for Claude Code. Every task gets its own tune, and the mood follows what the agent is doing and how fast it spends tokens.4
18. 114night-feasttheonly1me/claude-code-modsA vampire feeds on every tool call Claude finishes while the moon tracks how full the context window is. Between meals it stalks, swoops, and lies in wait. Dawn means it is time to compact.4
19. 115noctissynex1437/noctisRuns long Claude Code jobs overnight within your usage limits: pauses just before the 5-hour or weekly limit, resumes the same session after the reset (or relaunches it days later) and works through a list of jobs you hand it with /noctis:start <file>. Also runs in Codex CLI, Antigravity CLI, Droid and Copilot CLI.4
20. 116observeHula-Hoop-AI/supermodsAn /observe pane with a tab per provider: Docker and Modal containers with each one's live logs and GPU, CPU and RAM use (and Modal's cost), and Render and Vercel deploys (Vercel grouped by app under its production URL) with the current git branch highlighted. `/observe docker|modal|render|vercel` opens it on that tab4
21. 117session-infodougcunha/claude-modsSession pane: context, cost and turns, the prompt cache with the time until it expires, keep warm and a guard that holds a prompt that would write an expired cache again, the last turn's tokens, cache, tools and refused calls, a task list Claude keeps with a switch that keeps Claude working while tasks remain open, an autopick switch that answers a question left unanswered with its recommended option, the skills in use, GitHub Actions runs, mentioned Jira issues, live plan usage bars, running agents with their model and effort, the shell commands Claude runs in the background, the last build and test run, background runs included, with a prompt that asks Claude to fix a failure and a switch that skips a build or test run when nothing changed since the same command passed, the Git state of the repository and its submodules with a treeview of its changed files, and a treeview of the files this session created, modified or deleted.4
22. 118smart-compacthellosverre/smart-compactCompacts at the right moment: after a commit or green tests, a minute before the prompt cache expires, or when Claude asks for it with its own request_compact tool.4
23. 119statusbarian-exnodes/statusbarColored two-row status line below the prompt: model, folder, git branch and changes, context fill, 5h and 7d quota left, tokens, cost, session time4
24. 120typing-speedborabiricik/claude-modsA live typing speedometer above the prompt, offline spell check in your system language, a result card after each prompt (WPM, CPM, accuracy, typos, personal bests) and a /typing stats pane4
25. 121usage-barabyigiter/claude-usage-barSee your Claude Code session at a glance: context left, cost, today's and month-to-date spend, rate limits, git diff and PR status, right above the prompt. Set /budget limits and get a toast before you go over. Open the detail panel for context breakdown, turns, cache hit rate and top tools. Works in the CLI and the desktop Code tab.4
26. 122usage-paneT-AI-Labs/claude-code-modsA pane, opened with /tokens, that adds up tokens, cache hit rate, turns, tool calls and API price for the last turn, the session, today, 7 and 30 days, by model and by project, with the history of the 5-hour and weekly limits, and lists each session's prompts by cost with what made them expensive.4
27. 123usage-weatherptpmediabr/usage-weatherOne quiet line above the prompt: context, 5-hour and weekly usage, whether the prompt cache is warm, and a Clear & continue button.4
28. 124sub-metermidudev/better-claudeYour subscription usage at the bottom right of Claude Code: the 5-hour and weekly windows, taking turns, side by side or fixed on one of them.240
29. 125cache-meterDarioFontanel/claude-code-modsBarra sopra il prompt che si svuota col tempo: quanto resta dell'ora di prompt cache dall'ultima richiesta3
30. 126cache-meterdrdickgraysonjr/chalkeryPrompt cache status above the prompt: how long the cache stays warm, what a re-cache would cost, plan limits near the cap. Keeps a big cache warm on request and asks before a cold send. The cache part of Nate Herk's cache-keeper.3
31. 127cache-watchishuagrawal/cache-watchA band above the prompt that counts down to your prompt cache expiring and shows what it costs your next message3
32. 128cachebeat404Mayank/cachebeatKeeps the prompt cache warm while a session sits idle: shortly before the cache would expire, a small background request re-reads it, without touching the transcript. A beating heart under the prompt shows it working, and Claude can read and change it for you. Each beat counts toward your usage.3
33. 129cc-zhjiangnanquan/claude-code-zhClaude Code 简体中文 UI mod —— 以静态词典把斜杠命令说明、/config 项、Spinner 词、提示与通知显示为中文。零 token、零网络、不碰官方产物。3
34. 130claudettoxsyetopz/dotclaudeTunes Claude Code for coding at the lowest token cost, through its official extension points only: settings, hooks, skills, and an output style. It patches nothing. The tree is a rebuild in progress, and each capability lands with the measurement that decided its values. The one decided default is the compaction path, which stays the built-in compaction of Claude Code until a measured probe result beats it.3
35. 131ClauDiscobombulatingNiedvin/ClauDiscobombulatingConsole: limits, cache timer + alert, model/effort pickers, side pane. Desktop: limits and cache timer under the prompt.3
36. 132clawd-dashpinkpixel-dev/clawd-dashSession dashboard under the prompt: usage limits, context, cost, model, effort, session stats, git status, file changes, and an animated Clawd.3
37. 133clawd-viewthedepegger/clawd-viewA calm, plain-English view of Claude Code: a step-by-step checklist above the prompt, usage stats when there's room, and Clawd the pixel mascot acting out each step. Tool calls and commands stay out of sight.3
38. 134clubhousedcglanton-stack/claude-clubhouseClaude Clubhouse: a toolbar above the prompt, rooms for usage, agents, commands, tool rules and colors, and whole-window themes on macOS3
39. 135context-meterAndrewDongminYoo/cc-agents-kitReads each model request's own usage, shows the real context fill above the prompt, vetoes an auto-compact the advisor's double-counted usage would fire, and sends the handoff nudge once at 80%.3
40. 136cost-visibilitypatitow/claude-mod-cost-visibilityLive cost, context, and plan-quota meters above the Claude Code prompt (Nerd Font required for icons). Type /spend for the detail pane. Optional cost guards via /spend caps on.3
41. 137dashbandEgonLeitner/dashbandPrompt cache, context and plan limits at a glance, in the prompt footer and above the prompt3
42. 138effort-routertommy5dollar/effort-routerMake your Claude Code usage go up to twice as far. Picks the right reasoning effort for every prompt and every subagent, so easy work stops burning your limits and answers come back sooner.3
43. 139gate-meterdrdickgraysonjr/chalkeryProgress of the /unlazy gates bound to this session, one quiet row above the prompt: cells per gate or a pie, met of total, and its state: waiting for a decision, regressed, paused, abandoned, all met. /gates lists them all. Joins handoff-relay, cache-meter and next-steps in one band.3
44. 140hudseanrobertwright/claude-modsTwo coloured, animated lines under the prompt, every figure named: model, effort, context window, rate limits, turn timer, tool calls, agents, git state, worktree, cost, session length and folder.3
45. 141hudlitee950280/hudliteLean claude-hud: clickable 5h / 7d / context, cache and cost rows. Multilingual (English, 繁中, 简中, 日本語...)3
46. 142jev-claude-routerFlam1ngFir3ball/jev-claude-routerRoutes each Claude Code turn to the model and effort TypeSafe's Jev picks, weighed against what a switch costs, and compacts with Jev instead of a lossy summary.3
47. 143jev-effortgebeer/jev-effortSets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent conversation context. Shadow mode by default: logs what it would do without changing anything.3
48. 144mejora-promptsGrandullon/diariovida-mods/mejora y una frase: Claude te hace 3-5 preguntas, escribe un prompt con contexto (sin rol), lo puntúa y lo corrige hasta el 9/10, con bucle o sin bucle. Método de diariovida.com.3