#ModGitHub stars

1. 913usage-meters0xgigilau/claude-usage-metersProgress bars for context window, session/weekly/monthly usage and per-model token share, in a pane (or band above the prompt) and the status line.
2. 914usage-metersChristianBuzzetti/ClaudeModsAnimated usage strip above the prompt plus a Details pane: context window, 5-hour and weekly caps, cache hits, token flow and per-subagent spend
3. 915usage-metersdrewster99/claude-usage-metersContext length and today's / last hour's non-cache-read tokens (session + subagents) above the prompt
4. 916usage-modjasmo13/usage-modA live usage band above the prompt for this Claude Code session: cost, tokens, cache, context, rate limits, turns, tools. Desktop and terminal.
5. 917usage-modkreddevils18/claude-usage-modYour Claude Code usage as colored chips above the prompt: 5h and weekly limits (% left), session cost and spend history. /usage-mod opens the full view.
6. 918usage-modsperanzapedro/usage-modMostra quanto você já usou da janela de 5 horas e da semanal, e quando cada uma reinicia, numa faixa acima do chat. 8 personalizações: Padrão, LoL, CS, Carro, The Sims, Pokémon, Pac-Man e Windows 95.
7. 919usage-modsakixi-maison/usage-modsShows whether Claude is working, waiting on you or done, and context, rate-limit and cost usage, above the prompt
8. 920usage-reportSchweem/usage-reportShows context fill, 5-hour and weekly quota, and session cost on the status line under the prompt, with warnings near your limits.
9. 921usage-reportercskwork/claude-code-modsShows the weekly limit reading and, once configured, POSTs it hourly to your HTTPS endpoint. Off by default.
10. 922usage-reportertksunw/usage-reporterWrites your Claude usage limits and credits to ~/.claude/usage-reporter/usage.json so other tools can read them
11. 923usage-ringsdglasgal/usage-ringsClaude plan usage rings with reset times, what your Claude Code and Cowork usage would cost at API prices, a leaderboard of your most expensive sessions, spend alerts, and fire-and-money graphics.
12. 924usage-statsmina-asham/claude-usage-statsShows your Claude plan usage above the prompt: current session (5h) and weekly percentage used, with reset times.
13. 925usage-statusaliahmadcse/claude-usage-statusStatus line with the model, context fill, session tokens and cost, and the 5-hour and weekly usage limits.
14. 926usage-statusJump-High-Kid/claude-modsOne line above the prompt: 5h/weekly usage with reset times, context %, repo, model and effort
15. 927usage-torchhicrandn/claude-modsYour Claude usage limit, as a one-line torch bar above the prompt that fades as you use it.
16. 928usage-trackerSanjayPG/claude-code-usage-trackerShows your remaining Claude usage (current session and this week) as colour-coded progress bars above the prompt.
17. 929usage-weatherimsalik/claude-modsContext window forecast plus 5h/7d rate-limit usage with reset countdowns, drawn above the prompt.
18. 930usage-weatherqarge/claude-modsA live forecast above the prompt: context window fill (cached and uncached) updated on every model request, and the 5-hour and weekly usage limits as /usage reports them, kept in step across every session, with bars on a smooth color gradient, weather icons and reset countdowns.
19. 931uso-contaGuiAmaral85/claude-mod-uso-contaFaixa acima do campo de texto com o consumo: custo da conversa em US$ e tokens, ou o limite da conta quando ela informa
20. 932villager-hpAshley-Pettit/villager-hpYour Claude session and weekly usage limits as an animated villager health card, with a weekly pace hourglass, rank badges and a death screen at 0 HP
21. 933warm-compactziedgithub/claude-code-modsCompacts an idle session just before its prompt cache goes cold, or keeps the cache warm while you're away, so your next prompt doesn't re-read the whole conversation uncached. Two chips under the prompt, /warm-compact and /keep-warm turn each on or off for a session.
22. 934watch-towerBastienTeissier/watch-towerWatch Tower: a pane to follow a Claude Code session at a glance (subagents and what they are doing, context, cost, quotas, prompt cache countdown, attached plan's position, off-plan guard), with an optional ASCII companion
23. 935watchdoggodstale/WatchdogModWatch Dog: live agent/sub-agent/usage dashboard above the prompt, plus the /wd command to inject requests mid-task, pause/resume it and stop it gracefully, and /wd-log, /wd-git-graph (branch and history graph of the repo), /wd-help.
24. 936week-plansebastiandammeyer/claude-modsTurns Claude's weekly usage limit into a daily budget with a weekend reserve, a status line and a chart
25. 937whoamitornikegomareli/claude-whoamiClaude Code mod: shows which Claude account, organization and plan the session uses and how much of the usage limit is left, and holds prompts in a folder pinned to another account.
26. 938widget-bridgekirishimarisano-rgb/Mods-Claude-code-0-powerd-by-claudeSends each local session's status (what Claude is doing, task progress, context and usage) to the Claude Widget desktop app on this computer, and takes its Stop button
27. 939windvane20alexl/windvaneBabysits a long Claude Code session so you don't have to: the context fill is watched, the recorder drafts the checkpoint, compaction happens at the right point with the state banked and the work is resumed, the rules and the checkpoint ride inside the compacted conversation and every subagent's prompt, tool results are trimmed and secrets redacted at the door, project memory and rules are a tool call away, and a token ledger, a pane and a status segment show where the session stands.
28. 940workbenchPigula1984/workbenchA set of mods that put live session data around the prompt box: statusbar (model, effort, mode, directory, branch, usage) and workflow (a dynamic workflow's steps under the prompt).
29. 941wtforangeJigglypuff/better-btwSelect text, run /wtf, and a side pane explains what it means in the context of this conversation, without adding anything to the conversation.
30. 942x48-usage48X-Dev/claude-pluginsSaves Claude Code's 5-hour and weekly limits, context fill and session cost for the 48X AI Usage app.
31. 943yemeni-context-bandiyiob96/Context-Mod-CompanionContext-window band above the prompt with RTK token savings and a clickable pixel Yemeni companion whose mood follows how much context is left
32. 944zetetic-autopilotcdeust/claude-modsAutomatic effort and model, and a quota that limits how many agents run, not how well one runs. Every request runs at the effort its grade calls for (zetetic-genius) and the main tool loop steps down the ladder. A subagent runs on the model its Agent call names, else the one its agent definition pins (read from the definition file, since agent.spawn carries only the call's), else the one the DESIGN block of its prompt names, else, for an inheriting type nobody designed, the rung of the dispatch table (hooks/dispatch-table.ts) for its task's class: one haiku completion grades the spawn prompt (routine, planned, bugfix, analysis, critical; a review or not), and the table gives model and effort (no haiku rung; a review runs on opus when complex, else on sonnet). A classifier that gives no class decides nothing: the spawn inherits and a POLICY row says why. Its effort is the Agent call's, else the one its definition sets, else DESIGN's, else the table's; an inheriting type the call gave a model runs every step at the effort of the turn's grade (main's spawns on a graded turn; a fork, a workflow agent or a teammate is never rewritten). No pressure, quota or context changes a model or an effort the orchestrator designed. Each spawn's requested, definition and decided model, what ran, the effort decided for its steps, the table's class and a short reason for each are kept per session. Quota pressure limits concurrency: the cap on subagents running at once falls from max_parallel_agents (5) at an empty five-hour window to 1 at quota_pressure_percent, and a spawn past it is refused with a message the orchestrator reads (wait for a running agent to finish). Only the main loop's own spawns, a fork of main included, are counted and refused: a subagent's nested spawn, a workflow script's agent() and a teammate are not. Main itself drops to sonnet under quota pressure, and doing implementation work in the main loop is warned about (POLICY row, toast), never blocked. A long streaming tool result is written whole to a file in the session's tool-results directory and the model reads a preview and the path (nothing is cut). Owns `phases`: the phase each loop is in (planning, analysis, design, implementation, verification, test, review, report), read off its tool calls or, for an agent, its type; on each run, the steps the stuck escalation raised (counted where each raised step landed, under enforce only); and the advisor calls of main with when they came. The tool loop of a phase the insights calibrated runs at that rung instead of medium (never above the request's grade). Starts in enforce; observe logs the decisions without applying them.
33. 945zsemleParais4/parais-modsZsemle, a pixel-art companion above the prompt (golden retriever, cat, slime, paperclip): watches every usage limit (50/75/90% warnings, pace forecast, resets, API errors, automatic model switch and compaction, cost), stops work at 95%, guards file writes and cheers long turns. English and Hungarian, terminal and desktop.
34. 946lemo-corelemomo-ai/lemo-mod核心：风格、中英文界面、消息编号和 /lemo-mod 面板，以及给其他 lemo mod 用的 $.lemo / Core: styles, zh/en interface, message numbers and the /lemo-mod panel, plus the $.lemo helpers other lemo mods use54
35. 947rate-limit-guardmelodic-software/claude-code-pluginsShared rate-limit guard for loop lanes and Claude: a hooks module writes the subscription rate-limit windows to a fixed machine-scope file and toasts window changes (telling Claude too only with model_notices on, off by default), a StopFailure hook records rate-limit stops reactively, and a reader contract fixes how consuming sessions pause and resume.28
36. 948burn-meterOneWave-AI/claude-code-modsLive session cost odometer above the prompt: a burning fuse, real-world comparisons, threshold alerts25
37. 949costclaw-liveucsandman/Agnostic-AICOSTCLAW LIVE: per-request cost, cache decay and repeated-read detection while the session runs, and it serves the Nth identical Read of an unchanged file from its own cache instead of paying for it24
38. 950token-ledgerArunjay4213/claude-modsA per-turn cost and token ledger: a pinned status line with the session cost, the last turn's tokens and the cache hit ratio, and /ledger for a table of the recent turns with their model, tokens, cache reads and writes, duration and cost.11
39. 951spend-ledgerescapeboy/claude-code-kitPer-project token and cost ledger per machine; /spend; monthly note in Svod, with other machines pulled over ssh.97
40. 952cache-keepalivefederbenjamin/cache-keepaliveKeeps an idle session's prompt cache warm with a short prompt 2 min before it expires; capped per model, the last one a handoff3
41. 953clawdlingersinkoc/claude-modsKOZMOS Clawdling: a pixel crab companion that lives above the prompt. It blinks and sways, scuttles while tools run, thinks in bubbles, sweats past 80% context, dozes near the 5-hour limit and dances on a five-turn streak. It earns XP from tools and turns, levels up into a party hat, sunglasses, a scarf and a crown, and quips about what it sees. /clawdling toggles it, /clawdling feed treats it.21
42. 954usage-meterHolyGrail/claude-modsShows context, 5-hour, weekly and per-model weekly limit usage above the prompt19
43. 955desktop-usage-stripwhyashthakker/awesome-claude-code-modsShow quota, reset countdowns, tokens, and cost in a composer strip.109
44. 956mod-eventsbendrucker/claudeStructured event log for mods: `$.modEvents.emit` writes per-session OTel log records as JSONL18
45. 957cache-guardescapeboy/claude-code-kitKeeps the prompt cache warm while idle and holds the first prompt after the cache went cold, with its cost.97
46. 958hudhoobnn/hoobnn-agent-modsclaude-hud 0.13.1 as a mod: model, project, git, context, usage, tools, agents and todos, plus alerts, budget, history, a task summary, a detail pane and switchable themes7
47. 959voice-compactTekkiiiii/the-agencyStartup token diet: rewrites the long CAVEMAN / PONYTAIL MODE ACTIVE hook-context injections into ~150-token compact rules (level kept, pointer to /caveman or /ponytail)7
48. 960context-barBoom-Vitt/boombignose-modsContext window breakdown and prompt-cache countdown above the prompt; /context-bar toggles it.6