#ModGitHub stars

1. 337tangentsbuildwithpulkit/plug-into-claudeGo off on a tangent about any paragraph of Claude's replies, kept out of the main context until you promote it1
2. 338things-you-should-knowfhoces/learning-claude-codeCourse example mod: a band above the prompt with the session facts you tend to forget (files edited since the last commit, last turn's cost, last failed command, an oversized CLAUDE.md), plus /know to print them.1
3. 339tickturndimakotov1c/tickturnTime, tokens and cost of each Claude turn and the session total: a band above the prompt and a /time pane. Russian or English UI by the system language.1
4. 340time-machinexzwache/claude-time-machineEvery Claude turn becomes a snapshot: review what changed step by step, undo it, or travel back. Local, zero tokens.1
5. 341token-almanacCookPiu/token-almanacSession and machine-wide token usage, plan limit meters with reset countdowns, and an estimate of how long each limit lasts, fitted to your own history.1
6. 342token-breakdownzh10only1/claude-code-modsNeon HUD above the prompt with your context window's token usage by category, plus anime colour themes and a /tokens detail pane1
7. 343token-hamstervaleryia-piatrova/token-hamsterClaude Code mod that shows token usage, 5-hour and weekly limits, reset countdown and cost per turn as an animated hamster above the prompt1
8. 344token-panelflowmux-ai/claude-token-panelA pane listing each prompt's token usage and its cost at standard API (Enterprise usage) rates; /token-panel turns it on and off1
9. 345token-watchnevermemo/token-watchPlan usage, the context window and the prompt cache countdown as a banner above the Claude Code prompt, with burn rates, alerts and an opt-in keep-warm. TW Settings picks what it shows; TW Monitor lists every session's context and cache. /token-watch hides the banner, or prints it as text where it can't be drawn.1
10. 346token-weatherhamza-siddiq/token-showersA live forecast of the context window, in the band above the prompt. /token-weather turns it on or off.1
11. 347token-weathertravisoa/claude-modsA live forecast of the context window and the 5-hour and weekly quota, drawn above the prompt.1
12. 348token-weather-usagePedroLaRosa/claude-codeDemo: colored pills above the prompt: context tokens with weather, 5h/7d limits vs time elapsed, prompt cache time left, session cost, running subagents. No network, no files, no process access.1
13. 349tools-usageFazzani/claude-modsSide pane listing the tools used in the session (built-in, MCP, skill, agent, plugin, hook) with calls and token consumption.1
14. 350transcript-makeoverBroo37/claude-modsEnds every tool row with a check or a red cross and how long the call took, and every turn with a receipt: time, tools, failures, cost and share of the five-hour limit1
15. 351trimmodmyclaude/claude-code-modsLong shell output, folded before Claude reads it. Errors, the start and the end stay; you see about how many tokens that saved.1
16. 352usage-bandAuspexlabs/usage-bandLive Claude plan usage in Claude Code: 5-hour, 7-day and per-model weekly windows as slim meters, in the desktop app and the terminal1
17. 353usage-bandiamkhalid2/usage-bandMod: a slim retro line above the prompt showing your plan's 5-hour and weekly usage limits.1
18. 354usage-barrichardcsuwandi/claude-modsUsage bars (context, 5h, 7d, cost) above the prompt plus an auto-compact nudge; toggle with /usage-bar1
19. 355usage-meterewxgwy1987/claude-code-usage-meterShows plan rate-limit usage, session cost, context fill and a per-task token estimate above the prompt1
20. 356usage-meterg-campillo/claude-modsPlan usage under the prompt: 5-hour, weekly and Fable limits with reset times, plus prompt-cache expiry1
21. 357usage-meterMurtadha-Najem/claude-usage-meterShows what each request and each session took of your Claude plan's 5-hour and weekly limits1
22. 358usage-pacediazgonza17/usage-paceFranja sobre el input con el % usado de la sesión de 5 horas y de la semana, el tiempo al reset y un semáforo de ritmo1
23. 359usage-paneljamesnguyen1309/claude-usageLive Usage pane and a band above the prompt: when your tokens reload, calls, cost, context and rate limits; each prompt's tokens, models and subagents; and each limit's burn rate and forecast; and export or import the context (/usage-panel).1
24. 360usage-panelSiigari/usage-panelA /meter pane with your spend, pace, token mix, forecast, and plan week, plus /meter web: a full report that reads every Claude Code transcript on this computer and evaluates your usage.1
25. 361usage-ringOualid0/claude-modsA band above the prompt for your limits, this chat's context, prompt cache and todos, and its token total and rate1
26. 362usage-tickeraycandv/claude-usage-meterA usage board for Claude Code: a weekly pace gauge and a sliding ticker of your spend per model, in the terminal and on the desktop.1
27. 363usage-wrapupDaKev/usage-wrapupWhen your plan usage gets low, tells every running agent to wrap up before the limit cuts it off.1
28. 364visual-companionsYiftachCohen/visual-companionsDraws agent ```viz blocks as compact visuals, keeps the latest headline above the prompt, /catchup shows recent ones. Costs the model ~400 cached prompt tokens + ~80 per visual.1
29. 365wtf-meterdreamiurg/wtf-meterCounts the swearing in your prompts (English, German, Polish, Russian, Ukrainian): a heat meter, a swear jar, or Bluey-style child-friendly swaps1
30. 366token-metermidudev/better-claudeEach turn's tokens and the session's running total, in color at the end of the hint line under the prompt.240
31. 367harness-opsmelodic-software/claude-code-pluginsClaude Code operations: audit-skill-visibility (skills the listing budget hides), inventory (every invocable surface), audit-install-state, audit-performance (slowness), audit-mod-posture (mods and the guard), audit-native-overlap (skills duplicating built-ins), observability (telemetry), known-issues, changelog, behavior-probes, prerequisites, check, machine-profile, plugins (update the fleet), morning-brief, lanes (background loop sessions), setup. Plus opt-in hook event logs.28
32. 368context-barhamzafer/claude-code-modsYour context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. /context-bar shows or hides it.426
33. 369context-meterescapeboy/claude-code-kitBand above the prompt: context fill, cache read, cost, plan limits; warns at 50%/70%; Handoff button and /handoff past 70%.97
34. 370cache-paneldanyuchn/claude-modsPassive 50-minute prompt-cache reminder with a keyboard/mouse panel: keep warm, ping once, or compact, with live cost estimates.6
35. 371abo-usagetw67/claude-modsZeigt die Nutzung des Claude-Abos live als farbige Balken über dem Eingabefeld, mit Reset-Zeit, sowie die Higgsfield-Credits
36. 372active-time0xGondarxyz/claude-code-modsCounts the time you really spend with Claude Code (typing and Claude working, not an idle terminal) and shows it in the status line and /claude-time.
37. 373activitygveshk/barebone-modsA live crew panel: every agent, its model, effort, tokens and estimated cost, with a friendly pixel crab.
38. 374agent-context-pruner9Tech-Solutions/agent-context-prunerReplaces Claude Code's compaction summary with decision-model pruning: stale tool calls and results are dropped or truncated, everything kept stays verbatim.
39. 375agent-deckNeedSomeFoodMr/claude-modsA pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fill, tokens, estimated cost and time, with totals on top and the finished ones kept below; while agents work, one line above the prompt says how the run stands.
40. 376agent-deckPrabal-Singh/claude-modsA pane on the right that tracks this session's subagents as a tree: status, current action, files changed, tokens and cost
41. 377agent-efficiencypoppydad/agent-efficiencyTracks each subagent's model, tokens, tools and time, scores whether a cheaper model would have done, and keeps a bounded per-repo log under ~/.claude/agent-efficiency.
42. 378agent-paradedavep-s20/claude-modsA side panel of animated avatars for the main agent and every subagent: what each is doing, its tokens and tools, and when it finishes
43. 379agent-partyytruong11201/claude-code-modsYour running subagents as 16×16 pixel heroes above the prompt: their task, what they are doing, time, tokens, and a voice that tells their status
44. 380agent-radarfbrogno/claude-modsAlle Claude-Code-Sitzungen und Subagents auf einen Blick, Kaltstart-Wächter gegen teure Cache-Neuaufbauten, Keepwarm (Cache in der Pause per Mini-Ping warm halten), Modellwahl-Pflicht für Subagents, Such-Agents auf Haiku.
45. 381agent-routerCiroVilmer/jev-agent-routerPicks the model and effort of every subagent from its task type; with hot mode on, raises them when the 5-hour window resets with usage to spare
46. 382agent-treerussellpope/claude-modsPane of the herdr agents this session spawned, and theirs: status, model, context, cost, ticket. /agent-tree toggles it; a global view lists every herdr agent.
47. 383agent-treeTheClaessens/thomas-claude-modsLive graph of this session's agent, its subagents and theirs: model, context, tokens, status and assignment.
48. 384agent-watchBarncore/agent-watchA progress bar above the prompt and a live agents panel for any subagents Claude starts, with model, context, cost and time. Fork of johnnyvizz's savvy-progress (MIT).