#ModGitHub stars

1. 577guardian-cacheprompteafacil-hub/mods-claude-codeMuestra cuánto le queda al caché, el contexto y los límites, con botón de traspaso de sesión.
2. 578haiku-compactkjhq/haiku-compactSquish your context with Haiku when the prompt cache goes cold, so your main model re-caches a short summary instead of the whole transcript. One line above the prompt shows up only when the cache is cold, says what a squish saves, then what it saved.
3. 579hamsternickpotet/claude-hamsterA pixel hamster above the prompt in the Claude desktop app: it lives on your context window and tells you when to compact or clear. 110 tips on saving tokens, skills, plugins and MCP servers.
4. 580handoverpradyb/claude-mods/handover writes a handover note from the conversation (served from the prompt cache), saves it under ~/.claude/projects/<project>/handovers/<session-title>.md, clears the session and continues from the note in a fresh context. Suggests it when context passes a threshold.
5. 581hawkeyeakkaradej/hawkeyeBands above the prompt: session status dot, prompt-cache countdown, context ring, Reborn (continue in a new session), Suggest, Auto effort and auto-answered recommendations
6. 582heads-upsoenkenils/claude-code-modsWatches the running session and shows a heads-up when something is off: failing tools or tests in a row, edits outside the project, a context spike, or a run that stalls.
7. 583hearth-bandkoenrohrer/hearth-bandHearth: a pixel creature per model beside a prompt-cache campfire, with your limits and context, animated above the prompt
8. 584hook-flowlegibleco/hook-flowA side pane that shows Claude Code's agent loop as it runs: every hook event, a flow chart of the loop, a span timeline of each turn, and the tokens and dollars spent
9. 585hudbenelog/claude-modsA colored line above the prompt with plan, organization, model, effort, context usage, prompt-cache state and rate-limit quota
10. 586hudim-ksc/ks-claude-code-modsA band above the prompt: usage limits with a pace verdict, context, branch and cost, with Compact and collapse buttons.
11. 587hudsantisanudo13/claude-hudRight-docked pane: context used, session spend, remaining credit and clickable pending tasks that fill a ready-made prompt
12. 588hudcadeg761007/hudcadeA pixel-art HUD for Claude Code: context, cost, cache, agents and rate limits at a glance, little 8-bit scenes while Claude thinks, and Telegram notifications.
13. 589huginntauantcamargo/claude-modsHuginn, Odin's raven of thought: matches model and effort to each step. Skills that set the effort for the rest of the turn without breaking the prompt cache (/huginn:deep, /huginn:quick, /huginn:max), Sonnet, Opus and Fable subagents for delegated work, a session-start policy that tells Claude when to use which, and a status-line chip with the active tier.
14. 590idle-compactm-mizutani/dotfilesCompact the conversation once after 50 idle minutes, while the 1h prompt cache is still warm.
15. 591idle-compactShadowDog007/claude-modsRuns /compact while the session sits idle waiting on background work, right before the prompt cache expires.
16. 592idle-compactwryskware/claude-modsCompacts the session once it is 20% full and has been idle 50 minutes, while the prompt cache is still warm.
17. 593idle-compactxyjk0511/idle-compactCompact once after 50 idle minutes, while the 1h prompt cache is still warm. Works in the desktop app and SDK sessions too.
18. 594inline-repliesbetoescobar46/pitutoAnswer Claude's questions and quote its paragraphs with a click: numbered questions with clickable options, a on every paragraph, and the full context sent along with your message.
19. 595integralserg-yalosovetsky/integralOne HUD above the prompt: context bar with compact/checkpoint, plan limits, MCP health, plan progress. Replaces context-bar-compact and mcp-doctor.
20. 596jc-hud-modkarimdjaafar/jc-hud-modJC HUD — mod Claude Code : barre d'instruments Jasmine Conseil (contexte, forfait, modèle, horloges)
21. 597jevgecm0/jev-modAdds $.jev: typed Choice, Score and Noul judgments from TypeSafe's Jev, with a timeout and validated answers, for other mods to call.
22. 598jev-compactHAR5HA-7663/jev-compactContext compaction that prunes instead of summarising: rules drop exploration output and hook noise locally, Jev ranks the rest against a budget, a note says what was removed, and removed outputs are archived for the brain. Falls back to the built-in summary when it cannot do better.
23. 599jev-compact-triggerHAR5HA-7663/jev-compactCompanion to jev-compact: watches context use after every turn and starts a compaction at the configured percentage. Separate plugin on purpose — the engine skips a plugin's own session.compact hook when that plugin raises the compaction, so the trigger must come from outside jev-compact for the pruning to run.
24. 600jev-skill-suggestionAnatoliyShk/bulgolingoKeeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at all, a second re-reads the top three with their SKILL.md and can reject them all. The winner's SKILL.md is attached to the prompt, so the skills can be hidden from the model altogether (/jev-skill-suggestion:setup makes them user-invocable-only and /context counts them at 0). Falls back to the engine's built-in classifier when no key is set.
25. 601k9sholdennguyen/claude-code-setupA live, interactive k9s terminal in a pane (k9s runs under a private tmux server, so kube auth and context come from the shell that launched Claude Code), plus two tools so the model can read the k9s screen and send it keys. While k9s runs, Bash calls that invoke kubectl are refused and the model is pointed at those tools; kubectl works as usual otherwise. One server per Claude Code process, a watchdog and a start-up sweep keep orphans from surviving, and an idle stop keeps k9s from polling the cluster unseen.
26. 602kamehamehaAurumdev952/claude-code-kamehamehaContext usage as a pixel-art showdown: a hero laughs off a kamehameha that grows with the context window, strains harder and harder, and at 95% it's GAME OVER, please compact
27. 603kc-usage-bandkcsujeet/kc-claude-kitA row of pills above the prompt: model, git branch, context fill, 5h and 7d rate limits with reset times, input/output/cache tokens, and session cost, with usage figures turning amber from 70% and red from 90%
28. 604keep-goingJvrd97/claude-keep-goingRetries a turn that died on a transient API error (500, 529 overloaded, timeouts, connection resets) with backoff, and resumes work when the usage limit resets.
29. 605keep-goingsomeonewithpc/claude-mod-keep-goingKeeps unattended sessions going: continues after usage limits reset, retries API overload with backoff, resumes cut-off responses, and compacts idle sessions before the prompt cache expires.
30. 606keepcachewarmHitEmUp/keepcachewarmZeigt über dem Eingabefeld, wie lange der Prompt-Cache noch warm ist, mit Kontext, Limits und Kosten, und hält ihn auf Wunsch in Pausen warm.
31. 607keyfobshiran-yu/keyfobKeep your API keys and tokens out of your Claude Code conversations: tokens pasted as keyfob: lines are stored before the model sees them, Claude asks for a key through the /keyfob panel, a guard stops Bash commands that would print one, and each command gets only the keys it needs from the OS keystore
32. 608kontext-anzeigehb03/claude-modsHinweise, wann /compact, /clear oder Weitermachen sinnvoll ist: Kontextfüllung, Prompt-Cache, Auto-Compact und Limits. Schreibt die Werte für die Statuszeile, die Warnungen zeigt offene-punkte über der Eingabe; /kontext zeigt Details, /kontext test probiert Einblendung, Statuszeile und Systemmeldung aus.
33. 609last-callSunkanxx/ModsStops work at a clean point before the 5-hour (or 7-day) usage limit, keeps the prompt cache warm while waiting, and continues the work after the reset.
34. 610ledgerRobGruhl/claude-modsDURABLE: counts turns and tool calls per session ($.state) and for all time ($.store), shown in a band above the prompt
35. 611leitstandfbrogno/claude-modsLeitstand: Live-Dashboard für alle Claude-Code-Sitzungen: Titel statt Kürzel, leere Sitzungen gebündelt, kontoweite Limits, Crew-Übersicht je Sitzung mit gemessenen Token-Zahlen, Kosten und Cache-Trefferquote; Subagents als animierte Pixel-Männchen.
36. 612limit-lenscristi71000/limit-lensA band above the prompt showing this session's share of your usage limits, its API-equivalent cost, and what the same work would cost on each Claude model
37. 613limit-meterAlyan-khattak/Claude-Code-ModsYour plan's 5-hour and weekly usage limits above the prompt: percent used, time to reset, used today, with warnings at 75% and 90%.
38. 614limit-radarJvrd97/claude-limit-radarYour 5h/7d subscription limits, a burn-pace forecast and a cold-cache warning, shown above the prompt only when there is something to act on.
39. 615limitesngz-fernando/claude-code-limitesVes tus limites de Claude Code sin pedirlos: contexto, ventana de 5h, ventana de 7 dias y gasto, en una linea sobre el prompt.
40. 616limitpacefstandhartinger/limitpaceLive subscription usage and pace bars, with an optional provider-neutral delegation advisor.
41. 617limits-forecastdanylo-konovalenko-brainsport/limits-forecastForecasts whether you will hit your 5-hour or weekly usage limit before it resets, learns your usage pattern over time and suggests what to change.
42. 618limits-leftimgidedin/claude-mod-limits-leftShows how much of the 5-hour and weekly limits is left in the prompt footer, tracks how fast they are being used, and warns before one runs out.
43. 619limits-metermarcelmatula/claude-modsSession (5 h) and weekly usage limits as small progress bars with reset countdowns, plus whether the prompt cache is still warm and for how long and the session's name, centred under the prompt; /limits hides or shows them
44. 620linecatfivood/linecatA cat walks a line your Claude Code session unfolds, wearing what Claude is doing overhead; plus retro paper-panel styling for messages, tool rows and a usage monitor
45. 621local-llmdeadpixel3/claude-local-llmDelegate routine coding work to a local OpenAI-compatible model and see its live stats (time, tokens, speed, context) above the prompt
46. 622loop-breakerccdwyer/loop-breakerStops the agent repeating the same failing command or undoing its own edits, and shows a stuck meter above the prompt
47. 623lossless-compactionyottayoshida/lossless-compactionLossless context compaction for Claude Code: old tool output moves to local files and comes back unchanged by id, or by what it is about with a Jev key.
48. 624martian-baseChaveex/martians-mods-4-claudeUn Martien de Martian Base au-dessus du prompt, animé selon ce que fait Claude, avec les barres d'usage session (5 h) et semaine