#ModGitHub stars

1. 673polimento-visualDiogoHSM/claude-modsPill de contexto sob o prompt, borda laranja nas suas mensagens e ícones coloridos por tipo de execução
2. 674polite-compactiondtinth/claude-code-modsShows context tokens and session cost in a gray line above the prompt. At a token threshold, asks the agent to flush notes, then compacts when it says it is ready.
3. 675power-bottombrianSchanbacher/power-bottomA cross-platform Claude Code status line inspired by Trail of Bits' statusline script: model, folder, branch, context bar, cost, time, cache hits, live agents
4. 676powerupbetobetico/powerup/powerups: las lecciones de Claude Code en un panel con botones, en el terminal y en la app de escritorio. Sin tokens: el plugin responde a cada clic sin pasar por el modelo. Las lecciones se descargan con tu clave de acceso y se renuevan cada semana. Mod (function hooks); Claude Code 2.1.284 o posterior.
5. 677pro-limitsrodbegbie/rod-claude-modsGauges for the 5-hour and weekly Claude usage limits above the prompt, toggled with /pro-limits
6. 678prompt-cache-controljakerains/claudemodsPrompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and setting) and corrects itself from request timing. /cache opens a per-turn table.
7. 679prompt-cache-controlzadoli/claude-modsPrompt-cache meter above the Claude Code prompt: how many tokens each request read from, wrote to and sent past the cache, a live countdown to the cache's expiry, and what to do about it (keep going, compact or clear). The TTL follows Claude Code's own rules for your account (1 hour on a Claude subscription, 5 minutes on an API key, cloud provider or usage credits, plus the TTL variables and setting) and corrects itself from request timing. /cache opens a per-turn table and /cache settings a pane of on/off toggles; /keepwarm pings the cache after idle stretches so it never lapses (ported from cache-tax).
8. 680prompt-cache-forecastDominikvD/prompt-cache-forecastToken Weather plus Prompt-Cache: Kontextfüllung und darunter, wie viele Tokens gerade im Prompt-Cache liegen und wann er abläuft.
9. 681prompt-cache-watchramankrishna/prompt-cache-watchShows how much of each request the prompt cache served, and tells you when the cache was rebuilt and the likely reason.
10. 682prompt-questtomikng/prompt-questAn RPG layer for Claude Code: earn XP from sharp prompts and lean token use, spend skill points on perks, and learn AI lore.
11. 683prompt-shaperanhtuan23004/claude-modRewrites short, casual prompts with a fast model into Context / Objective / Steps / Output / Constraints, then lets you send the shaped or the original version
12. 684prompterniijoey/prompter-modTalk through what you want, get the right terms and a clean brief for Claude, with this repo's context filled in.
13. 685promptsignPromptSign/promptsign-pluginVerifies signatures on the instruction files Claude Code loads, meaning CLAUDE.md, skills, and agent definitions, before they reach model context. It re-checks a skill bundle before the Skill tool runs it. Sigstore keyless, offline verification against a pinned trust root, no telemetry.
14. 686pruebas-e2efran343/claude-modsCon /playwright, lee el manifest y el contexto del desarrollo y genera y ejecuta pruebas Playwright en la sandbox de Salesforce.
15. 687pulse-cache-taxMrValraven/pulse-modsKeeps the one-hour prompt cache warm during /keepwarm windows and holds a cold send once with its estimated rewrite cost. Pinging runs only after /keepwarm. Fork of karanb192/cache-tax.
16. 688pultEgor062020/claude-code-pultA control panel for Claude Code: quick-reply chips and a status band above the prompt, and a scrolling pane of cards for context, limits, prompt cache, deadlines from your notes, work areas and an SSH server. English and Russian.
17. 689purgarjpoucabanillas-lang/claude-mods/purgar: quita del contexto las salidas viejas de herramientas, sin resumen y sin gastar modelo; /purgar N deja solo los últimos N intercambios
18. 690push-upsRisdon8/push-upsPredicts how long Claude's turn will take and gives you push-ups to do while you wait, in a bar above the prompt. Local only: no model calls, no tokens.
19. 691quackpitimsungbin/quackpit-modA cockpit above your Claude Code prompt. The duck reads the gauges: task progress and how long the work will take, pace, context, plan limits, checks and cost in one instrument panel, with a rubber duck as Master Caution. Zero model tokens by default, no network, no processes, nothing added to context.
20. 692quiet-costarthurglaizal/quiet-costWhat each reply cost, in one quiet grey line under it: an estimated price in dollars, how long it took and the tokens, and more figures you pick. /quiet-cost opens the row that picks them.
21. 693quiet-token-bararthurglaizal/quiet-token-barYour context window as one quiet line above the prompt: a patterned bar, the fill against the compaction point, a compact button and your session and weekly limits, grey until something gets warm. /quiet-token-bar shows or hides it.
22. 694quota-bandandras-gyarmati/claude-quota-bandYour Claude plan's 5h and weekly usage, the context window and the prompt cache's time left, as one line of bars above the prompt
23. 695quota-guardcatsmonster/claude-quota-guardCompacts before the 5-hour/weekly usage limit is hit, pauses until it resets, then resumes the task automatically.
24. 696quota-meterkleyson-carreira/quota-meterBand above the prompt: 5-hour and weekly quota vs. ideal pace, time to reset, session tokens and cost
25. 697rankomilkycode/rankoYour session's figures above the Claude Code prompt: how full the context is and how far off auto-compaction is, the prompt cache, your plan's limits and when they run full, the task list, and a Compact button. Beside them Ranko, the rankello® mascot, shows what Claude is doing: he types, thinks, waves when it waits for you, cheers and naps.
26. 698rd-ledgerJoseph-Ayoub/claude-modsContemporaneous R&D time and AI-usage ledger: engagement hours by business component, list-price usage estimates, a weekly review with buttons, a CPA export, an optional bridge to rd-tracker, and a live Usage pane (cost, context, rate limits, models, subagents, code changes) behind one footer chip. Metadata only, nothing leaves the Mac.
27. 699reply-linesoonavi/claude-modsEnds each reply with one status line: context fill, usage windows and their resets, each repo's unpushed work, and what the turn did. For sessions watched in an app that draws no status lines.
28. 700research-offloadertimothylok/ClaudeCodeModsByTimLokSpots research prompts and keeps them out of the main context: sends them to your own research endpoint (e.g. a NotebookLM bridge) if configured, otherwise makes Claude delegate to a cheap subagent.
29. 701routing-modblackmath88/routing-mod-claudeRoutes each subagent to Haiku, Sonnet or Opus by the [tier:...] tag from your plan. The main session never switches model, so its prompt cache stays intact.
30. 702sabaipanupat-top/claude-sabaiPixel-art band above the prompt: folder, git and node; task progress with Clawd and his moods; a row of subagents; context, session and weekly limits; a toolbar. A Subagents pane with reports, and a Settings pane with raised or flat cards (light and dark), bar styles, alerts and an optional guard with per-rule Block / Ask. In the conversation: tool calls as one-line rows, test results, callout boxes and a receipt at the end of each working turn.
31. 703savepointKYWAxx/savepointContext hygiene with safeguards: checkpoint each finished step, then reset the context to that save, never mid-project.
32. 704savvy-progressBerkay2002/berkays-modsProgress bar above the prompt and an agents panel (/agents-info): running, finished and planned subagents with model, progress, context, cost and time. Crabs for the claude-config scout, builder and reviewer. Copy of johnnyvizz/claude-kit savvy-progress 1.2.0.
33. 705savvy-progressIsaacg1000/isaac-modsProgress bar above the prompt plus a live panel of every subagent with model, tokens, cost and a customizable pixel crab.
34. 706savvy-progressleolimaferreira/savvy-progress-officeAn office of your Claude Code session: the main session and each subagent at their desks, with model, progress, cost, tokens and time; plus a progress band above the prompt. Based on savvy-progress by johnnyvizz.
35. 707scoutermAgNiFiCeNtTaCo/ClaudeModsVegeta's scouter as a side pane: power level, ki (context), stamina and training (rate limits), zeni (cost) and the battle log of this session. Toggle with /scouter.
36. 708scrooge-context-vaulttwentynineteen/scrooge-context-vaultContext window monitor drawn as Scrooge McDuck's Money Bin: coins fill the vault as context fills, and at a set percentage (80% by default) Scrooge dives in for a swim
37. 709sdlc-workflowjayteealao/agent-skillsOne command, `/wf` (`$wf` under Codex), the single SDLC entry point for Claude Code and Codex from one plugin tree. It drives 9 stages, from intake through retro, with per-slice artifacts, runtime-truth verification and PO-confirmed stack fingerprinting. 18 keys: intake, shape, design, slice, plan, implement, verify, review, handoff, ship, retro, probe, yolo, campaign, loop, status, project, docs. Quick and standalone flows are `/wf intake` modes: `fix`, `rca`, `investigate`, `discover`, `audit`, `hotfix`, `refactor`, `update-deps`, `ideate`, `brainstorm`, `adopt`, `optimize`, `simplify`, `task`.
38. 710serhan-progressserhandenizhan/serhan-kitProgress bar above the prompt for /serhan, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time. Derived from johnnyvizz/claude-kit (savvy-progress).
39. 711sessionskryvets/claude-status-bar-modColoured session lines above the prompt: model, effort, folder, git state, context usage, and rate limit bars with pace
40. 712session-bandleonqi-io/claude-code-modsA status row above the prompt (context, cache, usage limits, generated tokens) with a handoff-file action and guided compact.
41. 713session-barNicholasDunham/claude-session-barA session status band above the prompt (context, 5h/7d limits, repo, model, cost, cache) that works in the terminal and in the desktop app
42. 714session-bridgeiddhi-sulakshana/claude-modsLets running Claude Code sessions message each other and hand off context, so one session can plan or audit while another builds.
43. 715session-crewdavidcoulson/session-crewA panel of the side sessions this Claude Code desktop session started (/crew): name, title, status and time, each a savvy-progress crab in a costume that walks while it works, rests while idle and celebrates when done.
44. 716session-dashtsurutanmen/session-dashUsage limits above the prompt, a pane with background work and the file each open Claude Code session is on
45. 717session-deckWasif-ZA/claude-modsSide pane: what is running (with Stop), files made this session (with Open), and a context gauge
46. 718session-flowTheBabaYaga/claude-session-flowA live pane that shows the session as a flow: each prompt, its phases, its subagents and its cost
47. 719session-hud0neWithNothing/session-hudLive HUD under the prompt: context window, rate limits, model, effort, session time, cost, edits, agents, tools and skills
48. 720session-infofrpatino6/claude-mods/info pane: session tokens, plan-aware quota/balance, and the skills, MCP tools and commands used