#ModGitHub stars

1. 289hudBedirYilmaz/claude-crt-hud-modA CRT-style status panel above or below the prompt: model, project and git, context with a compact button, plan usage, prompt cache, cost and running tools. /hud toggles it.1
2. 290hudSamarth2001/claude-pluginsA live usage cockpit above the prompt: context, plan limits with pace forecasts, and cost by day, week and month, in a one-line glance that expands into tabs and a dashboard pane1
3. 291idle-compactbenredmond/idle-compactCompacts an idle session just before its prompt cache expires, so returning does not re-write the full context1
4. 292idle-compactorymnao/dotfilesCompacts an idle Claude Code session shortly before its 1-hour prompt cache expires, so coming back later re-sends a short summary instead of the whole conversation uncached.1
5. 293idlecrashgrozoww/idlecrashCrash with fake tokens against other people who are also waiting for Claude: in a pane, in a terminal and in the desktop app.1
6. 294image-peekyoungOman/pill-modsimage-view (jarrodwatts) fixed for newer Claude Code: thumbnails of pasted images above the prompt, read from $TMPDIR/clipboard-*.png.1
7. 295jev-contextJayDoubleu/cc-mod-jevJev-scored context pruning for Claude Code through OpenRouter: at compaction every tool call and result is scored by TypeSafe's Jev decision model, stale ones are dropped or truncated, everything kept stays verbatim. An optional gate truncates oversized tool outputs as they arrive.1
8. 296jojo-sbr-token-usagedodofk/jojo-sbr-token-usageContext window usage as one line above the prompt, told as a Steel Ball Run race: Gyro's five lessons and a horse running to the finish flag.1
9. 297latex-renderchang-07/cc-latexDraws display LaTeX ($$...$$ or \[...\]) in assistant replies as typeset images (tectonic + kitty graphics)1
10. 298leo-modsquango2304/leo_claude_modLeo's Claude Code mods: usage bars, limits, cost, prompt cache countdown, active time and running agents1
11. 299limitsVaitaR/claude-code-limitsClaude Code mod: your 5h/7d quota, context window, prompt-cache time left and session cost on one line above the prompt, with per-subagent cost on hover1
12. 300limits-bandburnrate-ai/burnrateBand above the prompt: 5h/7d limits with reset timers, context fill, cache hit rate and what fills your context.1
13. 301litellm-keyjuninmd/cc-litellmSee your LiteLLM virtual key inside Claude Code: budget, spend, limits, expiry, models and recent usage. Admins can also create and edit keys, grant extra budget and read router fallbacks.1
14. 302lk-agent-mapconnectwithub/loopkeeperSee and cap your subagents: cards with cost, tokens, context and progress, spawn caps with an override you approve, tree and team views, idle alerts and a Stop button.1
15. 303lk-token-budgetconnectwithub/loopkeeperStop runaway token spend: budgets per session and per subagent with warn, deny-agents or stop actions, plus a prompt-cache countdown, cold-cache pings and keep-warm.1
16. 304lookoutStartupBros-com/hov-marketplaceA second pair of eyes while Claude works. Every few model steps it asks one tool-less fork of the session (served from the prompt cache) whether there is something you should know and might miss, and shows the answer above the prompt. No model call while nothing draws the session.1
17. 305luna-prunerluancamara/luna-prunerContext-size meter, noisy tool-output pruning and a cost audit for Claude Code, using OpenAI Decisions (gpt-6-luna).1
18. 306model-pickerjuampymdd/claude-code-model-pickerA band above the prompt to pick which model, and which version of it, runs the next requests, with cost, tokens and cache stats an animated pane of charts and live agents for the whole session, and a tab where Claude notes the theory behind what it builds.1
19. 307model-routerTFoxik/claude-model-routerModel and effort routing per kind of work, with prompt-cache and cost tracking, a cold-cache guard, and an optional learn mode that explains what each choice cost1
20. 308neon-hudezequielcutin/claude-hud-pluginA live HUD above the prompt: turn timer, active skill, subagent tree, git state, rtk token savings and one-click session checkpoints1
21. 309nervgonzalonicolasr/claude-code-nervBarra lateral estilo Evangelion: cuota, contexto, qué hace el agente, PRs, subagentes y alertas1
22. 310overallsTroepster/overallsStatus band above the prompt: context weather, usage limits, and the Ponytail and Caveman levels1
23. 311pasekSzewowsky/mody-claude-codePasek nad promptem: repo, branch, koszt, kontekst, limity 5h i tygodniowy, licznik ciepłego cache, przyciski REC i Handoff1
24. 312pastichenullphase-net/enfurbishAmbient language learning. Hooks weave vocabulary into ordinary Claude Code sessions — stale items you are forgetting, a small budget of new terms drawn from the work itself, and anything you use unprompted recorded rather than taught back at you. The ledger is a markdown file you own, written by a CLI rather than by hand.1
25. 313pedidosmatecocidocontortafritas/growth-lab-mods/pedidos: panel con los pedidos de hoy de tu Tiendanube y cuánto vendiste, sin gastar tokens1
26. 314pixlingscglremrcn/pixlingsA tiny pixel creature that lives above your Claude Code prompt. It counts down your prompt cache and guards it on model switches, wakes Claude when your usage limit resets, brings a helper for every subagent, makes sound on Windows and Linux, yelps before risky commands, rolls its eyes at "You're absolutely right", and brings back your old /buddy.1
27. 315prompt-cache-controlNasrallah-Adel/claude-prompt-cache-controlPrompt-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. A Clear button writes a handoff brief from the transcript with a cheap model, runs /clear, and sends the brief to the fresh conversation.1
28. 316prompt-forgetomikng/prompt-forgeSpends your Claude Code tokens where they count: moves a new task into a fresh session (a new terminal window, or its own git worktree) instead of dragging a long conversation along, and runs small, clear tasks on Sonnet.1
29. 317prompt-statusmatr1xp/local-modsTwo-line status above the prompt: model, directory, git branch, context fill and rate-limit usage1
30. 318quanta-costawukonigcom/quanta-costaQuanta Costa: your Claude subscription period, weekly limit with a pace forecast, session cost and plan value, as bars right above the Claude Code prompt.1
31. 319quota-bandkuan0808/cliproxy-kitAccount, quota, context and cache cards above the Claude Code prompt, with handoffs and a warning before a turn rewrites the prompt cache; quota and routing come from CLIProxyAPI with the quota-pilot plugin1
32. 320regiapurpleheads2026/Mod_claudeA graphic control room for Claude Code: a live radar of agents, skills and tools, with context and usage limits, in motion.1
33. 321review-gaterlorenzo/ai-coding-setupThe review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls -- almost all of them -- cost no subprocess at all, and a blocked commit can be put to you as a question instead of refused outright. The decision itself is still bin/review-gate, run only for a command that mentions a commit, so both routes read the same receipts and cannot disagree.1
34. 322savvy-progresslippdev/lippstackAgents panel (/agents-info): running, finished and planned subagents with model, context, tokens and time, plus the account plan quota (5h and weekly). Fork of johnnyvizz/claude-kit savvy-progress with new Clawd costumes.1
35. 323session-cardsalan-oliv/claude-modsSession stats above the prompt: repo folder, branch and session name, then cards for model, effort, context, startup, limits and cost1
36. 324session-hudanderson-spider/claude-modsA card above the prompt: model, the repository, folder and branch, context and cache; the five-hour and seven-day limits with their pace; the running subagents with their type, model and effort, and the tokens they used; what the last turn sent and added, edits and errors; when turned on, next steps to tick and put in the prompt; and /session-panel, a pane with every agent the session ran and the last 15 minutes.1
37. 325session-insightpakornkub/session-insightShows session usage, the skills used and the agents that ran, with a detail view and an agent diagram1
38. 326slick-barmustafa89/my-claude-code-modsOne-line session bar above the prompt: model, effort, repo, branch, context gauge, prompt cache health, rate limits, cost1
39. 327status-bandfinalpantasy/claude-mod-packOne tidy band above the prompt: usage limits and spend, context weather, what the last turn did, and your open tasks, each on its own labelled row, with Compact now and Handoff buttons always there.1
40. 328status-dashmwpark-aa/claude-terminal-modsBand above the prompt with gradient gauges (context, 5-hour and weekly limits) and toasts for finished turns, notifications and a full context.1
41. 329status-deckwellbrained/status-deckA status deck above the prompt: plan limits, context window, git branch, prompt cache and more, in six styles, each part switchable. Options: /status-deck-options1
42. 330status-hudhymleong/claude-modsA bar above the prompt showing current activity, 5-hour limit, weekly limit and context window.1
43. 331status-pillscarreirodev/mod-status-pillsA band of pills by the prompt, under it in the terminal and above it on the desktop and in the VS Code extension: model and effort, context, the 5-hour and 7-day limits with their resets, project and branch, and the prompt cache1
44. 332statusbarMomoChenisMe/claude-code-modsStatus rows under the Claude Code prompt: model and effort pills, and context, 5-hour, 7-day and Fable usage bars1
45. 333statuslinem-tababi/statuslineKeeps the prompt cache warm with a tool-less fork shortly before it expires and shows the cache clock and a per-session switch in the prompt hint line (/keepalive on|off|status).1
46. 334subagents-plusalgonormative/subagents-plusSee your subagents and workflows: a /subagents pane with an expandable tree of every subagent and workflow run (live activity, phases, tokens, transcripts) and a timeline, live cards on Agent rows (and Workflow rows in a terminal), and a band above the prompt1
47. 335tabbyalexskvo10/claude-tabbyA calm dashboard above the prompt: context and rate limits with forecasts, git and PR checks, tests, focus, a mini TODO and Tabby the cat1
48. 336tableromatecocidocontortafritas/growth-lab-mods/tablero: ventas de Tiendanube + tráfico de Google Analytics + Meta Ads en un panel, con MER y conversión, sin gastar tokens1